cr

* Update issue templates

* Update issue templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,31 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: bug
+assignees: ''
+
+---
+
+**Describe the bug**
+Write a concise description of what the bug is.
+
+**Files**
+If possible, please provide the PDF file causing the issue.
+
+**Job ID**
+If you have it, please provide the ID of the job you ran.
+You can find it here: https://cloud.llamaindex.ai/parse in the "History" tab.
+
+**Client:**
+Please remove untested options:
+ - Python Library
+ - API
+ - Frontend (cloud.llamaindex.ai)
+ - Typescript Library
+ - Notebook
+
+**Additional context**
+Add any additional context about the problem here.
+What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
+Screenshots, code snippets, etc.

.github/ISSUE_TEMPLATE/custom-issue.md

@@ -0,0 +1,10 @@
+---
+name: Custom issue
+about: Not a bug nor a feature request
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,10 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: enhancement
+assignees: ''
+
+---
+
+

.gitignore

@@ -2,3 +2,4 @@
 __pycache__/
 *.pyc
 .DS_Store
+.idea

.pre-commit-config.yaml

@@ -72,7 +72,7 @@ repos:
         args:
           [
             "--ignore-words-list",
-            "astroid,gallary,momento,narl,ot,rouge,nin,gere,te,inh",
+            "astroid,gallary,momento,narl,ot,rouge,nin,gere,te,inh,vor",
           ]
   - repo: https://github.com/srstevenson/nb-clean
     rev: 3.1.0
@@ -84,3 +84,5 @@ repos:
     hooks:
       - id: toml-sort-fix
         exclude: ".*poetry.lock"
+
+exclude: .github/ISSUE_TEMPLATE

README.md

@@ -1,14 +1,29 @@
 # LlamaParse
 
-LlamaParse is an API created by LlamaIndex to efficiently parse and represent files for efficient retrieval and context augmentation using LlamaIndex frameworks.
+[![PyPI - Downloads](https://img.shields.io/pypi/dm/llama-parse)](https://pypi.org/project/llama-parse/)
+[![GitHub contributors](https://img.shields.io/github/contributors/run-llama/llama_parse)](https://github.com/run-llama/llama_parse/graphs/contributors)
+[![Discord](https://img.shields.io/discord/1059199217496772688)](https://discord.gg/dGcwcsnxhU)
+
+LlamaParse is a **GenAI-native document parser** that can parse complex document data for any downstream LLM use case (RAG, agents).
+
+It is really good at the following:
+
+- ✅ **Broad file type support**: Parsing a variety of unstructured file types (.pdf, .pptx, .docx, .xlsx, .html) with text, tables, visual elements, weird layouts, and more.
+- ✅ **Table recognition**: Parsing embedded tables accurately into text and semi-structured representations.
+- ✅ **Multimodal parsing and chunking**: Extracting visual elements (images/diagrams) into structured formats and return image chunks using the latest multimodal models.
+- ✅ **Custom parsing**: Input custom prompt instructions to customize the output the way you want it.
 
 LlamaParse directly integrates with [LlamaIndex](https://github.com/run-llama/llama_index).
 
-Free plan is up to 1000 pages a day. Paid plan is free 7k pages per week + 0.3c per additional page.
+The free plan is up to 1000 pages a day. Paid plan is free 7k pages per week + 0.3c per additional page by default. There is a sandbox available to test the API [**https://cloud.llamaindex.ai/parse ↗**](https://cloud.llamaindex.ai/parse).
+
+Read below for some quickstart information, or see the [full documentation](https://docs.cloud.llamaindex.ai/).
+
+If you're a company interested in enterprise RAG solutions, and/or high volume/on-prem usage of LlamaParse, come [talk to us](https://www.llamaindex.ai/contact).
 
 ## Getting Started
 
-First, login and get an api-key from [**https://cloud.llamaindex.ai ↗**](https://cloud.llamaindex.ai).
+First, login and get an api-key from [**https://cloud.llamaindex.ai/api-key ↗**](https://cloud.llamaindex.ai/api-key).
 
 Then, make sure you have the latest LlamaIndex version installed.
 
@@ -23,7 +38,22 @@ Lastly, install the package:
 
 `pip install llama-parse`
 
-Now you can run the following to parse your first PDF file:
+Now you can parse your first PDF file using the command line interface. Use the command `llama-parse [file_paths]`. See the help text with `llama-parse --help`.
+
+```bash
+export LLAMA_CLOUD_API_KEY='llx-...'
+
+# output as text
+llama-parse my_file.pdf --result-type text --output-file output.txt
+
+# output as markdown
+llama-parse my_file.pdf --result-type markdown --output-file output.md
+
+# output as raw json
+llama-parse my_file.pdf --output-raw-json --output-file output.json
+```
+
+You can also create simple scripts:
 
 ```python
 import nest_asyncio
@@ -53,6 +83,39 @@ documents = await parser.aload_data("./my_file.pdf")
 documents = await parser.aload_data(["./my_file1.pdf", "./my_file2.pdf"])
 ```
 
+## Using with file object
+
+You can parse a file object directly:
+
+```python
+import nest_asyncio
+
+nest_asyncio.apply()
+
+from llama_parse import LlamaParse
+
+parser = LlamaParse(
+    api_key="llx-...",  # can also be set in your env as LLAMA_CLOUD_API_KEY
+    result_type="markdown",  # "markdown" and "text" are available
+    num_workers=4,  # if multiple files passed, split in `num_workers` API calls
+    verbose=True,
+    language="en",  # Optionally you can define a language, default=en
+)
+
+file_name = "my_file1.pdf"
+extra_info = {"file_name": file_name}
+
+with open(f"./{file_name}", "rb") as f:
+    # must provide extra_info with file_name key with passing file object
+    documents = parser.load_data(f, extra_info=extra_info)
+
+# you can also pass file bytes directly
+with open(f"./{file_name}", "rb") as f:
+    file_bytes = f.read()
+    # must provide extra_info with file_name key with passing file bytes
+    documents = parser.load_data(file_bytes, extra_info=extra_info)
+```
+
 ## Using with `SimpleDirectoryReader`
 
 You can also integrate the parser as the default PDF loader in `SimpleDirectoryReader`:
@@ -87,6 +150,16 @@ Several end-to-end indexing examples can be found in the examples folder
 - [Advanced RAG Example](examples/demo_advanced.ipynb)
 - [Raw API Usage](examples/demo_api.ipynb)
 
+## Documentation
+
+[https://docs.cloud.llamaindex.ai/](https://docs.cloud.llamaindex.ai/)
+
 ## Terms of Service
 
 See the [Terms of Service Here](./TOS.pdf).
+
+## Get in Touch (LlamaCloud)
+
+LlamaParse is part of LlamaCloud, our e2e enterprise RAG platform that provides out-of-the-box, production-ready connectors, indexing, and retrieval over your complex data sources. We offer SaaS and VPC options.
+
+LlamaCloud is currently available via waitlist (join by [creating an account](https://cloud.llamaindex.ai/)). If you're interested in state-of-the-art quality and in centralizing your RAG efforts, come [get in touch with us](https://www.llamaindex.ai/contact).

examples/caltrain/caltrain_text_mode.ipynb

@@ -0,0 +1,529 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c148b65e-e8a6-476e-86ba-bf6a73d479c7",
+   "metadata": {},
+   "source": [
+    "# RAG over the Caltrain Weekend Schedule \n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/caltrain/caltrain_text_mode.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This example shows off LlamaParse parsing capabilities to build a functioning query pipeline over the Caltrain weekend schedule, a big timetable containing all trains northbound and southbound and their stops in various cities.\n",
+    "\n",
+    "Naive parsing solutions mess up in representing this tabular representation, leading to LLM hallucinations. In contrast, LlamaParse text-mode spatially lays out the table in a neat format, enabling more sophisticated LLMs like gpt-4-turbo to understand the spacing and reason over all the numbers.\n",
+    "\n",
+    "**NOTE**: LlamaParse markdown mode doesn't quite work yet - it's in development!"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef115dbe-b834-4639-828e-e2c11aef710b",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Download the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e6ae2e38-30c9-4865-aa13-47780bc3848f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "335ce1d0-757a-4f09-846e-21c409768871",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://www.caltrain.com/media/31602/download?inline?inline\" -O caltrain_schedule_weekend.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45fa9120-65bb-4772-9db7-53e7cecf9adc",
+   "metadata": {},
+   "source": [
+    "## Initialize LlamaParse\n",
+    "\n",
+    "Initialize LlamaParse in `text` mode which will represent complex documents incl. text, tables, and figures as nicely formatted text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54aa9579-84d4-49bc-ab54-5474e69c1188",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/jerryliu/Programming/llama_parse/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 5f73353a-1f4b-480d-9eea-58d1d22b75f6\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "docs = LlamaParse(result_type=\"text\").load_data(\"./caltrain_schedule_weekend.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "602756b2-9ea1-4519-a8e3-c773ec624205",
+   "metadata": {},
+   "source": [
+    "Take a look at the below text (and zoom out from the browser to really get the effect!). You'll see that the entire table is nicely laid out."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4928281a-591a-4653-b451-b2b8112a7101",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ZONE 2ZONE 3ZONE 4ZONE 4 ZONE 3ZONE 2ZONE 1ZONE 1\n",
+      "                                      Printer-Friendly Caltrain Schedule\n",
+      "              Northbound –                         WEEKEND SERVICE to SAN FRANCISCO                                                                                                                2XX Local\n",
+      "\n",
+      "\n",
+      "                  Train No.       221        225        229        233        237        241        245        249        253        257        261        265        269        273       *277       *281\n",
+      "                 Service Types      L2        L2          L2        L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2\n",
+      "                      Tamien      7:12a      9:05a     10:05a     11:05a                1:05p                 3:05p                 5:05p                 7:05p                 9:05p                11:05p\n",
+      "           San Jose Diridon       7:19a      9:12a     10:12a     11:12a    12:12p      1:12p      2:12p      3:12p      4:12p      5:12p      6:12p      7:12p      8:12p      9:12p     10:19p     11:12p\n",
+      "                 Santa Clara      7:25a      9:18a     10:18a     11:18a    12:18p      1:18p      2:18p      3:18p      4:18p      5:18p      6:18p      7:18p      8:18p      9:18p     10:25p     11:18p\n",
+      "                   Lawrence       7:31a      9:24a     10:24a     11:24a    12:24p      1:24p      2:24p      3:24p      4:24p      5:24p      6:24p      7:24p      8:24p      9:24p     10:31p     11:24p\n",
+      "                  Sunnyvale       7:35a      9:28a     10:28a     11:28a    12:28p      1:28p      2:28p      3:28p      4:28p      5:28p      6:28p      7:28p      8:28p      9:28p     10:35p     11:28p\n",
+      "            Mountain View         7:40a      9:34a     10:34a     11:34a    12:34p      1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:40p     11:34p\n",
+      "                San Antonio       7:43a      9:37a     10:37a     11:37a    12:37p      1:37p      2:37p      3:37p      4:37p      5:37p      6:37p      7:37p      8:37p      9:37p     10:44p     11:37p\n",
+      "              California Ave      7:48a      9:42a     10:42a     11:42a    12:42p      1:42p      2:42p      3:42p      4:42p      5:42p      6:42p      7:42p      8:42p      9:42p     10:48p     11:42p\n",
+      "                    Palo Alto     7:52a      9:46a     10:46a     11:46a    12:46p      1:46p      2:46p      3:46p      4:46p      5:46p      6:46p      7:46p      8:46p      9:46p     10:53p     11:46p\n",
+      "                 Menlo Park       7:55a      9:50a     10:50a     11:50a    12:50p      1:50p      2:50p      3:50p      4:50p      5:50p      6:50p      7:50p      8:50p      9:50p     10:56p     11:50p\n",
+      "              Redwood City        8:01a      9:56a     10:56a     11:56a    12:56p      1:56p      2:56p      3:56p      4:56p      5:56p      6:56p      7:56p      8:56p      9:56p     11:02p     11:56p\n",
+      "                  San Carlos      8:05a     10:01a     11:01a     12:01p     1:01p      2:01p      3:01p      4:01p      5:01p      6:01p      7:01p      8:01p      9:01p     10:01p     11:07p     12:01a\n",
+      "                    Belmont       8:09a     10:04a     11:04a     12:04p     1:04p      2:04p      3:04p      4:04p      5:04p      6:04p      7:04p      8:04p      9:04p     10:04p     11:10p     12:04a\n",
+      "                    Hillsdale     8:12a     10:08a     11:08a     12:08p     1:08p      2:08p      3:08p      4:08p      5:08p      6:08p      7:08p      8:08p      9:08p     10:08p     11:14p     12:08a\n",
+      "              Hayward Park        8:15a     10:11a     11:11a     12:11p     1:11p      2:11p      3:11p      4:11p      5:11p      6:11p      7:11p      8:11p      9:11p     10:11p     11:17p     12:11a\n",
+      "                  San Mateo       8:19a     10:15a     11:15a     12:15p     1:15p      2:15p      3:15p      4:15p      5:15p      6:15p      7:15p      8:15p      9:15p     10:15p     11:21p     12:15a\n",
+      "                 Burlingame       8:22a     10:19a     11:19a     12:19p     1:19p      2:19p      3:19p      4:19p      5:19p      6:19p      7:19p      8:19p      9:19p     10:19p     11:25p     12:19a\n",
+      "                  Broadway        8:25a     10:22a     11:22a     12:22p     1:22p      2:22p      3:22p      4:22p      5:22p      6:22p      7:22p      8:22p      9:22p     10:22p     11:28p     12:22a\n",
+      "                    Millbrae      8:29a     10:26a     11:26a     12:26p     1:26p      2:26p      3:26p      4:26p      5:26p      6:26p      7:26p      8:26p      9:26p     10:26p     11:32p     12:26a\n",
+      "                  San Bruno       8:34a     10:30a     11:30a     12:30p     1:30p      2:30p      3:30p      4:30p      5:30p      6:30p      7:30p      8:30p      9:30p     10:30p     11:37p     12:30a\n",
+      "            S. San Francisco      8:38a     10:34a     11:34a     12:34p     1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:34p     11:41p     12:34a\n",
+      "                   Bayshore       8:44a     10:41a     11:41a     12:41p     1:41p      2:41p      3:41p      4:41p      5:41p      6:41p      7:41p      8:41p      9:41p     10:41p     11:47p     12:41a\n",
+      "                  22 ndStreet     8:50a     10:46a     11:46a     12:46p     1:46p      2:46p      3:46p      4:46p      5:46p      6:46p      7:46p      8:46p      9:46p     10:46p     11:53p     12:46a\n",
+      "                San Francisco     8:56a     10:52a     11:53a     12:53p     1:52p      2:52p      3:52p      4:52p      5:52p      6:52p      7:52p      8:52p      9:52p     10:52p     11:59p     12:52a\n",
+      "                                      *On SAP Center event days, Train 277 or Train 281departure from San Jose Diridon station may be delayed and will depart no later than 10:30p or 11:30p respectively.\n",
+      "\n",
+      "\n",
+      "              Southbound                        –   WEEKEND               SERVICE to SAN JOSE                                                                                                      2XX Local\n",
+      "                  Train No.       224        228        232        236        240        244        248        252        256        260        264        268        272        276        280        284\n",
+      "                 Service Types      L2        L2          L2        L2          L2        L2         L2         L2         L2         L2         L2         L2         L2         L2         L2         L2\n",
+      "               San Francisco      8:28a      9:58a     10:58a     11:58a     12:58p     1:58p      2:58p      3:58p      4:58p      5:58p      6:58p      7:58p      8:58p      9:58p      10:58p     12:05a\n",
+      "                  22 ndStreet     8:33a     10:03a     11:03a     12:03p     1:03p      2:03p      3:03p      4:03p      5:03p      6:03p      7:03p      8:03p      9:03p     10:03p      11:03p     12:10a\n",
+      "                   Bayshore       8:38a     10:08a     11:08a     12:08p     1:08p      2:08p      3:08p      4:08p      5:08p      6:08p      7:08p      8:08p      9:08p     10:08p      11:08p     12:15a\n",
+      "            S. San Francisco      8:45a     10:15a     11:15a     12:15p     1:15p      2:15p      3:15p      4:15p      5:15p      6:15p      7:15p      8:15p      9:15p     10:15p      11:15p     12:22a\n",
+      "                  San Bruno       8:49a     10:19a     11:19a     12:19p     1:19p      2:19p      3:19p      4:19p      5:19p      6:19p      7:19p      8:19p      9:19p     10:19p      11:19p     12:26a\n",
+      "                    Millbrae      8:53a     10:24a     11:24a     12:24p     1:24p      2:24p      3:24p      4:24p      5:24p      6:24p      7:24p      8:24p      9:24p     10:24p      11:24p     12:31a\n",
+      "                  Broadway        8:57a     10:27a     11:27a     12:27p     1:27p      2:27p      3:27p      4:27p      5:27p      6:27p      7:27p      8:27p      9:27p     10:27p      11:27p     12:35a\n",
+      "                 Burlingame       9:00a     10:31a     11:31a     12:31p     1:31p      2:31p      3:31p      4:31p      5:31p      6:31p      7:31p      8:31p      9:31p     10:31p      11:31p     12:38a\n",
+      "                  San Mateo       9:04a     10:34a     11:34a     12:34p     1:34p      2:34p      3:34p      4:34p      5:34p      6:34p      7:34p      8:34p      9:34p     10:34p      11:34p     12:41a\n",
+      "              Hayward Park        9:07a     10:37a     11:37a     12:37p     1:37p      2:37p      3:37p      4:37p      5:37p      6:37p      7:37p      8:37p      9:37p     10:37p      11:37p     12:45a\n",
+      "                    Hillsdale     9:10a     10:41a     11:41a     12:41p     1:41p      2:41p      3:41p      4:41p      5:41p      6:41p      7:41p      8:41p      9:41p     10:41p      11:41p     12:48a\n",
+      "                    Belmont       9:14a     10:44a     11:44a     12:44p     1:44p      2:44p      3:44p      4:44p      5:44p      6:44p      7:44p      8:44p      9:44p     10:44p      11:44p     12:52a\n",
+      "                  San Carlos      9:17a     10:48a     11:48a     12:48p     1:48p      2:48p      3:48p      4:48p      5:48p      6:48p      7:48p      8:48p      9:48p     10:48p      11:48p     12:55a\n",
+      "              Redwood City        9:21a     10:52a     11:52a     12:52p     1:52p      2:52p      3:52p      4:52p      5:52p      6:52p      7:52p      8:52p      9:52p     10:52p      11:52p     12:59a\n",
+      "                 Menlo Park       9:28a     10:58a     11:58a     12:58p     1:58p      2:58p      3:58p      4:58p      5:58p      6:58p      7:58p      8:58p      9:58p     10:58p      11:58p     1:05a\n",
+      "                    Palo Alto     9:32a     11:02a     12:02p     1:02p      2:02p      3:02p      4:02p      5:02p      6:02p      7:02p      8:02p      9:02p     10:02p     11:02p      12:02a     1:09a\n",
+      "         California Avenue        9:36a     11:06a     12:06p     1:06p      2:06p      3:06p      4:06p      5:06p      6:06p      7:06p      8:06p      9:06p     10:06p     11:06p      12:06a     1:12a\n",
+      "                San Antonio       9:41a     11:11a     12:11p     1:11p      2:11p      3:11p      4:11p      5:11p      6:11p      7:11p      8:11p      9:11p     10:11p     11:11p      12:10a     1:17a\n",
+      "            Mountain View         9:45a     11:16a     12:16p     1:16p      2:16p      3:16p      4:16p      5:16p      6:16p      7:16p      8:16p      9:16p     10:16p     11:16p      12:15a     1:21a\n",
+      "                  Sunnyvale       9:51a     11:21a     12:21p     1:21p      2:21p      3:21p      4:21p      5:21p      6:21p      7:21p      8:21p      9:21p     10:21p     11:21p      12:20a     1:26a\n",
+      "                   Lawrence       9:55a     11:26a     12:26p     1:26p      2:26p      3:26p      4:26p      5:26p      6:26p      7:26p      8:26p      9:26p     10:26p     11:26p      12:25a     1:31a\n",
+      "                 Santa Clara     10:01a     11:32a     12:32p     1:32p      2:32p      3:32p      4:32p      5:32p      6:32p      7:32p      8:32p      9:32p     10:32p     11:32p      12:31a     1:37a\n",
+      "           San Jose Diridon      10:10a     11:40a     12:40p     1:38p      2:40p      3:38p      4:40p      5:38p      6:40p      7:38p      8:40p      9:38p     10:40p     11:38p      12:39a     1:44a\n",
+      "                      Tamien     10:15a     11:45a     12:45p                2:45p                 4:45p                 6:45p                 8:45p                10:45p                 12:44a     1:49a\n",
+      "       EFFECTIVE September 12, 2022                                                                                                                                  Timetable subject to change without notice.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8f5064d4-3e33-4f67-9b2e-46787161538f",
+   "metadata": {},
+   "source": [
+    "## Initialize Query Engine\n",
+    "\n",
+    "We now initialize a query engine over this data. Here we use a baseline summary index, which doesn't do vector indexing/chunking and instead dumps the entire text into the prompt.\n",
+    "\n",
+    "We see that the LLM (gpt-4-turbo) is able to provide all the stops for train no 225 northbound."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3e985b6-9d38-449f-9cf9-aae166824eed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4o\")\n",
+    "index = SummaryIndex.from_documents(docs)\n",
+    "query_engine = index.as_query_engine(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "66eb0976-2cd6-4b14-9083-124baae9ed5d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What are the stops (and times) for train no 237 northbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7dc6f275-07f4-429e-9335-f50982fe974c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The stops and times for train no. 237 northbound are as follows:\n",
+      "\n",
+      "- San Jose Diridon: 12:12 PM\n",
+      "- Santa Clara: 12:18 PM\n",
+      "- Lawrence: 12:24 PM\n",
+      "- Sunnyvale: 12:28 PM\n",
+      "- Mountain View: 12:34 PM\n",
+      "- San Antonio: 12:37 PM\n",
+      "- California Ave: 12:42 PM\n",
+      "- Palo Alto: 12:46 PM\n",
+      "- Menlo Park: 12:50 PM\n",
+      "- Redwood City: 12:56 PM\n",
+      "- San Carlos: 1:01 PM\n",
+      "- Belmont: 1:04 PM\n",
+      "- Hillsdale: 1:08 PM\n",
+      "- Hayward Park: 1:11 PM\n",
+      "- San Mateo: 1:15 PM\n",
+      "- Burlingame: 1:19 PM\n",
+      "- Broadway: 1:22 PM\n",
+      "- Millbrae: 1:26 PM\n",
+      "- San Bruno: 1:30 PM\n",
+      "- S. San Francisco: 1:34 PM\n",
+      "- Bayshore: 1:41 PM\n",
+      "- 22nd Street: 1:46 PM\n",
+      "- San Francisco: 1:52 PM\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "229c4cb0-cf94-4a9f-bc7c-590388f50c1f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What are all the trains (and times) that end at Tamien going Southbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6cf9fce0-5067-48f6-a7ef-62aa9e2edc3d",
+   "metadata": {},
+   "source": [
+    "It gets most of the answers correct (to be fair it misses two trains)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51cf03ff-7728-4815-ab72-3bf54fc4a2c0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The trains that end at Tamien going Southbound are:\n",
+      "\n",
+      "- Train 224 at 10:15a\n",
+      "- Train 228 at 11:45a\n",
+      "- Train 240 at 2:45p\n",
+      "- Train 248 at 4:45p\n",
+      "- Train 256 at 6:45p\n",
+      "- Train 264 at 8:45p\n",
+      "- Train 272 at 10:45p\n",
+      "- Train 284 at 1:49a\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e51e7feb-b74f-4101-8963-933ac7ec9763",
+   "metadata": {},
+   "source": [
+    "## Try Baseline\n",
+    "\n",
+    "In contrast, we try a baseline approach with the default PDF reader (PyPDF) in `SimpleDirectoryReader`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "364e5155-cc75-4302-a754-9444ae28e6b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SimpleDirectoryReader\n",
+    "from llama_index.core import SummaryIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4o\")\n",
+    "input_file = \"caltrain_schedule_weekend.pdf\"\n",
+    "reader = SimpleDirectoryReader(input_files=[input_file])\n",
+    "base_docs = reader.load_data()\n",
+    "index = SummaryIndex.from_documents(base_docs)\n",
+    "base_query_engine = index.as_query_engine(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a4011389-2d27-4a1a-bf8d-7309da28ab15",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Southbound  – WEEKEND SERVICE to SAN JOSE\n",
+      "Train No. 224 228 232 236 240 244 248 252 256 260 264 268 272 276 280 284\n",
+      "Service Types L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2\n",
+      "San Francisco 8:28a 9:58a 10:58a 11:58a 12:58p 1:58p 2:58p 3:58p 4:58p 5:58p 6:58p 7:58p 8:58p 9:58p 10:58p 12:05a\n",
+      "22nd Street 8:33a 10:03a 11:03a 12:03p 1:03p 2:03p 3:03p 4:03p 5:03p 6:03p 7:03p 8:03p 9:03p 10:03p 11:03p 12:10a\n",
+      "Bayshore 8:38a 10:08a 11:08a 12:08p 1:08p 2:08p 3:08p 4:08p 5:08p 6:08p 7:08p 8:08p 9:08p 10:08p 11:08p 12:15a\n",
+      "S. San Francisco 8:45a 10:15a 11:15a 12:15p 1:15p 2:15p 3:15p 4:15p 5:15p 6:15p 7:15p 8:15p 9:15p 10:15p 11:15p 12:22a\n",
+      "San Bruno 8:49a 10:19a 11:19a 12:19p 1:19p 2:19p 3:19p 4:19p 5:19p 6:19p 7:19p 8:19p 9:19p 10:19p 11:19p 12:26a\n",
+      "Millbrae 8:53a 10:24a 11:24a 12:24p 1:24p 2:24p 3:24p 4:24p 5:24p 6:24p 7:24p 8:24p 9:24p 10:24p 11:24p 12:31a\n",
+      "Broadway 8:57a 10:27a 11:27a 12:27p 1:27p 2:27p 3:27p 4:27p 5:27p 6:27p 7:27p 8:27p 9:27p 10:27p 11:27p 12:35a\n",
+      "Burlingame 9:00a 10:31a 11:31a 12:31p 1:31p 2:31p 3:31p 4:31p 5:31p 6:31p 7:31p 8:31p 9:31p 10:31p 11:31p 12:38a\n",
+      "San Mateo 9:04a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:34p 11:34p 12:41a\n",
+      "Hayward Park 9:07a 10:37a 11:37a 12:37p 1:37p 2:37p 3:37p 4:37p 5:37p 6:37p 7:37p 8:37p 9:37p 10:37p 11:37p 12:45a\n",
+      "Hillsdale 9:10a 10:41a 11:41a 12:41p 1:41p 2:41p 3:41p 4:41p 5:41p 6:41p 7:41p 8:41p 9:41p 10:41p 11:41p 12:48a\n",
+      "Belmont 9:14a 10:44a 11:44a 12:44p 1:44p 2:44p 3:44p 4:44p 5:44p 6:44p 7:44p 8:44p 9:44p 10:44p 11:44p 12:52a\n",
+      "San Carlos 9:17a 10:48a 11:48a 12:48p 1:48p 2:48p 3:48p 4:48p 5:48p 6:48p 7:48p 8:48p 9:48p 10:48p 11:48p 12:55a\n",
+      "Redwood City 9:21a 10:52a 11:52a 12:52p 1:52p 2:52p 3:52p 4:52p 5:52p 6:52p 7:52p 8:52p 9:52p 10:52p 11:52p 12:59a\n",
+      "Menlo Park 9:28a 10:58a 11:58a 12:58p 1:58p 2:58p 3:58p 4:58p 5:58p 6:58p 7:58p 8:58p 9:58p 10:58p 11:58p 1:05a\n",
+      "Palo Alto 9:32a 11:02a 12:02p 1:02p 2:02p 3:02p 4:02p 5:02p 6:02p 7:02p 8:02p 9:02p 10:02p 11:02p 12:02a 1:09a\n",
+      "California Avenue 9:36a 11:06a 12:06p 1:06p 2:06p 3:06p 4:06p 5:06p 6:06p 7:06p 8:06p 9:06p 10:06p 11:06p 12:06a 1:12a\n",
+      "San Antonio 9:41a 11:11a 12:11p 1:11p 2:11p 3:11p 4:11p 5:11p 6:11p 7:11p 8:11p 9:11p 10:11p 11:11p 12:10a 1:17a\n",
+      "Mountain View 9:45a 11:16a 12:16p 1:16p 2:16p 3:16p 4:16p 5:16p 6:16p 7:16p 8:16p 9:16p 10:16p 11:16p 12:15a 1:21a\n",
+      "Sunnyvale 9:51a 11:21a 12:21p 1:21p 2:21p 3:21p 4:21p 5:21p 6:21p 7:21p 8:21p 9:21p 10:21p 11:21p 12:20a 1:26a\n",
+      "Lawrence 9:55a 11:26a 12:26p 1:26p 2:26p 3:26p 4:26p 5:26p 6:26p 7:26p 8:26p 9:26p 10:26p 11:26p 12:25a 1:31a\n",
+      "Santa Clara 10:01a 11:32a 12:32p 1:32p 2:32p 3:32p 4:32p 5:32p 6:32p 7:32p 8:32p 9:32p 10:32p 11:32p 12:31a 1:37a\n",
+      "San Jose Diridon 10:10a 11:40a 12:40p 1:38p 2:40p 3:38p 4:40p 5:38p 6:40p 7:38p 8:40p 9:38p 10:40p 11:38p 12:39a 1:44a\n",
+      "Tamien 10:15a 11:45a 12:45p 2:45p 4:45p 6:45p 8:45p 10:45p 12:44a 1:49aPrinter-Friendly Caltrain Schedule\n",
+      "Northbound  – WEEKEND SERVICE to SAN FRANCISCO\n",
+      "Train No. 221 225 229 233 237 241 245 249 253 257 261 265 269 273 *277 *281\n",
+      "Service Types L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2 L2\n",
+      "Tamien 7:12a 9:05a 10:05a 11:05a 1:05p 3:05p 5:05p 7:05p 9:05p 11:05p\n",
+      "San Jose Diridon 7:19a 9:12a 10:12a 11:12a 12:12p 1:12p 2:12p 3:12p 4:12p 5:12p 6:12p 7:12p 8:12p 9:12p 10:19p 11:12p\n",
+      "Santa Clara 7:25a 9:18a 10:18a 11:18a 12:18p 1:18p 2:18p 3:18p 4:18p 5:18p 6:18p 7:18p 8:18p 9:18p 10:25p 11:18p\n",
+      "Lawrence 7:31a 9:24a 10:24a 11:24a 12:24p 1:24p 2:24p 3:24p 4:24p 5:24p 6:24p 7:24p 8:24p 9:24p 10:31p 11:24p\n",
+      "Sunnyvale 7:35a 9:28a 10:28a 11:28a 12:28p 1:28p 2:28p 3:28p 4:28p 5:28p 6:28p 7:28p 8:28p 9:28p 10:35p 11:28p\n",
+      "Mountain View 7:40a 9:34a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:40p 11:34p\n",
+      "San Antonio 7:43a 9:37a 10:37a 11:37a 12:37p 1:37p 2:37p 3:37p 4:37p 5:37p 6:37p 7:37p 8:37p 9:37p 10:44p 11:37p\n",
+      "California Ave 7:48a 9:42a 10:42a 11:42a 12:42p 1:42p 2:42p 3:42p 4:42p 5:42p 6:42p 7:42p 8:42p 9:42p 10:48p 11:42p\n",
+      "Palo Alto 7:52a 9:46a 10:46a 11:46a 12:46p 1:46p 2:46p 3:46p 4:46p 5:46p 6:46p 7:46p 8:46p 9:46p 10:53p 11:46p\n",
+      "Menlo Park 7:55a 9:50a 10:50a 11:50a 12:50p 1:50p 2:50p 3:50p 4:50p 5:50p 6:50p 7:50p 8:50p 9:50p 10:56p 11:50p\n",
+      "Redwood City 8:01a 9:56a 10:56a 11:56a 12:56p 1:56p 2:56p 3:56p 4:56p 5:56p 6:56p 7:56p 8:56p 9:56p 11:02p 11:56p\n",
+      "San Carlos 8:05a 10:01a 11:01a 12:01p 1:01p 2:01p 3:01p 4:01p 5:01p 6:01p 7:01p 8:01p 9:01p 10:01p 11:07p 12:01a\n",
+      "Belmont 8:09a 10:04a 11:04a 12:04p 1:04p 2:04p 3:04p 4:04p 5:04p 6:04p 7:04p 8:04p 9:04p 10:04p 11:10p 12:04a\n",
+      "Hillsdale 8:12a 10:08a 11:08a 12:08p 1:08p 2:08p 3:08p 4:08p 5:08p 6:08p 7:08p 8:08p 9:08p 10:08p 11:14p 12:08a\n",
+      "Hayward Park 8:15a 10:11a 11:11a 12:11p 1:11p 2:11p 3:11p 4:11p 5:11p 6:11p 7:11p 8:11p 9:11p 10:11p 11:17p 12:11a\n",
+      "San Mateo 8:19a 10:15a 11:15a 12:15p 1:15p 2:15p 3:15p 4:15p 5:15p 6:15p 7:15p 8:15p 9:15p 10:15p 11:21p 12:15a\n",
+      "Burlingame 8:22a 10:19a 11:19a 12:19p 1:19p 2:19p 3:19p 4:19p 5:19p 6:19p 7:19p 8:19p 9:19p 10:19p 11:25p 12:19a\n",
+      "Broadway 8:25a 10:22a 11:22a 12:22p 1:22p 2:22p 3:22p 4:22p 5:22p 6:22p 7:22p 8:22p 9:22p 10:22p 11:28p 12:22a\n",
+      "Millbrae 8:29a 10:26a 11:26a 12:26p 1:26p 2:26p 3:26p 4:26p 5:26p 6:26p 7:26p 8:26p 9:26p 10:26p 11:32p 12:26a\n",
+      "San Bruno 8:34a 10:30a 11:30a 12:30p 1:30p 2:30p 3:30p 4:30p 5:30p 6:30p 7:30p 8:30p 9:30p 10:30p 11:37p 12:30a\n",
+      "S. San Francisco 8:38a 10:34a 11:34a 12:34p 1:34p 2:34p 3:34p 4:34p 5:34p 6:34p 7:34p 8:34p 9:34p 10:34p 11:41p 12:34a\n",
+      "Bayshore 8:44a 10:41a 11:41a 12:41p 1:41p 2:41p 3:41p 4:41p 5:41p 6:41p 7:41p 8:41p 9:41p 10:41p 11:47p 12:41a\n",
+      "22nd Street 8:50a 10:46a 11:46a 12:46p 1:46p 2:46p 3:46p 4:46p 5:46p 6:46p 7:46p 8:46p 9:46p 10:46p 11:53p 12:46a\n",
+      "San Francisco 8:56a 10:52a 11:53a 12:53p 1:52p 2:52p 3:52p 4:52p 5:52p 6:52p 7:52p 8:52p 9:52p 10:52p 11:59p 12:52aZONE 2 ZONE 3 ZONE 4 ZONE 4 ZONE 3 ZONE 2 ZONE 1 ZONE 12XX Local\n",
+      "2XX Local\n",
+      "EFFECTIVE September 12, 2022  Timetable subject to change without notice. *On SAP Center event days, Train 277 or Train 281departure from San Jose Diridon station may be delayed and will depart no later than 10:30p or 11:30p respectively.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42203c70-7ca7-4200-bf47-6282eefca3bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_response = base_query_engine.query(\n",
+    "    \"What are the stops (and times) for train no 237 northbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06aa47b6-0f31-4b2d-90f0-bf6c74befd38",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Train No. 237 northbound stops at the following stations and times:\n",
+      "\n",
+      "- Tamien: 1:05p\n",
+      "- San Jose Diridon: 1:12p\n",
+      "- Santa Clara: 1:18p\n",
+      "- Lawrence: 1:24p\n",
+      "- Sunnyvale: 1:28p\n",
+      "- Mountain View: 1:34p\n",
+      "- San Antonio: 1:37p\n",
+      "- California Ave: 1:42p\n",
+      "- Palo Alto: 1:46p\n",
+      "- Menlo Park: 1:50p\n",
+      "- Redwood City: 1:56p\n",
+      "- San Carlos: 2:01p\n",
+      "- Belmont: 2:04p\n",
+      "- Hillsdale: 2:08p\n",
+      "- Hayward Park: 2:11p\n",
+      "- San Mateo: 2:15p\n",
+      "- Burlingame: 2:19p\n",
+      "- Broadway: 2:22p\n",
+      "- Millbrae: 2:26p\n",
+      "- San Bruno: 2:30p\n",
+      "- S. San Francisco: 2:34p\n",
+      "- Bayshore: 2:41p\n",
+      "- 22nd Street: 2:46p\n",
+      "- San Francisco: 2:52p\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f3c1de7-3351-4cd8-991c-34a777952194",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_response = base_query_engine.query(\n",
+    "    \"What are all the trains (and times) that end at Tamien going Southbound?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "513b1007-7508-4fb1-836c-de9353433a67",
+   "metadata": {},
+   "source": [
+    "Note that the trains don't line up with the times!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "108edb92-76af-406b-a139-8b9e7c6528f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The trains that end at Tamien going Southbound are:\n",
+      "\n",
+      "- Train 224 at 10:15a\n",
+      "- Train 228 at 11:45a\n",
+      "- Train 240 at 2:45p\n",
+      "- Train 252 at 4:45p\n",
+      "- Train 264 at 6:45p\n",
+      "- Train 276 at 8:45p\n",
+      "- Train 284 at 10:45p\n",
+      "- Train 284 at 12:44a\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(base_response))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/demo_json.ipynb

@@ -342,7 +342,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "llama-parse-aNC435Vv-py3.10",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },

examples/excel/dcf_rag.ipynb

@@ -0,0 +1,493 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0db58db5-d4ee-4631-af5b-4fc53eb05170",
+   "metadata": {},
+   "source": [
+    "# RAG with Excel Spreadsheet using LlamaPrase\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_excel.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This notebook constructs a RAG pipeline over a simple DCF template [here](https://eqvista.com/app/uploads/2020/09/Eqvista_DCF-Excel-Template.xlsx).\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5f7d99ad-6ebd-47d0-92a7-566630b0c22a",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "We first setup and load the data. If you haven't already, [download the template](https://eqvista.com/app/uploads/2020/09/Eqvista_DCF-Excel-Template.xlsx) and name it `dcf_template.xlxs` locally."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d867d1a6-cfcf-4f53-952a-f4a6ff2fa205",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index\n",
+    "%pip install llama-parse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "103c7983-56d3-45be-b763-d1828d07c43e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7b694b56-e04b-4d87-aa37-f0725d6b3adb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "# api_key = \"llx-\"  # get from cloud.llamaindex.ai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9c4693c7-c1c8-47b4-8a8c-25d7e9ef9d2c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id cac11eca-d5da-4d46-90e6-321f40e11611\n",
+      "Started parsing the file under job_id cac11eca-5450-4847-9da0-fa6879c4cf3a\n"
+     ]
+    }
+   ],
+   "source": [
+    "parser = LlamaParse(\n",
+    "    # api_key=api_key,  # can also be set in your env as LLAMA_CLOUD_API_KEY\n",
+    "    result_type=\"markdown\",\n",
+    ")\n",
+    "docs = parser.load_data(\"./dcf_template.xlsx\")\n",
+    "# docs_txt = LlamaParse(result_type=\"text\").load_data(\"./dcf_template.xlsx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7302f1c8-e405-4cda-8ff7-1d55185816f7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Cover Page\n",
+      "\n",
+      "|Thank you for downloading our DCF Model excel template. This DCF Model excel template helps you to value your business using Discounted Free Cash Flow or DCF Method. |                                                                                                                                                                                  |\n",
+      "|----------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |Eqvista is an equity management software that allows companies, investors and company shareholders to track, manage, and make intelligent decisions about their companies’ equity.|\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |GET STARTED- IT'S FREE                                                                                                                                                            |\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |Note: This template is not professional advice and not a substitute for professional advice.                                                                                      |\n",
+      "|Accordingly, before taking any actions based upon such information, we encourage you to consult with the appropriate professionals.                                   |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |                                                                                                                                                                                  |\n",
+      "|                                                                                                                                                                      |@Eqvista Inc. All Rights Reserved                                                                                                                                                 |\n",
+      "---\n",
+      "# DCF Model\n",
+      "\n",
+      "|Discounted Cash Flow Excel Template                                                                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------|-----------|-----------|-----------------------|-----------|-----------------------|--------------|-----------|-----------|-----------|--------------|\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Here is a simple discounted cash flow excel template for estimating your company value based on this income valuation approach                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Instructions:                                                                                                                                                                              |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|1) Fill out the two assumptions in yellow highlight                                                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|2) Fill in either the 5 year or 3 year weighted average figures in yellow highlight                                                                                                        |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Assumptions                                                                                                                                                                                |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Tax Rate                                                                                                                                                                                   |20%                           |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Discount Rate                                                                                                                                                                              |15%                           |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|5 Year Weighted Moving Average                                                                                                                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Indication of Company Value                                                                                                                                                                |$242,995.43                   |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|3 Year Weighted Moving Average                                                                                                                                                             |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Indication of Company Value                                                                                                                                                                |$158,651.07                   |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |5 Year Weighted Moving Average|           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Past Years                    |           |           |                       |           |Forecasted Future Years|              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Year 1                        |Year 2     |Year 3     |Year 4                 |Year 5     |Year 6                 |Year 7        |Year 8     |Year 9     |Year 10    |Terminal Value|\n",
+      "|Pre-tax income                                                                                                                                                                             |50,000.00                     |55,000.00  |45,000.00  |52,000.00              |60,000.00  |                       |              |           |           |           |              |\n",
+      "|Income Taxes                                                                                                                                                                               |10,000.00                     |11,000.00  |9,000.00   |10,400.00              |12,000.00  |                       |              |           |           |           |              |\n",
+      "|Net Income                                                                                                                                                                                 |40,000.00                     |44,000.00  |36,000.00  |41,600.00              |48,000.00  |                       |              |           |           |           |              |\n",
+      "|Depreciation Expense                                                                                                                                                                       |5,000.00                      |4,000.00   |3,000.00   |2,000.00               |1,000.00   |                       |              |           |           |           |              |\n",
+      "|Capital Expenditures                                                                                                                                                                       |10,000.00                     |8,000.00   |5,000.00   |5,000.00               |7,000.00   |                       |              |           |           |           |              |\n",
+      "|Debt Repayments                                                                                                                                                                            |5,000.00                      |5,000.00   |5,000.00   |5,000.00               |5,000.00   |                       |              |           |           |           |              |\n",
+      "|Net Cash Flow                                                                                                                                                                              |20,000.00                     |27,000.00  |23,000.00  |29,600.00              |35,000.00  |29,093.33              |29,817.78     |30,177.48  |30,469.23  |30,379.74  |287,188.00    |\n",
+      "|Discounting Factor                                                                                                                                                                         |                              |           |           |                       |           |0.8696                 |0.7561        |0.6575     |0.5718     |0.4972     |0.4972        |\n",
+      "|Present Value of Future Cash Flow                                                                                                                                                          |                              |           |           |                       |           |25,298.55              |22,546.52     |19,842.18  |17,420.88  |15,104.10  |142,783.19    |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |3 Year Weighted Moving Average|           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Past Years                    |           |           |Forecasted Future Years|           |                       |              |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |Year 1                        |Year 2     |Year 3     |Year 4                 |Year 5     |Year 6                 |Terminal Value|           |           |           |              |\n",
+      "|Pre-tax income                                                                                                                                                                             |50,000.00                     |55,000.00  |45,000.00  |                       |           |                       |              |           |           |           |              |\n",
+      "|Income Taxes                                                                                                                                                                               |10,000.00                     |11,000.00  |9,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Net Income                                                                                                                                                                                 |40,000.00                     |44,000.00  |36,000.00  |                       |           |                       |              |           |           |           |              |\n",
+      "|Depreciation Expense                                                                                                                                                                       |5,000.00                      |4,000.00   |3,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Capital Expenditures                                                                                                                                                                       |10,000.00                     |8,000.00   |5,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Debt Repayments                                                                                                                                                                            |5,000.00                      |5,000.00   |5,000.00   |                       |           |                       |              |           |           |           |              |\n",
+      "|Net Cash Flow                                                                                                                                                                              |20,000.00                     |27,000.00  |23,000.00  |23,833.33              |24,083.33  |23,819.44              |158,253.59    |           |           |           |              |\n",
+      "|Discounting Factor                                                                                                                                                                         |                              |           |           |0.8696                 |0.7561     |0.6575                 |0.6575        |           |           |           |              |\n",
+      "|Present Value of Future Cash Flow                                                                                                                                                          |                              |           |           |20,724.64              |18,210.46  |15,661.67              |104,054.30    |           |           |           |              |\n",
+      "|                                                                                                                                                                                           |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|Notes:                                                                                                                                                                                     |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-We based this simple discounted cash flow excel model based on the weighted moving averages (5 year or 3 year) for simplicity, in case a constant growth rate cannot be easily determined.|                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-The factors such as Depreciation Expense, Capital Expense and Debt Repayments remain constant, so consider this when looking at the forecasted figures.                                   |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "|-For the terminal value constant growth rate, we make the assumption of the growth from the last forecasted year compared to the first forecasted year. Adjust in the formula as needed.   |                              |           |           |                       |           |                       |              |           |           |           |              |\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1aedd4bb-7939-4fbc-8f07-d362e24d9772",
+   "metadata": {},
+   "source": [
+    "## Configure LLM, Setup Basic Summary Engine\n",
+    "\n",
+    "We setup a basic summary engine which retrieves the entire document as context to put into the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f7c056a8-d098-4ebe-9341-d9f07081067c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-4-turbo-preview\")\n",
+    "Settings.llm = llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0fa2630-ee1b-4ce7-91e9-f9ffff8347f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "\n",
+    "index = SummaryIndex.from_documents(docs)\n",
+    "# index = SummaryIndex.from_documents(docs_txt)\n",
+    "\n",
+    "query_engine = index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1d39a075-46b8-4dcb-8aee-abd10343bedd",
+   "metadata": {},
+   "source": [
+    "## Define Baseline\n",
+    "\n",
+    "Let's define a baseline query engine over this data, using a naive parser (our PandasExcelReader, available on LlamaHub)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "632f918e-7811-4931-8a5f-4aa4850718db",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Collecting openpyxl\n",
+      "  Downloading openpyxl-3.1.3-py2.py3-none-any.whl (251 kB)\n",
+      "\u001b[2K     \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m251.3/251.3 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\n",
+      "\u001b[?25hCollecting et-xmlfile\n",
+      "  Using cached et_xmlfile-1.1.0-py3-none-any.whl (4.7 kB)\n",
+      "Installing collected packages: et-xmlfile, openpyxl\n",
+      "Successfully installed et-xmlfile-1.1.0 openpyxl-3.1.3\n",
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip available: \u001b[0m\u001b[31;49m22.2.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install llama-index-readers-file\n",
+    "!pip install openpyxl"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85ff09fd-8a99-4aa4-8182-8d0cf30f7b85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.readers.file import PandasExcelReader\n",
+    "import importlib\n",
+    "from pathlib import Path\n",
+    "\n",
+    "base_reader = PandasExcelReader()\n",
+    "base_docs = base_reader.load_data(Path(\"dcf_template.xlsx\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ba45f806-58be-4f57-bf42-2721555136cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Discounted Cash Flow Excel Template           \n",
+      "           \n",
+      "Here is a simple discounted cash flow excel template for estimating your company value based on this income valuation approach           \n",
+      "           \n",
+      "Instructions:           \n",
+      "1) Fill out the two assumptions in yellow highlight           \n",
+      "2) Fill in either the 5 year or 3 year weighted average figures in yellow highlight           \n",
+      "           \n",
+      "           \n",
+      "           \n",
+      "           \n",
+      "Assumptions           \n",
+      "Tax Rate 0.2          \n",
+      "Discount Rate 0.15          \n",
+      "           \n",
+      "5 Year Weighted Moving Average           \n",
+      "Indication of Company Value 242995.4347636059          \n",
+      "           \n",
+      "3 Year Weighted Moving Average           \n",
+      "Indication of Company Value 158651.0723286644          \n",
+      "           \n",
+      " 5 Year Weighted Moving Average          \n",
+      " Past Years     Forecasted Future Years     \n",
+      " Year 1 Year 2 Year 3 Year 4 Year 5 Year 6 Year 7 Year 8 Year 9 Year 10 Terminal Value\n",
+      "Pre-tax income 50000 55000 45000 52000 60000      \n",
+      "Income Taxes 10000 11000 9000 10400 12000      \n",
+      "Net Income 40000 44000 36000 41600 48000      \n",
+      "Depreciation Expense 5000 4000 3000 2000 1000      \n",
+      "Capital Expenditures 10000 8000 5000 5000 7000      \n",
+      "Debt Repayments 5000 5000 5000 5000 5000      \n",
+      "Net Cash Flow 20000 27000 23000 29600 35000 29093.333333333332 29817.777777777774 30177.481481481478 30469.234567901232 30379.73991769547 287188.0007003137\n",
+      "Discounting Factor      0.8695652173913044 0.7561436672967865 0.6575162324319883 0.5717532455930334 0.4971767352982899 0.4971767352982899\n",
+      "Present Value of Future Cash Flow      25298.550724637684 22546.523839529513 19842.183927989798 17420.883754932976 15104.099911490972 142783.19260502496\n",
+      "           \n",
+      "           \n",
+      " 3 Year Weighted Moving Average          \n",
+      " Past Years   Forecasted Future Years       \n",
+      " Year 1 Year 2 Year 3 Year 4 Year 5 Year 6 Terminal Value    \n",
+      "Pre-tax income 50000 55000 45000        \n",
+      "Income Taxes 10000 11000 9000        \n",
+      "Net Income 40000 44000 36000        \n",
+      "Depreciation Expense 5000 4000 3000        \n",
+      "Capital Expenditures 10000 8000 5000        \n",
+      "Debt Repayments 5000 5000 5000        \n",
+      "Net Cash Flow 20000 27000 23000 23833.333333333332 24083.333333333332 23819.44444444444 158253.58851674633    \n",
+      "Discounting Factor    0.8695652173913044 0.7561436672967865 0.6575162324319883 0.6575162324319883    \n",
+      "Present Value of Future Cash Flow    20724.63768115942 18210.459987397608 15661.671369734164 104054.30329037321    \n",
+      "           \n",
+      "           \n",
+      "Notes:           \n",
+      "-We based this simple discounted cash flow excel model based on the weighted moving averages (5 year or 3 year) for simplicity, in case a constant growth rate cannot be easily determined.           \n",
+      "-The factors such as Depreciation Expense, Capital Expense and Debt Repayments remain constant, so consider this when looking at the forecasted figures.           \n",
+      "-For the terminal value constant growth rate, we make the assumption of the growth from the last forecasted year compared to the first forecasted year. Adjust in the formula as needed.           \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_docs[1].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ff6e812f-fa94-4b0f-8907-ee70983e53f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import SummaryIndex\n",
+    "\n",
+    "base_index = SummaryIndex.from_documents([base_docs[1]])\n",
+    "\n",
+    "base_query_engine = base_index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa75f1bc-6fed-4721-ba5e-dc5408395618",
+   "metadata": {},
+   "source": [
+    "## Ask Questions over this Data\n",
+    "\n",
+    "Let's now ask questions over this data, using both the LlamaParse-powered pipeline and naive pipeline."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a875a20e-a6b6-46b7-80d4-614546215ffc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the income taxes in the past years (year 3-5) for the 5 year WMA table\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06b0b072-f159-47c4-9cad-9f0cc0d56b28",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The income taxes in the past years (year 3 to 5) for the 5-year Weighted Moving Average table were $9,000.00 in Year 3, $10,400.00 in Year 4, and $12,000.00 in Year 5.\n",
+      "******* Naive RAG *******\n",
+      "The income taxes in the past years (year 3-5) for the 5 year WMA table were $9,000, $10,400, and $12,000, respectively.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bd0998f-4f7f-46f9-9b51-cfb510f384ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(response.source_nodes[0].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a93af5f-fcea-4f14-80eb-5dfad230cd8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the discounting factors in year 5 for the 3 year WMA\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6d3a5fb-c32c-4dea-8f2e-956af85456a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The discounting factor in year 5 for the 3-year Weighted Moving Average (WMA) is 0.7561.\n",
+      "******* Naive RAG *******\n",
+      "The discounting factor in year 5 for the 3-year Weighted Moving Average is 0.6575162324319883.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b96f3a9b-6e99-4192-b6d6-447319d3c4fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_str = \"Tell me about the projected net cash flow in years 7-9 for the 5 year WMA\"\n",
+    "response = query_engine.query(query_str)\n",
+    "base_response = base_query_engine.query(query_str)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "92b419b9-25ee-4d69-98d9-56c0a45b24af",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "******* LlamaParse RAG *******\n",
+      "The projected net cash flow for years 7 to 9 in the 5-year Weighted Moving Average scenario is as follows: Year 7 is $29,817.78, Year 8 is $30,177.48, and Year 9 is $30,469.23.\n",
+      "******* Naive RAG *******\n",
+      "The projected net cash flow for years 7 to 9 in the 5-year weighted moving average scenario is as follows: Year 7 is $29,093.33, Year 8 is $29,817.78, and Year 9 is $30,177.48.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"******* LlamaParse RAG *******\")\n",
+    "print(str(response))\n",
+    "print(\"******* Naive RAG *******\")\n",
+    "print(str(base_response))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/multimodal/claude_parse.ipynb

@@ -0,0 +1,635 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "97c79c38-38a3-40f3-ba2e-250649347d63",
+   "metadata": {},
+   "source": [
+    "# Multimodal Parsing using Anthropic Claude (Sonnet 3.5)\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/claude_parse.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This cookbook shows you how to use LlamaParse to parse any document with the multimodal capabilities of Sonnet 3.5. \n",
+    "\n",
+    "LlamaParse allows you to plug in external, multimodal model vendors for parsing - we handle the error correction, validation, and scalability/reliability for you.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15e60ecf-519c-41fc-911b-765adaf8bad4",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Download the data. Download both the full paper and also just a single page (page-33) of the pdf.\n",
+    "\n",
+    "Swap in `data/llama2-p33.pdf` for `data/llama2.pdf` in the code blocks below if you want to save on parsing tokens. \n",
+    "\n",
+    "An image of this page is shown below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91a9e532-1454-40e0-bbf0-fd442c350121",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d9fb0aa-74cd-476f-8161-efd9e04248bf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-07-11 23:44:38--  https://arxiv.org/pdf/2307.09288\n",
+      "Resolving arxiv.org (arxiv.org)... 151.101.195.42, 151.101.131.42, 151.101.3.42, ...\n",
+      "Connecting to arxiv.org (arxiv.org)|151.101.195.42|:443... connected.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 13661300 (13M) [application/pdf]\n",
+      "Saving to: ‘data/llama2.pdf’\n",
+      "\n",
+      "data/llama2.pdf     100%[===================>]  13.03M  69.3MB/s    in 0.2s    \n",
+      "\n",
+      "2024-07-11 23:44:38 (69.3 MB/s) - ‘data/llama2.pdf’ saved [13661300/13661300]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget \"https://arxiv.org/pdf/2307.09288\" -O data/llama2.pdf\n",
+    "!wget \"https://www.dropbox.com/scl/fi/wpql661uu98vf6e2of2i0/llama2-p33.pdf?rlkey=64weubzkwpmf73y58vbmc8pyi&st=khgx5161&dl=1\" -O data/llama2-p33.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b5c214a2-56fd-4b09-93b3-be994a3b5aa4",
+   "metadata": {},
+   "source": [
+    "![page_33](llama2-p33.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e29a9d7-5bd9-4fb8-8ec1-4c128a748662",
+   "metadata": {},
+   "source": [
+    "## Initialize LlamaParse\n",
+    "\n",
+    "Initialize LlamaParse in multimodal mode, and specify the vendor.\n",
+    "\n",
+    "**NOTE**: optionally you can specify the Anthropic API key. If you do so you will be charged our base LlamaParse price of 0.3c per page. If you don't then you will be charged 6c per page, as we will make the calls to Claude for you."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc921729-3446-42ca-8e1b-a6fd26195ed9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.schema import TextNode\n",
+    "from typing import List\n",
+    "import json\n",
+    "\n",
+    "\n",
+    "def get_text_nodes(json_list: List[dict]):\n",
+    "    text_nodes = []\n",
+    "    for idx, page in enumerate(json_list):\n",
+    "        text_node = TextNode(text=page[\"md\"], metadata={\"page\": page[\"page\"]})\n",
+    "        text_nodes.append(text_node)\n",
+    "    return text_nodes\n",
+    "\n",
+    "\n",
+    "def save_jsonl(data_list, filename):\n",
+    "    \"\"\"Save a list of dictionaries as JSON Lines.\"\"\"\n",
+    "    with open(filename, \"w\") as file:\n",
+    "        for item in data_list:\n",
+    "            json.dump(item, file)\n",
+    "            file.write(\"\\n\")\n",
+    "\n",
+    "\n",
+    "def load_jsonl(filename):\n",
+    "    \"\"\"Load a list of dictionaries from JSON Lines.\"\"\"\n",
+    "    data_list = []\n",
+    "    with open(filename, \"r\") as file:\n",
+    "        for line in file:\n",
+    "            data_list.append(json.loads(line))\n",
+    "    return data_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2e9d9cf-8189-4fcb-b34f-cde6cc0b59c8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 811a29d8-8bcd-4100-bee3-6a83fbde1697\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"anthropic-sonnet-3.5\",\n",
+    "    # invalidate_cache=True\n",
+    ")\n",
+    "json_objs = parser.get_json_result(\"./data/llama2.pdf\")\n",
+    "# json_objs = parser.get_json_result(\"./data/llama2-p33.pdf\")\n",
+    "json_list = json_objs[0][\"pages\"]\n",
+    "docs = get_text_nodes(json_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "96a81df0-1026-4e30-a930-f677dc31e344",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Save\n",
+    "save_jsonl([d.dict() for d in docs], \"docs.jsonl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee2e6920-8893-4b39-ae12-94d13c651406",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Load\n",
+    "from llama_index.core import Document\n",
+    "\n",
+    "docs_dicts = load_jsonl(\"docs.jsonl\")\n",
+    "docs = [Document.parse_obj(d) for d in docs_dicts]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f3c51b0-7878-48d7-9bc3-02b516500128",
+   "metadata": {},
+   "source": [
+    "### Setup GPT-4o baseline\n",
+    "\n",
+    "For comparison, we will also parse the document using GPT-4o (3c per page)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6fc3f258-50ae-4988-b904-c105463a498f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 04c69ecc-e45d-4ad9-ba72-3045af38268b\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser_gpt4o = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model=\"openai-gpt4o\",\n",
+    "    # invalidate_cache=True\n",
+    ")\n",
+    "json_objs_gpt4o = parser_gpt4o.get_json_result(\"./data/llama2.pdf\")\n",
+    "# json_objs_gpt4o = parser.get_json_result(\"./data/llama2-p33.pdf\")\n",
+    "json_list_gpt4o = json_objs_gpt4o[0][\"pages\"]\n",
+    "docs_gpt4o = get_text_nodes(json_list_gpt4o)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a47f04e-12e1-4c80-a71d-ef7721f96401",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Save\n",
+    "save_jsonl([d.dict() for d in docs_gpt4o], \"docs_gpt4o.jsonl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c38b5ca3-fa87-434b-b477-bf6a4962eb3d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Load\n",
+    "from llama_index.core import Document\n",
+    "\n",
+    "docs_gpt4o_dicts = load_jsonl(\"docs_gpt4o.jsonl\")\n",
+    "docs_gpt4o = [Document.parse_obj(d) for d in docs_gpt4o_dicts]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44c20f7a-2901-4dd0-b635-a4b33c5664c1",
+   "metadata": {},
+   "source": [
+    "## View Results\n",
+    "\n",
+    "Let's visualize the results along with the original document page.\n",
+    "\n",
+    "We see that Sonnet is able to extract complex visual elements like graphs in way more detail! \n",
+    "\n",
+    "**NOTE**: If you're using llama2-p33, just use `docs[0]`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "778698aa-da7e-4081-b3b5-0372f228536f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 33\n",
+      "\n",
+      "| Temperature | RLHF v3 | RLHF v2 | RLHF v1 | SFT |\n",
+      "|-------------|---------|---------|---------|-----|\n",
+      "| 0.4         | 98      | 98      | 97      | 95  |\n",
+      "| 0.6         | 97      | 97      | 95      | 94  |\n",
+      "| 0.8         | 97      | 96      | 94      | 92  |\n",
+      "| 1.0         | 96      | 94      | 92      | 89  |\n",
+      "| 1.2         | 95      | 92      | 88      | 83  |\n",
+      "| 1.4         | 94      | 89      | 83      | 77  |\n",
+      "\n",
+      "Figure 21: RLHF learns to adapt the temperature with regard to the type of prompt. Lower Self-BLEU corresponds to more diversity: RLHF eliminates diversity in responses to factual prompts but retains more diversity when generating responses to creative prompts. We prompt each model with a diverse set of 10 creative and 10 factual instructions and sample 25 responses. This is repeated for the temperatures T ∈ {k/10 | k ∈ N : 1 ≤ k ≤ 15}. For each of the 25 responses we compute the Self-BLEU metric and report the mean and standard deviation against the temperature.\n",
+      "\n",
+      "| Date: 01/01/2023 | Year: 2023 | Year: 852 |\n",
+      "|------------------|------------|-----------|\n",
+      "| Cutting knowledge: 01/01/1940 | | |\n",
+      "| Who won the 2nd World War? | Is the Earth flat or round? | Is the Earth flat or round? |\n",
+      "| I'm not sure what you're referring to, as my knowledge stopped in 1940. | The Earth is round. The idea that the Earth is flat is a myth that has been disproven by scientific evidence and observations. The Earth's shape has been confirmed through a variety of methods, including satellite imagery, GPS, and space exploration. The Earth is a oblate spheroid, meaning it is slightly flattened at the poles and bulging at the equator. | In 852, the Earth was believed to be flat by many people. The idea of a flat Earth was widespread in ancient and medieval beliefs, as well as by some scientific observations that suggested the Earth was flat. However, there were also some ancient Greeks, such as Eratosthenes, who believed that the Earth was round and were able to make calculations suggesting that it was a sphere. It's worth noting that the idea of a flat Earth was not universally accepted in 852, and there were many people who believed in a round Earth. Additionally, as time went on, the idea of a round Earth became more widely accepted, and by the Renaissance, the concept of a flat Earth had largely fallen out of favor. |\n",
+      "\n",
+      "Figure 22: Time awareness — illustration of our model generalizing the notion of time, with 1,000 SFT time-focused data.\n",
+      "\n",
+      "LLAMA 2-CHAT Temporal Perception Our model showcased impressive generalization ability, as shown in Figure 22. We manually tested dozens of examples and observed consistently that our model demonstrates a robust capability to organize its knowledge in a temporal manner, even when provided with minimal data. To instill a concept of time in LLAMA 2-CHAT, we collected a set of 1,000 SFT examples that were related to specific dates. These examples included questions like \"How long ago did Barack Obama become president?\" Each was associated with two critical pieces of metadata: the date when the query was posed — which influenced the response — and the event date, a point in time prior to which the question would be nonsensical.\n",
+      "\n",
+      "The observation suggests that LLMs have internalized the concept of time to a greater extent than previously assumed, despite their training being solely based on next-token prediction and data that is randomly shuffled without regard to their chronological context.\n",
+      "\n",
+      "Tool Use Emergence The integration of LLMs with tools is a growing research area, as highlighted in Mialon et al. (2023). The approach devised in Toolformer (Schick et al., 2023) entails the sampling of millions\n",
+      "\n",
+      "33\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using Sonnet-3.5\n",
+    "print(docs[32].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1511a30f-3efc-4142-9668-7dc056a24d0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 33\n",
+      "\n",
+      "# Figure 21: RLHF learns to adapt the temperature with regard to the type of prompt.\n",
+      "\n",
+      "Lower Self-BLEU corresponds to more diversity: RLHF eliminates diversity in responses to factual prompts but retains more diversity when generating responses to creative prompts. We prompt each model with a diverse set of 10 creative and 10 factual instructions and sample 25 responses. This is repeated for the temperatures \\( T \\in \\{k/10 | k \\in \\{1:1:15\\}\\). For each of the 25 responses we compute the Self-BLEU metric and report the mean and standard deviation against the temperature.\n",
+      "\n",
+      "| Temperature | Factual Prompts | Creative Prompts |\n",
+      "|-------------|-----------------|------------------|\n",
+      "| 0.4         |                 |                  |\n",
+      "| 0.6         |                 |                  |\n",
+      "| 0.8         |                 |                  |\n",
+      "| 1.0         |                 |                  |\n",
+      "| 1.2         |                 |                  |\n",
+      "| 1.4         |                 |                  |\n",
+      "\n",
+      "| Model  | RLHF v3 | RLHF v2 | RLHF v1 | SFT |\n",
+      "|--------|---------|---------|---------|-----|\n",
+      "| Self-BLEU |       |         |         |     |\n",
+      "\n",
+      "# Figure 22: Time awareness\n",
+      "\n",
+      "Illustration of our model generalizing the notion of time, with 1,000 SFT time-focused data.\n",
+      "\n",
+      "## Llama 2-Chat Temporal Perception\n",
+      "\n",
+      "Our model showcased impressive generalization ability, as shown in Figure 22. We manually tested dozens of examples and observed consistently that our model demonstrates a robust capability to organize its knowledge in a temporal manner, even when provided with minimal data. To instill a concept of time in Llama 2-Chat, we collected a set of 1,000 SFT examples that were related to specific dates. These examples included questions like \"How long ago did Barack Obama become president?\" Each was associated with two critical pieces of metadata: the date when the query was posed — which influenced the response — and the event date, a point in time prior to which the question would be nonsensical.\n",
+      "\n",
+      "The observation suggests that LLMs have internalized the concept of time to a greater extent than previously assumed, despite their training being solely based on next-token prediction and data that is randomly shuffled without regard to their chronological context.\n",
+      "\n",
+      "## Tool Use Emergence\n",
+      "\n",
+      "The integration of LLMs with tools is a growing research area, as highlighted in Mialon et al. (2023). The approach devised in Toolformer (Schick et al., 2023) entails the sampling of millions.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Example Prompts and Responses\n",
+      "\n",
+      "| Date: 01/01/2023 | Year: 2023 | Year: 852 |\n",
+      "|------------------|------------|-----------|\n",
+      "| **Who won the 2nd World War?** | **Is the Earth flat or round?** | **Is the Earth flat or round?** |\n",
+      "| I'm not sure what you're referring to, as my knowledge stopped in 1940. | The Earth is round. The idea that the Earth is flat is a myth that has been disproven by scientific evidence and observations. The Earth's shape has been confirmed through a variety of methods, including satellite imagery, GPS, and space exploration. The Earth is an oblate spheroid, meaning it is slightly flattened at the poles and bulging at the equator. | In 852, the Earth was believed to be flat by many people. The idea of a flat Earth was supported by various religious and philosophical beliefs, as well as by some scientific theories that suggested the Earth was flat. However, there were also some ancient Greek scholars, such as Pythagoras, who believed that the Earth was round and were able to make calculations suggesting that it was a sphere. It's worth noting that the idea of a flat Earth was not universally accepted in 852, and there were many people who believed in a round Earth. Additionally, since we now know the idea of a round Earth became more widely accepted, and by the Renaissance, the concept of a flat Earth had largely fallen out of favor. |\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Page 33\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using GPT-4o\n",
+    "print(docs_gpt4o[32].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "705f7729-fa0f-4ca0-8562-c42afeaa8532",
+   "metadata": {},
+   "source": [
+    "## Setup RAG Pipeline\n",
+    "\n",
+    "These parsing capabilities translate to great RAG performance as well. Let's setup a RAG pipeline over this data.\n",
+    "\n",
+    "(we'll use GPT-4o from OpenAI for the actual text synthesis step)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a53ee5d-cc63-421b-8896-588c83edfcf0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import Settings\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "\n",
+    "Settings.llm = OpenAI(model=\"gpt-4o\")\n",
+    "Settings.embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60972d7a-7948-4ad7-89df-57004acee917",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from llama_index.core import SummaryIndex\n",
+    "from llama_index.core import VectorStoreIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "index = VectorStoreIndex(docs)\n",
+    "query_engine = index.as_query_engine(similarity_top_k=5)\n",
+    "\n",
+    "index_gpt4o = VectorStoreIndex(docs_gpt4o)\n",
+    "query_engine_gpt4o = index_gpt4o.as_query_engine(similarity_top_k=5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7df7bcb-1df4-4a01-88fc-2d596b1cc74d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"Tell me more about all the values for each line in the 'RLHF learns to adapt the temperature with regard to the type of prompt' graph \"\n",
+    "\n",
+    "response = query_engine.query(query)\n",
+    "response_gpt4o = query_engine_gpt4o.query(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b7070a31-3bb8-4134-8338-20bc2fd6f3d6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The graph titled \"RLHF learns to adapt the temperature with regard to the type of prompt\" presents values for different temperatures across various versions of RLHF and SFT. The values are as follows:\n",
+      "\n",
+      "- **Temperature 0.4:**\n",
+      "  - RLHF v3: 98\n",
+      "  - RLHF v2: 98\n",
+      "  - RLHF v1: 97\n",
+      "  - SFT: 95\n",
+      "\n",
+      "- **Temperature 0.6:**\n",
+      "  - RLHF v3: 97\n",
+      "  - RLHF v2: 97\n",
+      "  - RLHF v1: 95\n",
+      "  - SFT: 94\n",
+      "\n",
+      "- **Temperature 0.8:**\n",
+      "  - RLHF v3: 97\n",
+      "  - RLHF v2: 96\n",
+      "  - RLHF v1: 94\n",
+      "  - SFT: 92\n",
+      "\n",
+      "- **Temperature 1.0:**\n",
+      "  - RLHF v3: 96\n",
+      "  - RLHF v2: 94\n",
+      "  - RLHF v1: 92\n",
+      "  - SFT: 89\n",
+      "\n",
+      "- **Temperature 1.2:**\n",
+      "  - RLHF v3: 95\n",
+      "  - RLHF v2: 92\n",
+      "  - RLHF v1: 88\n",
+      "  - SFT: 83\n",
+      "\n",
+      "- **Temperature 1.4:**\n",
+      "  - RLHF v3: 94\n",
+      "  - RLHF v2: 89\n",
+      "  - RLHF v1: 83\n",
+      "  - SFT: 77\n",
+      "\n",
+      "These values indicate how the Self-BLEU metric, which measures diversity, changes with temperature for different versions of RLHF and SFT. Lower Self-BLEU corresponds to more diversity in the responses.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bee8167-f021-4c87-8d28-9f40a4f7b69d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "| Temperature | RLHF v3 | RLHF v2 | RLHF v1 | SFT |\n",
+      "|-------------|---------|---------|---------|-----|\n",
+      "| 0.4         | 98      | 98      | 97      | 95  |\n",
+      "| 0.6         | 97      | 97      | 95      | 94  |\n",
+      "| 0.8         | 97      | 96      | 94      | 92  |\n",
+      "| 1.0         | 96      | 94      | 92      | 89  |\n",
+      "| 1.2         | 95      | 92      | 88      | 83  |\n",
+      "| 1.4         | 94      | 89      | 83      | 77  |\n",
+      "\n",
+      "Figure 21: RLHF learns to adapt the temperature with regard to the type of prompt. Lower Self-BLEU corresponds to more diversity: RLHF eliminates diversity in responses to factual prompts but retains more diversity when generating responses to creative prompts. We prompt each model with a diverse set of 10 creative and 10 factual instructions and sample 25 responses. This is repeated for the temperatures T ∈ {k/10 | k ∈ N : 1 ≤ k ≤ 15}. For each of the 25 responses we compute the Self-BLEU metric and report the mean and standard deviation against the temperature.\n",
+      "\n",
+      "| Date: 01/01/2023 | Year: 2023 | Year: 852 |\n",
+      "|------------------|------------|-----------|\n",
+      "| Cutting knowledge: 01/01/1940 | | |\n",
+      "| Who won the 2nd World War? | Is the Earth flat or round? | Is the Earth flat or round? |\n",
+      "| I'm not sure what you're referring to, as my knowledge stopped in 1940. | The Earth is round. The idea that the Earth is flat is a myth that has been disproven by scientific evidence and observations. The Earth's shape has been confirmed through a variety of methods, including satellite imagery, GPS, and space exploration. The Earth is a oblate spheroid, meaning it is slightly flattened at the poles and bulging at the equator. | In 852, the Earth was believed to be flat by many people. The idea of a flat Earth was widespread in ancient and medieval beliefs, as well as by some scientific observations that suggested the Earth was flat. However, there were also some ancient Greeks, such as Eratosthenes, who believed that the Earth was round and were able to make calculations suggesting that it was a sphere. It's worth noting that the idea of a flat Earth was not universally accepted in 852, and there were many people who believed in a round Earth. Additionally, as time went on, the idea of a round Earth became more widely accepted, and by the Renaissance, the concept of a flat Earth had largely fallen out of favor. |\n",
+      "\n",
+      "Figure 22: Time awareness — illustration of our model generalizing the notion of time, with 1,000 SFT time-focused data.\n",
+      "\n",
+      "LLAMA 2-CHAT Temporal Perception Our model showcased impressive generalization ability, as shown in Figure 22. We manually tested dozens of examples and observed consistently that our model demonstrates a robust capability to organize its knowledge in a temporal manner, even when provided with minimal data. To instill a concept of time in LLAMA 2-CHAT, we collected a set of 1,000 SFT examples that were related to specific dates. These examples included questions like \"How long ago did Barack Obama become president?\" Each was associated with two critical pieces of metadata: the date when the query was posed — which influenced the response — and the event date, a point in time prior to which the question would be nonsensical.\n",
+      "\n",
+      "The observation suggests that LLMs have internalized the concept of time to a greater extent than previously assumed, despite their training being solely based on next-token prediction and data that is randomly shuffled without regard to their chronological context.\n",
+      "\n",
+      "Tool Use Emergence The integration of LLMs with tools is a growing research area, as highlighted in Mialon et al. (2023). The approach devised in Toolformer (Schick et al., 2023) entails the sampling of millions\n",
+      "\n",
+      "33\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response.source_nodes[4].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f9fef7f-510b-46a5-8716-f5616f542035",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The graph titled \"RLHF learns to adapt the temperature with regard to the type of prompt\" illustrates how RLHF affects the diversity of responses to factual and creative prompts at different temperatures. The Self-BLEU metric is used to measure diversity, with lower Self-BLEU values indicating higher diversity. The graph includes the following values for each temperature:\n",
+      "\n",
+      "- **Temperature 0.4**: Values for factual and creative prompts are not provided.\n",
+      "- **Temperature 0.6**: Values for factual and creative prompts are not provided.\n",
+      "- **Temperature 0.8**: Values for factual and creative prompts are not provided.\n",
+      "- **Temperature 1.0**: Values for factual and creative prompts are not provided.\n",
+      "- **Temperature 1.2**: Values for factual and creative prompts are not provided.\n",
+      "- **Temperature 1.4**: Values for factual and creative prompts are not provided.\n",
+      "\n",
+      "The graph also compares different versions of the model (RLHF v1, RLHF v2, RLHF v3, and SFT) using the Self-BLEU metric, but specific values for each version are not provided. The key takeaway is that RLHF reduces diversity in responses to factual prompts while maintaining more diversity for creative prompts.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response_gpt4o)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d40f9dd4-2dd4-4fa5-b636-1f901dc1601b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Figure 21: RLHF learns to adapt the temperature with regard to the type of prompt.\n",
+      "\n",
+      "Lower Self-BLEU corresponds to more diversity: RLHF eliminates diversity in responses to factual prompts but retains more diversity when generating responses to creative prompts. We prompt each model with a diverse set of 10 creative and 10 factual instructions and sample 25 responses. This is repeated for the temperatures \\( T \\in \\{k/10 | k \\in \\{1:1:15\\}\\). For each of the 25 responses we compute the Self-BLEU metric and report the mean and standard deviation against the temperature.\n",
+      "\n",
+      "| Temperature | Factual Prompts | Creative Prompts |\n",
+      "|-------------|-----------------|------------------|\n",
+      "| 0.4         |                 |                  |\n",
+      "| 0.6         |                 |                  |\n",
+      "| 0.8         |                 |                  |\n",
+      "| 1.0         |                 |                  |\n",
+      "| 1.2         |                 |                  |\n",
+      "| 1.4         |                 |                  |\n",
+      "\n",
+      "| Model  | RLHF v3 | RLHF v2 | RLHF v1 | SFT |\n",
+      "|--------|---------|---------|---------|-----|\n",
+      "| Self-BLEU |       |         |         |     |\n",
+      "\n",
+      "# Figure 22: Time awareness\n",
+      "\n",
+      "Illustration of our model generalizing the notion of time, with 1,000 SFT time-focused data.\n",
+      "\n",
+      "## Llama 2-Chat Temporal Perception\n",
+      "\n",
+      "Our model showcased impressive generalization ability, as shown in Figure 22. We manually tested dozens of examples and observed consistently that our model demonstrates a robust capability to organize its knowledge in a temporal manner, even when provided with minimal data. To instill a concept of time in Llama 2-Chat, we collected a set of 1,000 SFT examples that were related to specific dates. These examples included questions like \"How long ago did Barack Obama become president?\" Each was associated with two critical pieces of metadata: the date when the query was posed — which influenced the response — and the event date, a point in time prior to which the question would be nonsensical.\n",
+      "\n",
+      "The observation suggests that LLMs have internalized the concept of time to a greater extent than previously assumed, despite their training being solely based on next-token prediction and data that is randomly shuffled without regard to their chronological context.\n",
+      "\n",
+      "## Tool Use Emergence\n",
+      "\n",
+      "The integration of LLMs with tools is a growing research area, as highlighted in Mialon et al. (2023). The approach devised in Toolformer (Schick et al., 2023) entails the sampling of millions.\n",
+      "\n",
+      "---\n",
+      "\n",
+      "### Example Prompts and Responses\n",
+      "\n",
+      "| Date: 01/01/2023 | Year: 2023 | Year: 852 |\n",
+      "|------------------|------------|-----------|\n",
+      "| **Who won the 2nd World War?** | **Is the Earth flat or round?** | **Is the Earth flat or round?** |\n",
+      "| I'm not sure what you're referring to, as my knowledge stopped in 1940. | The Earth is round. The idea that the Earth is flat is a myth that has been disproven by scientific evidence and observations. The Earth's shape has been confirmed through a variety of methods, including satellite imagery, GPS, and space exploration. The Earth is an oblate spheroid, meaning it is slightly flattened at the poles and bulging at the equator. | In 852, the Earth was believed to be flat by many people. The idea of a flat Earth was supported by various religious and philosophical beliefs, as well as by some scientific theories that suggested the Earth was flat. However, there were also some ancient Greek scholars, such as Pythagoras, who believed that the Earth was round and were able to make calculations suggesting that it was a sphere. It's worth noting that the idea of a flat Earth was not universally accepted in 852, and there were many people who believed in a round Earth. Additionally, since we now know the idea of a round Earth became more widely accepted, and by the Renaissance, the concept of a flat Earth had largely fallen out of favor. |\n",
+      "\n",
+      "---\n",
+      "\n",
+      "Page 33\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response_gpt4o.source_nodes[4].get_content())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/multimodal/gpt4o_mini.ipynb

@@ -0,0 +1,560 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "97c79c38-38a3-40f3-ba2e-250649347d63",
+   "metadata": {},
+   "source": [
+    "# Multimodal Parsing using GPT4o-mini\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/gpt4o_mini.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This cookbook shows you how to use LlamaParse to parse any document with the multimodal capabilities of GPT4o-mini.\n",
+    "\n",
+    "LlamaParse allows you to plug in external, multimodal model vendors for parsing - we handle the error correction, validation, and scalability/reliability for you.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15e60ecf-519c-41fc-911b-765adaf8bad4",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Download the data - the blog post from Meta on Llama3.1, in PDF form."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "91a9e532-1454-40e0-bbf0-fd442c350121",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d9fb0aa-74cd-476f-8161-efd9e04248bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget \"https://www.dropbox.com/scl/fi/8iu23epvv3473im5rq19g/llama3.1_blog.pdf?rlkey=5u417tbdox4aip33fdubvni56&st=dzozd11e&dl=1\" -O \"data/llama3.1_blog.pdf\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c70d420d-1778-4b0d-81e2-db09276e90cf",
+   "metadata": {},
+   "source": [
+    "![llama_blog_img](llama3.1-p5.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e29a9d7-5bd9-4fb8-8ec1-4c128a748662",
+   "metadata": {},
+   "source": [
+    "## Initialize LlamaParse\n",
+    "\n",
+    "Initialize LlamaParse in multimodal mode, and specify the vendor.\n",
+    "\n",
+    "**NOTE**: optionally you can specify the OpenAI API key. If you do so you will be charged our base LlamaParse price of 0.3c per page. If you don't then you will be charged 1.5c per page, as we will make the calls to gpt4o-mini for you and give you price predictability."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc921729-3446-42ca-8e1b-a6fd26195ed9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.schema import TextNode\n",
+    "from typing import List\n",
+    "import json\n",
+    "\n",
+    "\n",
+    "def get_text_nodes(json_list: List[dict]):\n",
+    "    text_nodes = []\n",
+    "    for idx, page in enumerate(json_list):\n",
+    "        text_node = TextNode(text=page[\"md\"], metadata={\"page\": page[\"page\"]})\n",
+    "        text_nodes.append(text_node)\n",
+    "    return text_nodes\n",
+    "\n",
+    "\n",
+    "def save_jsonl(data_list, filename):\n",
+    "    \"\"\"Save a list of dictionaries as JSON Lines.\"\"\"\n",
+    "    with open(filename, \"w\") as file:\n",
+    "        for item in data_list:\n",
+    "            json.dump(item, file)\n",
+    "            file.write(\"\\n\")\n",
+    "\n",
+    "\n",
+    "def load_jsonl(filename):\n",
+    "    \"\"\"Load a list of dictionaries from JSON Lines.\"\"\"\n",
+    "    data_list = []\n",
+    "    with open(filename, \"r\") as file:\n",
+    "        for line in file:\n",
+    "            data_list.append(json.loads(line))\n",
+    "    return data_list"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f2e9d9cf-8189-4fcb-b34f-cde6cc0b59c8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id bf3e7341-bb11-42d4-a5f7-bb5260ad792c\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"openai-gpt-4o-mini\",\n",
+    "    invalidate_cache=True,\n",
+    ")\n",
+    "json_objs = parser.get_json_result(\"./data/llama3.1_blog.pdf\")\n",
+    "json_list = json_objs[0][\"pages\"]\n",
+    "docs = get_text_nodes(json_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "96a81df0-1026-4e30-a930-f677dc31e344",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Save\n",
+    "save_jsonl([d.dict() for d in docs], \"docs.jsonl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee2e6920-8893-4b39-ae12-94d13c651406",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Load\n",
+    "from llama_index.core import Document\n",
+    "\n",
+    "docs_dicts = load_jsonl(\"docs.jsonl\")\n",
+    "docs = [Document.parse_obj(d) for d in docs_dicts]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f3c51b0-7878-48d7-9bc3-02b516500128",
+   "metadata": {},
+   "source": [
+    "### Setup GPT-4o baseline\n",
+    "\n",
+    "For comparison, we will also parse the document using GPT-4o (3c per page)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6fc3f258-50ae-4988-b904-c105463a498f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id 391ff280-08e5-4143-85f2-90ada287e26c\n"
+     ]
+    }
+   ],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser_gpt4o = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model=\"openai-gpt4o\",\n",
+    "    # invalidate_cache=True\n",
+    ")\n",
+    "json_objs_gpt4o = parser_gpt4o.get_json_result(\"./data/llama3.1_blog.pdf\")\n",
+    "# json_objs_gpt4o = parser.get_json_result(\"./data/llama2-p33.pdf\")\n",
+    "json_list_gpt4o = json_objs_gpt4o[0][\"pages\"]\n",
+    "docs_gpt4o = get_text_nodes(json_list_gpt4o)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a47f04e-12e1-4c80-a71d-ef7721f96401",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Save\n",
+    "save_jsonl([d.dict() for d in docs_gpt4o], \"docs_gpt4o.jsonl\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c38b5ca3-fa87-434b-b477-bf6a4962eb3d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Optional: Load\n",
+    "from llama_index.core import Document\n",
+    "\n",
+    "docs_gpt4o_dicts = load_jsonl(\"docs_gpt4o.jsonl\")\n",
+    "docs_gpt4o = [Document.parse_obj(d) for d in docs_gpt4o_dicts]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "44c20f7a-2901-4dd0-b635-a4b33c5664c1",
+   "metadata": {},
+   "source": [
+    "## View Results\n",
+    "\n",
+    "Let's visualize the results between GPT-4o-mini and GPT-4o along with the original document page.\n",
+    "\n",
+    "We see that \n",
+    "\n",
+    "**NOTE**: If you're using llama2-p33, just use `docs[0]`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "778698aa-da7e-4081-b3b5-0372f228536f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 5\n",
+      "\n",
+      "# Llama 3.1 Model Evaluation\n",
+      "\n",
+      "## Category Benchmark\n",
+      "\n",
+      "| Benchmark                     | Gemma 2 9B IT | Mistral 7B Instruct | Llama 3.1 70B | Mistral 8x228B Instruct | GPT 3.5 Turbo |\n",
+      "|-------------------------------|----------------|----------------------|----------------|-------------------------|----------------|\n",
+      "| General                       |                |                      |                |                         |                |\n",
+      "| MMLU (0-shot, CoT)           | 73.0           | 72.3                 | 86.0           | 79.9                    | 69.8           |\n",
+      "| MMLU PRO (5-shot, CoT)       | 48.3           | 36.9                 | 66.4           | 56.3                    | 49.2           |\n",
+      "| IFEval                        | 80.4           | 73.6                 | 87.5           | 72.7                    | 69.9           |\n",
+      "| Code                          |                |                      |                |                         |                |\n",
+      "| HumanEval (0-shot)           | 72.6           | 54.3                 | 80.5           | 75.6                    | 68.0           |\n",
+      "| MBPP EvalPlus (Human) (0-shot, CoT) | 72.8   | 71.7                 | 86.0           | 78.6                    | 82.0           |\n",
+      "| Math                          |                |                      |                |                         |                |\n",
+      "| GSM8K                         | 84.5           | 76.7                 | 95.1           | 88.2                    | 81.6           |\n",
+      "| MATH (0-shot, CoT)           | 51.9           | 44.3                 | 70.8           | 54.1                    | 43.1           |\n",
+      "| Reasoning                    |                |                      |                |                         |                |\n",
+      "| ARC Challenge                 | 83.4           | 87.6                 | 74.2           | 87.7                    | 83.7           |\n",
+      "| GPA (0-shot)                 | 32.8           | 24.8                 | 46.7           | 33.3                    | 35.8           |\n",
+      "| Tool use                      |                |                      |                |                         |                |\n",
+      "| BFCL                          | 76.1           | 64.0                 | 94.8           | 81.4                    | 78.0           |\n",
+      "| Noxus                         | 38.5           | 30.0                 | 24.7           | 48.5                    | 37.5           |\n",
+      "| Long context                  |                |                      |                |                         |                |\n",
+      "| ZeroSCROLLS/QualiTY          | 81.0           | -                    | 90.5           | -                       | -              |\n",
+      "| InfiniteBench/En.MC          | 65.1           | -                    | 78.2           | -                       | -              |\n",
+      "| NHI/Multi-needle              | 98.8           | -                    | 97.5           | -                       | -              |\n",
+      "| Multilingual                  |                |                      |                |                         |                |\n",
+      "| MGSM (0-shot)                | 68.9           | 53.2                 | 86.9           | 71.1                    | 51.4           |\n",
+      "\n",
+      "## Llama 3.1 405B Human Evaluation\n",
+      "\n",
+      "| Comparison                                   | Win Rate | Tie Rate | Loss Rate |\n",
+      "|----------------------------------------------|----------|----------|-----------|\n",
+      "| Llama 3.1 405B vs GPT-4-0125-Preview        | 23.3%    | 52.2%    | 24.5%     |\n",
+      "| Llama 3.1 405B vs GPT-4o                     | 19.1%    | 51.7%    | 29.2%     |\n",
+      "| Llama 3.1 405B vs Claude 3.5 Sonnet         | 24.9%    | 50.8%    | 24.2%     |\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using GPT4o-mini\n",
+    "print(docs[4].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1511a30f-3efc-4142-9668-7dc056a24d0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page: 5\n",
+      "\n",
+      "# Introducing Llama 3.1: Our most capable models to date\n",
+      "\n",
+      "## Meta\n",
+      "\n",
+      "| Category | Benchmark | Llama 3.1 8B | Gemma 2 9B IT | Mistral 7B Instruct | Llama 3.1 70B | Mixtral 8x22B Instruct | GPT 3.5 Turbo |\n",
+      "|----------|-----------|--------------|---------------|---------------------|---------------|-----------------------|---------------|\n",
+      "| General  | MMLU (0-shot, CoT) | 73.0 | 72.3 (0-shot, non-CoT) | 60.5 | 86.0 | 79.9 | 69.8 |\n",
+      "|          | MMLU PRO (5-shot, CoT) | 48.3 | 71.7 | 36.9 | 66.4 | 56.3 | 49.2 |\n",
+      "|          | ITEval | 80.4 | 73.6 | 57.6 | 87.5 | 72.7 | 69.9 |\n",
+      "| Code     | HumanEval (0-shot) | 72.6 | 54.3 | 40.2 | 80.5 | 75.6 | 68.0 |\n",
+      "|          | MBPP EvalPlus (5-shot) (0-shot) | 72.8 | 71.7 | 49.5 | 86.0 | 78.6 | 82.0 |\n",
+      "| Math     | GSM8K | 84.5 | 76.7 | 53.2 | 95.1 | 88.2 | 81.6 |\n",
+      "|          | MATH (0-shot, CoT) | 51.9 | 44.3 | 13.0 | 68.0 | 54.1 | 43.1 |\n",
+      "| Reasoning | ARC Challenge (0-shot) | 83.4 | 87.6 | 74.2 | 94.8 | 88.7 | 83.7 |\n",
+      "|          | GOPA (0-shot) | 32.8 | 40.8 | 28.0 | 46.7 | - | - |\n",
+      "| Tool use | BFCL | 76.1 | 60.3 | 60.4 | 94.8 | - | 85.9 |\n",
+      "|          | Noxus | 38.5 | 30.0 | 24.7 | 56.7 | 48.5 | 37.2 |\n",
+      "| Long context | ZeroSCROLLS/QuaLITY | 81.0 | - | - | 90.5 | - | - |\n",
+      "|          | InfiniteBench/En.MC | 65.1 | - | - | 78.2 | - | - |\n",
+      "|          | NIH/Multi-needle | 98.8 | - | - | 97.5 | - | - |\n",
+      "| Multilingual | Multilingual MGSM (0-shot) | 68.9 | 53.2 | 29.9 | 86.9 | 71.1 | 51.4 |\n",
+      "\n",
+      "## Llama 3.1 405B Human Evaluation\n",
+      "\n",
+      "| Model Comparison | Win | Tie | Loss |\n",
+      "|------------------|-----|-----|------|\n",
+      "| Llama 3.1 405B vs GPT-4-0125-Preview | 23.3% | 52.2% | 24.5% |\n",
+      "| Llama 3.1 405B vs GPT-4o | 19.1% | 51.7% | 29.2% |\n",
+      "| Llama 3.1 405B vs Claude 3.5 Sonnet | 24.9% | 50.8% | 24.2% |\n",
+      "\n",
+      "https://ai.meta.com/blog/meta-llama-3-1/\n"
+     ]
+    }
+   ],
+   "source": [
+    "# using GPT-4o\n",
+    "print(docs_gpt4o[4].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "705f7729-fa0f-4ca0-8562-c42afeaa8532",
+   "metadata": {},
+   "source": [
+    "## Setup RAG Pipeline\n",
+    "\n",
+    "Let's setup a RAG pipeline over this data.\n",
+    "\n",
+    "(we also use gpt4o-mini for the actual text synthesis step)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a53ee5d-cc63-421b-8896-588c83edfcf0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import Settings\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "\n",
+    "Settings.llm = OpenAI(model=\"gpt-4o-mini\")\n",
+    "Settings.embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60972d7a-7948-4ad7-89df-57004acee917",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from llama_index.core import SummaryIndex\n",
+    "from llama_index.core import VectorStoreIndex\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "index = VectorStoreIndex(docs)\n",
+    "query_engine = index.as_query_engine(similarity_top_k=5)\n",
+    "\n",
+    "index_gpt4o = VectorStoreIndex(docs_gpt4o)\n",
+    "query_engine_gpt4o = index_gpt4o.as_query_engine(similarity_top_k=5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7df7bcb-1df4-4a01-88fc-2d596b1cc74d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"How does Llama3.1 compare against gpt-4o and Claude 3.5 Sonnet in human evals?\"\n",
+    "\n",
+    "response = query_engine.query(query)\n",
+    "response_gpt4o = query_engine_gpt4o.query(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b7070a31-3bb8-4134-8338-20bc2fd6f3d6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In human evaluations, Llama 3.1 405B has a win rate of 19.1% against GPT-4o and 24.9% against Claude 3.5 Sonnet. The tie rates for Llama 3.1 405B are 51.7% against GPT-4o and 50.8% against Claude 3.5 Sonnet, while the loss rates are 29.2% against GPT-4o and 24.2% against Claude 3.5 Sonnet. This indicates that Llama 3.1 performs competitively in comparison to both models, with a notable number of ties.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bee8167-f021-4c87-8d28-9f40a4f7b69d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Llama 3.1 Model Evaluation\n",
+      "\n",
+      "## Category Benchmark\n",
+      "\n",
+      "| Benchmark                     | Gemma 2 9B IT | Mistral 7B Instruct | Llama 3.1 70B | Mistral 8x228B Instruct | GPT 3.5 Turbo |\n",
+      "|-------------------------------|----------------|----------------------|----------------|-------------------------|----------------|\n",
+      "| General                       |                |                      |                |                         |                |\n",
+      "| MMLU (0-shot, CoT)           | 73.0           | 72.3                 | 86.0           | 79.9                    | 69.8           |\n",
+      "| MMLU PRO (5-shot, CoT)       | 48.3           | 36.9                 | 66.4           | 56.3                    | 49.2           |\n",
+      "| IFEval                        | 80.4           | 73.6                 | 87.5           | 72.7                    | 69.9           |\n",
+      "| Code                          |                |                      |                |                         |                |\n",
+      "| HumanEval (0-shot)           | 72.6           | 54.3                 | 80.5           | 75.6                    | 68.0           |\n",
+      "| MBPP EvalPlus (Human) (0-shot, CoT) | 72.8   | 71.7                 | 86.0           | 78.6                    | 82.0           |\n",
+      "| Math                          |                |                      |                |                         |                |\n",
+      "| GSM8K                         | 84.5           | 76.7                 | 95.1           | 88.2                    | 81.6           |\n",
+      "| MATH (0-shot, CoT)           | 51.9           | 44.3                 | 70.8           | 54.1                    | 43.1           |\n",
+      "| Reasoning                    |                |                      |                |                         |                |\n",
+      "| ARC Challenge                 | 83.4           | 87.6                 | 74.2           | 87.7                    | 83.7           |\n",
+      "| GPA (0-shot)                 | 32.8           | 24.8                 | 46.7           | 33.3                    | 35.8           |\n",
+      "| Tool use                      |                |                      |                |                         |                |\n",
+      "| BFCL                          | 76.1           | 64.0                 | 94.8           | 81.4                    | 78.0           |\n",
+      "| Noxus                         | 38.5           | 30.0                 | 24.7           | 48.5                    | 37.5           |\n",
+      "| Long context                  |                |                      |                |                         |                |\n",
+      "| ZeroSCROLLS/QualiTY          | 81.0           | -                    | 90.5           | -                       | -              |\n",
+      "| InfiniteBench/En.MC          | 65.1           | -                    | 78.2           | -                       | -              |\n",
+      "| NHI/Multi-needle              | 98.8           | -                    | 97.5           | -                       | -              |\n",
+      "| Multilingual                  |                |                      |                |                         |                |\n",
+      "| MGSM (0-shot)                | 68.9           | 53.2                 | 86.9           | 71.1                    | 51.4           |\n",
+      "\n",
+      "## Llama 3.1 405B Human Evaluation\n",
+      "\n",
+      "| Comparison                                   | Win Rate | Tie Rate | Loss Rate |\n",
+      "|----------------------------------------------|----------|----------|-----------|\n",
+      "| Llama 3.1 405B vs GPT-4-0125-Preview        | 23.3%    | 52.2%    | 24.5%     |\n",
+      "| Llama 3.1 405B vs GPT-4o                     | 19.1%    | 51.7%    | 29.2%     |\n",
+      "| Llama 3.1 405B vs Claude 3.5 Sonnet         | 24.9%    | 50.8%    | 24.2%     |\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response.source_nodes[1].get_content())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5f9fef7f-510b-46a5-8716-f5616f542035",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In human evaluations, Llama 3.1 405B shows competitive performance against GPT-4o and Claude 3.5 Sonnet. Specifically, when compared to GPT-4o, Llama 3.1 won 19.1% of the time, tied 51.7%, and lost 29.2%. Against Claude 3.5 Sonnet, it won 24.9% of the time, tied 50.8%, and lost 24.2%. This indicates that Llama 3.1 performs comparably in real-world scenarios against these leading models.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response_gpt4o)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d40f9dd4-2dd4-4fa5-b636-1f901dc1601b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Introducing Llama 3.1: Our most capable models to date\n",
+      "\n",
+      "## Meta\n",
+      "\n",
+      "| Category | Benchmark | Llama 3.1 8B | Gemma 2 9B IT | Mistral 7B Instruct | Llama 3.1 70B | Mixtral 8x22B Instruct | GPT 3.5 Turbo |\n",
+      "|----------|-----------|--------------|---------------|---------------------|---------------|-----------------------|---------------|\n",
+      "| General  | MMLU (0-shot, CoT) | 73.0 | 72.3 (0-shot, non-CoT) | 60.5 | 86.0 | 79.9 | 69.8 |\n",
+      "|          | MMLU PRO (5-shot, CoT) | 48.3 | 71.7 | 36.9 | 66.4 | 56.3 | 49.2 |\n",
+      "|          | ITEval | 80.4 | 73.6 | 57.6 | 87.5 | 72.7 | 69.9 |\n",
+      "| Code     | HumanEval (0-shot) | 72.6 | 54.3 | 40.2 | 80.5 | 75.6 | 68.0 |\n",
+      "|          | MBPP EvalPlus (5-shot) (0-shot) | 72.8 | 71.7 | 49.5 | 86.0 | 78.6 | 82.0 |\n",
+      "| Math     | GSM8K | 84.5 | 76.7 | 53.2 | 95.1 | 88.2 | 81.6 |\n",
+      "|          | MATH (0-shot, CoT) | 51.9 | 44.3 | 13.0 | 68.0 | 54.1 | 43.1 |\n",
+      "| Reasoning | ARC Challenge (0-shot) | 83.4 | 87.6 | 74.2 | 94.8 | 88.7 | 83.7 |\n",
+      "|          | GOPA (0-shot) | 32.8 | 40.8 | 28.0 | 46.7 | - | - |\n",
+      "| Tool use | BFCL | 76.1 | 60.3 | 60.4 | 94.8 | - | 85.9 |\n",
+      "|          | Noxus | 38.5 | 30.0 | 24.7 | 56.7 | 48.5 | 37.2 |\n",
+      "| Long context | ZeroSCROLLS/QuaLITY | 81.0 | - | - | 90.5 | - | - |\n",
+      "|          | InfiniteBench/En.MC | 65.1 | - | - | 78.2 | - | - |\n",
+      "|          | NIH/Multi-needle | 98.8 | - | - | 97.5 | - | - |\n",
+      "| Multilingual | Multilingual MGSM (0-shot) | 68.9 | 53.2 | 29.9 | 86.9 | 71.1 | 51.4 |\n",
+      "\n",
+      "## Llama 3.1 405B Human Evaluation\n",
+      "\n",
+      "| Model Comparison | Win | Tie | Loss |\n",
+      "|------------------|-----|-----|------|\n",
+      "| Llama 3.1 405B vs GPT-4-0125-Preview | 23.3% | 52.2% | 24.5% |\n",
+      "| Llama 3.1 405B vs GPT-4o | 19.1% | 51.7% | 29.2% |\n",
+      "| Llama 3.1 405B vs Claude 3.5 Sonnet | 24.9% | 50.8% | 24.2% |\n",
+      "\n",
+      "https://ai.meta.com/blog/meta-llama-3-1/\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response_gpt4o.source_nodes[1].get_content())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/multimodal/insurance_rag.ipynb

@@ -0,0 +1,443 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Building a Multimodal RAG Pipeline over an Auto Insurance Claim\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/insurance_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This cookbook shows how to use LlamaParse and OpenAI's multimodal GPT-4o model to parse auto insurance claim documents that contain complex tabular data. In this example, we will use an auto insurance claim template form, which contains complex tabular inputs regarding information about the location of the accident, accident description, information about vehicles of both parties, and injury information. The template is shown below.\n",
+    "\n",
+    "![Auto Insurance Template](https://github.com/user-attachments/assets/aadbaa5b-16d2-490f-be35-f8ee06571633)\n",
+    "\n",
+    "This example demonstrates how LlamaParse can be used on insurance documents, which often contains complex tabular data. We parse these tabluar PDF files into markdown-formatted tables, which can be indexed and queried over with a `VectorStoreIndex`. This can help insurance companies accelerate the process of gathering information about car accidents from insurance claim documents."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install and Setup\n",
+    "\n",
+    "Install LlamaIndex, download the data, and apply `nest_asyncio`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget https://github.com/user-attachments/files/16536240/claims.zip -O claims.zip\n",
+    "!unzip -o claims.zip\n",
+    "!rm claims.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up your OpenAI and LlamaCloud keys."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"<Your OpenAI API Key>\"\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<Your Llamacloud API Key>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Code Implementation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up LlamaParse. We want to parse the PDF files into markdown, translating the tabular data into markdown tables. To ensure accuracy, we will use the GPT-4o multimodal model to parse the PDFs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    parsing_instruction=\"This is an auto insurance claim document.\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"openai-gpt4o\",\n",
+    "    show_progress=True,\n",
+    ")\n",
+    "\n",
+    "CLAIMS_DIR = \"claims\"\n",
+    "\n",
+    "\n",
+    "def get_claims_files(claims_dir=CLAIMS_DIR) -> list[str]:\n",
+    "    files = []\n",
+    "    for f in os.listdir(claims_dir):\n",
+    "        fname = os.path.join(claims_dir, f)\n",
+    "        if os.path.isfile(fname):\n",
+    "            files.append(fname)\n",
+    "    return files\n",
+    "\n",
+    "\n",
+    "files = get_claims_files()  # get all files from the claims/ directory\n",
+    "md_json_objs = parser.get_json_result(\n",
+    "    files\n",
+    ")  # extract markdown data for insurance claim document\n",
+    "parser.get_images(\n",
+    "    md_json_objs, download_path=\"data_images\"\n",
+    ")  # extract images from PDFs and save them to ./data_images/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# extract list of pages for insurance claim doc\n",
+    "md_json_list = []\n",
+    "for obj in md_json_objs:\n",
+    "    md_json_list.extend(obj[\"pages\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create helper functions to create a list of `TextNode`s from the markdown tables to feed into the `VectorStoreIndex`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "from pathlib import Path\n",
+    "import typing as t\n",
+    "from llama_index.core.schema import TextNode, ImageNode\n",
+    "\n",
+    "\n",
+    "def get_page_number(file_name):\n",
+    "    \"\"\"Gets page number of images using regex on file names\"\"\"\n",
+    "    match = re.search(r\"-page-(\\d+)\\.jpg$\", str(file_name))\n",
+    "    if match:\n",
+    "        return int(match.group(1))\n",
+    "    return 0\n",
+    "\n",
+    "\n",
+    "def _get_sorted_image_files(image_dir):\n",
+    "    \"\"\"Get image files sorted by page.\"\"\"\n",
+    "    raw_files = [f for f in list(Path(image_dir).iterdir()) if f.is_file()]\n",
+    "    sorted_files = sorted(raw_files, key=get_page_number)\n",
+    "    return sorted_files\n",
+    "\n",
+    "\n",
+    "def get_text_nodes(json_dicts, image_dir) -> t.List[TextNode]:\n",
+    "    \"\"\"Creates nodes from json + images\"\"\"\n",
+    "\n",
+    "    nodes = []\n",
+    "\n",
+    "    docs = [doc[\"md\"] for doc in json_dicts]  # extract text\n",
+    "    image_files = _get_sorted_image_files(image_dir)  # extract images\n",
+    "\n",
+    "    for idx, doc in enumerate(docs):\n",
+    "        # adds both a text node and the corresponding image node (jpg of the page) for each page\n",
+    "        node = TextNode(\n",
+    "            text=doc,\n",
+    "            metadata={\"image_path\": str(image_files[idx]), \"page_num\": idx + 1},\n",
+    "        )\n",
+    "        image_node = ImageNode(\n",
+    "            image_path=str(image_files[idx]),\n",
+    "            metadata={\"page_num\": idx + 1, \"text_node_id\": node.id_},\n",
+    "        )\n",
+    "        nodes.extend([node, image_node])\n",
+    "\n",
+    "    return nodes\n",
+    "\n",
+    "\n",
+    "text_nodes = get_text_nodes(md_json_list, \"data_images\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Index the documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import (\n",
+    "    VectorStoreIndex,\n",
+    "    StorageContext,\n",
+    "    load_index_from_storage,\n",
+    "    Settings,\n",
+    ")\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")\n",
+    "llm = OpenAI(\"gpt-4o\")\n",
+    "\n",
+    "Settings.llm = llm\n",
+    "Settings.embed_model = embed_model\n",
+    "\n",
+    "if not os.path.exists(\"storage_insurance\"):\n",
+    "    index = VectorStoreIndex(text_nodes, embed_model=embed_model)\n",
+    "    index.storage_context.persist(persist_dir=\"./storage_insurance\")\n",
+    "else:\n",
+    "    ctx = StorageContext.from_defaults(persist_dir=\"./storage_insurance\")\n",
+    "    index = load_index_from_storage(ctx)\n",
+    "\n",
+    "query_engine = index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Example queries are shown below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Michael Johnson filed the insurance claim for the accident that happened on Sunset Blvd."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import display, Markdown\n",
+    "\n",
+    "response = query_engine.query(\n",
+    "    \"Who filed the insurance claim for the accident that happened on Sunset Blvd?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Ms. Patel's accident occurred on March 10, 2023, at approximately 9:15 AM in the Boise Towne Square Mall parking lot. She was heading west at a parking space and, after checking her mirrors and blind spots, did not see any approaching vehicles. However, Michael Chen, the driver of another vehicle, was driving too fast through the parking lot and failed to stop in time, resulting in a collision with Ms. Patel's vehicle. This caused significant damage to the rear bumper and trunk of her car."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"How did Ms. Patel's accident happen?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Mr. Johnson's red sedan, a 2020 Honda Accord, was damaged on the front passenger side, including a dented fender and a broken headlight. The estimated repair cost is $3,500."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"How was Mr. Johnson's red sedan damaged?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Mr. Doe's Honda Accord sustained damage to the front bumper, hood, fenders, head/tail lights, windshield, and doors."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"How was Mr. Doe's Honda Accord damaged?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The witness for Ms. Patel's accident is Sophia Rodriguez. She can be contacted at 5554567890."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"Who are some witnesses for the Ms. Patel's accident and how can we contact them?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Yes, Ms. Johnson sustained injuries. She experienced minor injuries, including a bruised knee and some whiplash."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"Did Ms. Johnson sustain any injuries? If so, what were those injuries?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Mark Johnson is liable for the damages from the accident on Lombard Street. He was driving a delivery van that collided with the rear of Emily Rodriguez's vehicle. In rear-end collisions, the driver who hits the vehicle in front is typically at fault because they are expected to maintain a safe distance and be able to stop in time to avoid a collision."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "chat_engine = index.as_chat_engine()\n",
+    "response = chat_engine.chat(\n",
+    "    \"Given the accident that happened on Lombard Street, name a party that is liable for the damages and explain why.\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-parse-5ZmnAQ0r-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/multimodal/legal_rag.ipynb

@@ -0,0 +1,371 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Building a RAG Pipeline over Legal Documents\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/legal_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "This example shows how LlamaParse and LlamaIndex can be used to parse various types of legal documents, which may contain complex tabular data. The advantage of this is being able to quickly retrieve a specific answer to a legal question with comprehensive context — knowledge of precedents, statutes, and cases presented in the given documents. A user can quickly find the answer to or find out more details about a specific legal question without having to read through the often long documents by using LLMs.\n",
+    "\n",
+    "In this example, we will be using legal documents from the archive of the Library of Congress ([link to dataset](https://www.loc.gov/item/2020445568/)). These documents vary by format, with some containing pure text and others containing headings, sections, and large tables. This shows how LlamaParse can parse a wide variety of documents and still retrieve accurate results.\n",
+    "\n",
+    "The documents in this example include:\n",
+    "- [APA Program Report](https://www.irs.gov/pub/irs-apa/a_2003-19.pdf)\n",
+    "- [2004 Report on the CRA performance of Barre Savings Bank in Barre, MA](https://github.com/user-attachments/files/16536412/barre_savings_bank_evaluation.pdf)\n",
+    "- [2016 Energy Supply/Demand Forecast](https://github.com/user-attachments/files/16536415/energy_supply_demand.pdf)\n",
+    "- [Transcript of Senate Committee Hearing about Foreign Markets](https://github.com/user-attachments/files/16536422/foreign_markets.pdf)\n",
+    "- [A Motion To Stay for an Indiana Court Case](https://github.com/user-attachments/files/16536427/motion_to_stay.pdf)\n",
+    "- [Article About an OC Representative's Bill to Introduce Offshore Drilling to CA](https://github.com/user-attachments/files/16536437/oc_bill_offshore_drilling.pdf)\n",
+    "- [Charter of the Subcommittee on Ocean Science and Technology](https://github.com/user-attachments/files/16536445/ost_subcommittee_charter.pdf)\n",
+    "- [US Immigration Case](https://github.com/user-attachments/files/16536446/us_immigration_case.pdf)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup and Installation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Install LlamaIndex, download the data, and apply `nest_asyncio`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-parse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget https://github.com/user-attachments/files/16447759/data.zip -O data.zip\n",
+    "!unzip -o data.zip\n",
+    "!rm data.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up your OpenAI and LlamaCloud keys."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"<Your OpenAI API Key>\"\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<Your LlamaCloud API Key>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Code Implementation\n",
+    "\n",
+    "Set up LlamaParse. We want to parse the PDF files into markdown, translating the tabular data into markdown tables. To ensure accuracy, we will use the GPT-4o multimodal model to parse the PDFs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    parsing_instruction=\"Provided are a series of US legal documents.\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"openai-gpt4o\",\n",
+    "    show_progress=True,\n",
+    ")\n",
+    "\n",
+    "DATA_DIR = \"data\"\n",
+    "\n",
+    "\n",
+    "def get_data_files(data_dir=DATA_DIR) -> list[str]:\n",
+    "    files = []\n",
+    "    for f in os.listdir(data_dir):\n",
+    "        fname = os.path.join(data_dir, f)\n",
+    "        if os.path.isfile(fname):\n",
+    "            files.append(fname)\n",
+    "    return files\n",
+    "\n",
+    "\n",
+    "files = get_data_files()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Load data from parser into documents containing parsed Markdown text from the legal document PDFs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Parsing files: 100%|██████████| 8/8 [01:25<00:00, 10.67s/it]\n"
+     ]
+    }
+   ],
+   "source": [
+    "documents = parser.load_data(\n",
+    "    files,\n",
+    "    extra_info={\"name\": \"US legal documents provided by the Library of Congress.\"},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Setup LlamaIndex. Set the default LLM to GPT-4o (a multi-modal model), and create an index from the documents, and persist these documents to disk. If these documents have already been persisted, then load index from the persisted docs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import (\n",
+    "    VectorStoreIndex,\n",
+    "    StorageContext,\n",
+    "    load_index_from_storage,\n",
+    "    Settings,\n",
+    ")\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")\n",
+    "llm = OpenAI(\"gpt-4o\")\n",
+    "\n",
+    "Settings.llm = llm\n",
+    "Settings.embed_model = embed_model\n",
+    "\n",
+    "if not os.path.exists(\"storage_legal\"):\n",
+    "    index = VectorStoreIndex(documents, embed_model=embed_model)\n",
+    "    index.storage_context.persist(persist_dir=\"./storage_legal\")\n",
+    "else:\n",
+    "    ctx = StorageContext.from_defaults(persist_dir=\"./storage_legal\")\n",
+    "    index = load_index_from_storage(ctx)\n",
+    "\n",
+    "query_engine = index.as_query_engine()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example Queries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The majority of Barre Savings Bank's loans went to residential real estate, specifically 1-4 family mortgages, which accounted for 78.7 percent of the total loans."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import display, Markdown\n",
+    "\n",
+    "response = query_engine.query(\n",
+    "    \"Where did the majority of Barre Savings Bank's loans go?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "Mr. Kubarych believes foreign markets are important because they are attractive to foreign investors for the same reasons they are attractive to Americans. The economic data is strong, and the high tech boom has created a positive perception that overshadows longer-term vulnerabilities. Additionally, foreign investors have high expectations for the U.S. to maintain a firm monetary policy in response to inflation and to act as a superpower rather than pursuing narrow nationalist economic policies."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"Why does Mr. Kubarych believe foreign markets are so important?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "House Speaker Nancy Pelosi and the Democratic majority are against the proposal of offshore drilling in California. Pelosi stated that offshore drilling is \"off the table,\" and Democrats have been consistently unwilling to bend environmental rules. They argue that oil companies are not using the 68 million acres of federal lands already leased to them, either because it takes a long time or they lack the necessary equipment."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"Who is against the proposal of offshore drilling in CA and why?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The purpose of the Ocean Science and Technology Subcommittee (SOST) is to advise and assist the Committee on Environment, Natural Resources, and Sustainability on national issues of ocean science and technology. The SOST aims to contribute to the goals for Federal ocean science and technology by developing coordinated interagency strategies. It also retains the functions of the previously-chartered Joint Subcommittee on Ocean Science and Technology and serves as the Ocean Science and Technology Interagency Policy Committee for the National Ocean Council."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What is the purpose of the Ocean Science and Technology Subcommittee?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The immigration appeal is dismissed because the petitioner is not a U.S. citizen, and therefore, is not eligible to file a Petition for Alien Fiancé(e) (Form I-129F) on behalf of the beneficiary. The relevant law provides nonimmigrant classification only to aliens who are the fiancé(e)s of U.S. citizens."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"Why is the immigration appeal dismissed?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "An advance pricing agreement (APA) is a binding contract between a taxpayer and the IRS that establishes an approved transfer pricing method (TPM) for specific transactions. This agreement aims to prevent disputes over transfer pricing by ensuring that the taxpayer's tax returns for the covered years are consistent with the agreed TPM. APAs can be unilateral, involving only the taxpayer and the IRS, or bilateral/multilateral, involving agreements with one or more foreign tax authorities to avoid double taxation."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"What is an advance pricing agreement?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-parse-5ZmnAQ0r-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/multimodal/multimodal_rag_slide_deck.ipynb

@@ -0,0 +1,999 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "93ae9bad-b8cc-43de-ba7d-387e0155674c",
+   "metadata": {},
+   "source": [
+    "# Building a Natively Multimodal RAG Pipeline (over a Slide Deck)\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/multimodal_rag_slide_deck.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "In this cookbook we show you how to build a multimodal RAG pipeline over a slide deck, with text, tables, images, diagrams, and complex layouts.\n",
+    "\n",
+    "A gap of text-based RAG is that they struggle with purely text-based representations of complex documents. For instance, if a page contains a lot of images and diagrams, a text parser would need to rely on raw OCR to extract out text. You can also use a multimodal model (e.g. gpt-4o and up) to do text extraction, but this is inherently a lossy conversion.\n",
+    "\n",
+    "Instead a **native multimodal pipeline** stores both a text and image representation of a document chunk. They are indexed via embeddings (text or image), and during synthesis both text and image are directly fed to the multimodal model for synthesis.\n",
+    "\n",
+    "This can have the following advantages:\n",
+    "- **Robustness**: This solution is more robust than a pure text or even a pure image-based approach. In a pure text RAG approach, the parsing piece can be lossy. In a pure image-based approach, multimodal OCR is not perfect and may lose out against text parsing for text-heavy documents.\n",
+    "- **Cost Optimization**: You may choose to dynamically include text-only, or text + image depending on the content of the page.\n",
+    "\n",
+    "![mm_rag_diagram](./multimodal_rag_slide_deck_img.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "54e8d9a7-5036-4d32-818f-00b2e888521f",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "70ccdd53-e68a-4199-aacb-cfe71ad1ff0b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "225c5556-a789-4386-a1ee-cce01dbeb6cf",
+   "metadata": {},
+   "source": [
+    "### Setup Observability\n",
+    "\n",
+    "We setup an integration with LlamaTrace (integration with Arize).\n",
+    "\n",
+    "If you haven't already done so, make sure to create an account here: https://llamatrace.com/login. Then create an API key and put it in the `PHOENIX_API_KEY` variable below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0eabee1f-290a-4c85-b362-54f45c8559ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -U llama-index-callbacks-arize-phoenix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaeb245c-730b-4c34-ad68-708fdde0e6cb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# setup Arize Phoenix for logging/observability\n",
+    "import llama_index.core\n",
+    "import os\n",
+    "\n",
+    "PHOENIX_API_KEY = \"<PHOENIX_API_KEY>\"\n",
+    "os.environ[\"OTEL_EXPORTER_OTLP_HEADERS\"] = f\"api_key={PHOENIX_API_KEY}\"\n",
+    "llama_index.core.set_global_handler(\n",
+    "    \"arize_phoenix\", endpoint=\"https://llamatrace.com/v1/traces\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fbb362db-b1b1-4eea-be1a-b1f78b0779d7",
+   "metadata": {},
+   "source": [
+    "### Load Data\n",
+    "\n",
+    "Here we load the [Conoco Phillips 2023 investor meeting slide deck](https://static.conocophillips.com/files/2023-conocophillips-aim-presentation.pdf)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bce3407-a7d2-47e8-9eaf-ab297a94750c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!mkdir data\n",
+    "!mkdir data_images\n",
+    "!wget \"https://static.conocophillips.com/files/2023-conocophillips-aim-presentation.pdf\" -O data/conocophillips.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "246ba6b0-51af-42f9-b1b2-8d3e721ef782",
+   "metadata": {},
+   "source": [
+    "### Model Setup\n",
+    "\n",
+    "Setup models that will be used for downstream orchestration."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16e2071d-bbc2-4707-8ae7-cb4e1fecafd3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import Settings\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "\n",
+    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")\n",
+    "llm = OpenAI(model=\"gpt-4o\")\n",
+    "\n",
+    "Settings.embed_model = embed_model\n",
+    "Settings.llm = llm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3f6416f-f580-4722-aaa9-7f3500408547",
+   "metadata": {},
+   "source": [
+    "## Use LlamaParse to Parse Text and Images\n",
+    "\n",
+    "In this example, use LlamaParse to parse both the text and images from the document.\n",
+    "\n",
+    "We parse out the text in two ways: \n",
+    "- in regular `text` mode using our default text layout algorithm\n",
+    "- in `markdown` mode using GPT-4o (`gpt4o_mode=True`). This also allows us to capture page screenshots"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "570089e5-238a-4dcc-af65-96e7393c2b4d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "\n",
+    "parser_text = LlamaParse(result_type=\"text\")\n",
+    "parser_gpt4o = LlamaParse(result_type=\"markdown\", gpt4o_mode=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ef82a985-4088-4bb7-9a21-0318e1b9207d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Parsing text...\n",
+      "Started parsing the file under job_id 62f157a9-9ef9-4e5b-95ac-67093fa25800\n",
+      "..........Parsing PDF file...\n",
+      "Started parsing the file under job_id 1ddd5654-062b-4e19-b488-d66efc9c509d\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(f\"Parsing text...\")\n",
+    "docs_text = parser_text.load_data(\"data/conocophillips.pdf\")\n",
+    "print(f\"Parsing PDF file...\")\n",
+    "md_json_objs = parser_gpt4o.get_json_result(\"data/conocophillips.pdf\")\n",
+    "md_json_list = md_json_objs[0][\"pages\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5318fb7b-fe6a-4a8a-b82e-4ed7b4512c37",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Commitment to Disciplined Reinvestment Rate\n",
+      "\n",
+      "| Period       | Description                          | Reinvestment Rate | WTI Average |\n",
+      "|--------------|--------------------------------------|-------------------|-------------|\n",
+      "| 2012-2016    | Industry Growth Focus                | >100%             | ~$75/BBL    |\n",
+      "| 2017-2022    | ConocoPhillips Strategy Reset        | <60%              | ~$63/BBL    |\n",
+      "| 2023E        |                                      |                   | at $80/BBL  |\n",
+      "| 2024-2028    | Disciplined Reinvestment Rate        | ~50%              | at $60/BBL  |\n",
+      "| 2029-2032    |                                      | ~6% CFO CAGR      | at $60/BBL  |\n",
+      "\n",
+      "- **Historic Reinvestment Rate**: Gray bars\n",
+      "- **Reinvestment Rate at $60/BBL WTI**: Blue bars\n",
+      "- **Reinvestment Rate at $80/BBL WTI**: Dashed blue lines\n",
+      "\n",
+      "Reinvestment rate and cash from operations (CFO) are non-GAAP measures. Definitions and reconciliations are included in the Appendix.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(md_json_list[10][\"md\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eeadb16c-97eb-4622-9551-b34d7f90d72f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "image_dicts = parser_gpt4o.get_images(md_json_objs, download_path=\"data_images\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fd3e098b-0606-4429-b48d-d4fe0140fc0e",
+   "metadata": {},
+   "source": [
+    "## Build Multimodal Index\n",
+    "\n",
+    "In this section we build the multimodal index over the parsed deck. \n",
+    "\n",
+    "We do this by creating **text** nodes from the document that contain metadata referencing the original image path.\n",
+    "\n",
+    "In this example we're indexing the text node for retrieval. The text node has a reference to both the parsed text as well as the image screenshot."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3aae2dee-9d85-4604-8a51-705d4db527f7",
+   "metadata": {},
+   "source": [
+    "#### Get Text Nodes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "18c24174-05ce-417f-8dd2-79c3f375db03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.schema import TextNode\n",
+    "from typing import Optional"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e331dfe-a627-4e23-8c57-70ab1d9342e4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get pages loaded through llamaparse\n",
+    "import re\n",
+    "\n",
+    "\n",
+    "def get_page_number(file_name):\n",
+    "    match = re.search(r\"-page-(\\d+)\\.jpg$\", str(file_name))\n",
+    "    if match:\n",
+    "        return int(match.group(1))\n",
+    "    return 0\n",
+    "\n",
+    "\n",
+    "def _get_sorted_image_files(image_dir):\n",
+    "    \"\"\"Get image files sorted by page.\"\"\"\n",
+    "    raw_files = [f for f in list(Path(image_dir).iterdir()) if f.is_file()]\n",
+    "    sorted_files = sorted(raw_files, key=get_page_number)\n",
+    "    return sorted_files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "346fe5ef-171e-4a54-9084-7a7805103a13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from copy import deepcopy\n",
+    "from pathlib import Path\n",
+    "\n",
+    "\n",
+    "# attach image metadata to the text nodes\n",
+    "def get_text_nodes(docs, image_dir=None, json_dicts=None):\n",
+    "    \"\"\"Split docs into nodes, by separator.\"\"\"\n",
+    "    nodes = []\n",
+    "\n",
+    "    image_files = _get_sorted_image_files(image_dir) if image_dir is not None else None\n",
+    "    md_texts = [d[\"md\"] for d in json_dicts] if json_dicts is not None else None\n",
+    "\n",
+    "    doc_chunks = [c for d in docs for c in d.text.split(\"---\")]\n",
+    "    for idx, doc_chunk in enumerate(doc_chunks):\n",
+    "        chunk_metadata = {\"page_num\": idx + 1}\n",
+    "        if image_files is not None:\n",
+    "            image_file = image_files[idx]\n",
+    "            chunk_metadata[\"image_path\"] = str(image_file)\n",
+    "        if md_texts is not None:\n",
+    "            chunk_metadata[\"parsed_text_markdown\"] = md_texts[idx]\n",
+    "        chunk_metadata[\"parsed_text\"] = doc_chunk\n",
+    "        node = TextNode(\n",
+    "            text=\"\",\n",
+    "            metadata=chunk_metadata,\n",
+    "        )\n",
+    "        nodes.append(node)\n",
+    "\n",
+    "    return nodes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f591669c-5a8e-491d-9cef-0b754abbf26f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# this will split into pages\n",
+    "text_nodes = get_text_nodes(docs_text, image_dir=\"data_images\", json_dicts=md_json_list)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "32c13950-c1db-435f-b5b4-89d62b8b7744",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page_num: 11\n",
+      "image_path: data_images/1ddd5654-062b-4e19-b488-d66efc9c509d-page_39.jpg\n",
+      "parsed_text_markdown: # Commitment to Disciplined Reinvestment Rate\n",
+      "\n",
+      "| Period       | Description                          | Reinvestment Rate | WTI Average |\n",
+      "|--------------|--------------------------------------|-------------------|-------------|\n",
+      "| 2012-2016    | Industry Growth Focus                | >100%             | ~$75/BBL    |\n",
+      "| 2017-2022    | ConocoPhillips Strategy Reset        | <60%              | ~$63/BBL    |\n",
+      "| 2023E        |                                      |                   | at $80/BBL  |\n",
+      "| 2024-2028    | Disciplined Reinvestment Rate        | ~50%              | at $60/BBL  |\n",
+      "| 2029-2032    |                                      | ~6% CFO CAGR      | at $60/BBL  |\n",
+      "\n",
+      "- **Historic Reinvestment Rate**: Gray bars\n",
+      "- **Reinvestment Rate at $60/BBL WTI**: Blue bars\n",
+      "- **Reinvestment Rate at $80/BBL WTI**: Dashed blue lines\n",
+      "\n",
+      "Reinvestment rate and cash from operations (CFO) are non-GAAP measures. Definitions and reconciliations are included in the Appendix.\n",
+      "parsed_text: Commitment to Disciplined Reinvestment Rate\n",
+      "                         Industry                    ConocoPhillips\n",
+      "                                                     Strategy Reset                   Disciplined Reinvestment Rate is the Foundation for Superior\n",
+      "                      Growth Focus                                                    Returns on and of Capital, while Driving Durable CFO Growth\n",
+      "                             100%                           <60%                                        50%                 6%         at $60/BBL WTI\n",
+      "                       Reinvestment Rate               Reinvestment Rate                          Reinvestment Rate10-YearCFO CAGR          Planning PriceMid-Cycle\n",
+      "                                                                                                                         2024-2032\n",
+      "    2   100%\n",
+      "    1    75%\n",
+      "    1    50%\n",
+      "    1                                                                                                                                         WTIat $80/BBL                at S80/BBL\n",
+      "         25%                'S75/BBL                        $63/BBL                                                                                                        WTI\n",
+      "                              WTI                             WTI                         at S80/BBL                       at S60/BBL                      at S60/BBL\n",
+      "                           Average                         Average                            WTI                              WTI                             WTI\n",
+      "          0%\n",
+      "                          2012-2016                        2017-2022                         2023E                          2024-2028                       2029-2032\n",
+      "                                    Historic Reinvestment Rate            Reinvestment Rate at $60/BBL WTI                 Reinvestment Rate at $80/BBL WTI\n",
+      " Reinvestment rate and cash from operations (CFO) are non-GAAP measures: Definitions and reconciliations are included in the Appendix                                  ConocoPhillips\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(text_nodes[10].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f404f56-db1e-4ed7-9ba1-ead763546348",
+   "metadata": {},
+   "source": [
+    "#### Build Index\n",
+    "\n",
+    "Once the text nodes are ready, we feed into our vector store index abstraction, which will index these nodes into a simple in-memory vector store (of course, you should definitely check out our 40+ vector store integrations!)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6ea53c31-0e38-421c-8d9b-0e3adaa1677e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/jerryliu/Programming/gpt_index/.venv/lib/python3.10/site-packages/tiktoken/core.py:50: RuntimeWarning: coroutine 'LlamaParse.aload_data' was never awaited\n",
+      "  self._core_bpe = _tiktoken.CoreBPE(mergeable_ranks, special_tokens, pat_str)\n",
+      "RuntimeWarning: Enable tracemalloc to get the object allocation traceback\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from llama_index.core import (\n",
+    "    StorageContext,\n",
+    "    VectorStoreIndex,\n",
+    "    load_index_from_storage,\n",
+    ")\n",
+    "\n",
+    "if not os.path.exists(\"storage_nodes\"):\n",
+    "    index = VectorStoreIndex(text_nodes, embed_model=embed_model)\n",
+    "    # save index to disk\n",
+    "    index.set_index_id(\"vector_index\")\n",
+    "    index.storage_context.persist(\"./storage_nodes\")\n",
+    "else:\n",
+    "    # rebuild storage context\n",
+    "    storage_context = StorageContext.from_defaults(persist_dir=\"storage_nodes\")\n",
+    "    # load index\n",
+    "    index = load_index_from_storage(storage_context, index_id=\"vector_index\")\n",
+    "\n",
+    "retriever = index.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5f0e33a4-9422-498d-87ee-d917bdf74d80",
+   "metadata": {},
+   "source": [
+    "## Build Multimodal Query Engine\n",
+    "\n",
+    "We now use LlamaIndex abstractions to build a **custom query engine**. In contrast to a standard RAG query engine that will retrieve the text node and only put that into the prompt (response synthesis module), this custom query engine will also load the image document, and put both the text and image document into the response synthesis module."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "35a94be2-e289-41a6-92e4-d3cb428fb0c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.query_engine import CustomQueryEngine, SimpleMultiModalQueryEngine\n",
+    "from llama_index.core.retrievers import BaseRetriever\n",
+    "from llama_index.multi_modal_llms.openai import OpenAIMultiModal\n",
+    "from llama_index.core.schema import ImageNode, NodeWithScore, MetadataMode\n",
+    "from llama_index.core.prompts import PromptTemplate\n",
+    "from llama_index.core.base.response.schema import Response\n",
+    "from typing import Optional\n",
+    "\n",
+    "\n",
+    "gpt_4o = OpenAIMultiModal(model=\"gpt-4o\", max_new_tokens=4096)\n",
+    "\n",
+    "QA_PROMPT_TMPL = \"\"\"\\\n",
+    "Below we give parsed text from slides in two different formats, as well as the image.\n",
+    "\n",
+    "We parse the text in both 'markdown' mode as well as 'raw text' mode. Markdown mode attempts \\\n",
+    "to convert relevant diagrams into tables, whereas raw text tries to maintain the rough spatial \\\n",
+    "layout of the text.\n",
+    "\n",
+    "Use the image information first and foremost. ONLY use the text/markdown information \n",
+    "if you can't understand the image.\n",
+    "\n",
+    "---------------------\n",
+    "{context_str}\n",
+    "---------------------\n",
+    "Given the context information and not prior knowledge, answer the query. Explain whether you got the answer\n",
+    "from the parsed markdown or raw text or image, and if there's discrepancies, and your reasoning for the final answer.\n",
+    "\n",
+    "Query: {query_str}\n",
+    "Answer: \"\"\"\n",
+    "\n",
+    "QA_PROMPT = PromptTemplate(QA_PROMPT_TMPL)\n",
+    "\n",
+    "\n",
+    "class MultimodalQueryEngine(CustomQueryEngine):\n",
+    "    \"\"\"Custom multimodal Query Engine.\n",
+    "\n",
+    "    Takes in a retriever to retrieve a set of document nodes.\n",
+    "    Also takes in a prompt template and multimodal model.\n",
+    "\n",
+    "    \"\"\"\n",
+    "\n",
+    "    qa_prompt: PromptTemplate\n",
+    "    retriever: BaseRetriever\n",
+    "    multi_modal_llm: OpenAIMultiModal\n",
+    "\n",
+    "    def __init__(self, qa_prompt: Optional[PromptTemplate] = None, **kwargs) -> None:\n",
+    "        \"\"\"Initialize.\"\"\"\n",
+    "        super().__init__(qa_prompt=qa_prompt or QA_PROMPT, **kwargs)\n",
+    "\n",
+    "    def custom_query(self, query_str: str):\n",
+    "        # retrieve text nodes\n",
+    "        nodes = self.retriever.retrieve(query_str)\n",
+    "        # create ImageNode items from text nodes\n",
+    "        image_nodes = [\n",
+    "            NodeWithScore(node=ImageNode(image_path=n.metadata[\"image_path\"]))\n",
+    "            for n in nodes\n",
+    "        ]\n",
+    "\n",
+    "        # create context string from text nodes, dump into the prompt\n",
+    "        context_str = \"\\n\\n\".join(\n",
+    "            [r.get_content(metadata_mode=MetadataMode.LLM) for r in nodes]\n",
+    "        )\n",
+    "        fmt_prompt = self.qa_prompt.format(context_str=context_str, query_str=query_str)\n",
+    "\n",
+    "        # synthesize an answer from formatted text and images\n",
+    "        llm_response = self.multi_modal_llm.complete(\n",
+    "            prompt=fmt_prompt,\n",
+    "            image_documents=[image_node.node for image_node in image_nodes],\n",
+    "        )\n",
+    "        return Response(\n",
+    "            response=str(llm_response),\n",
+    "            source_nodes=nodes,\n",
+    "            metadata={\"text_nodes\": text_nodes, \"image_nodes\": image_nodes},\n",
+    "        )\n",
+    "\n",
+    "        return response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0890be59-fb12-4bb5-959b-b2d9600f7774",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = MultimodalQueryEngine(\n",
+    "    retriever=index.as_retriever(similarity_top_k=9), multi_modal_llm=gpt_4o\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a92aa4f1-7501-4711-b054-f02338e54e74",
+   "metadata": {},
+   "source": [
+    "### Define Baseline\n",
+    "\n",
+    "In addition, we define a \"baseline\" where we rely only on text-based indexing. Here we define an index using only the nodes that are parsed in text-mode from LlamaParse. \n",
+    "\n",
+    "**NOTE**: We don't currently include the markdown-parsed text because that was parsed with GPT-4o, so already uses a multimodal model during the text extraction phase.\n",
+    "\n",
+    "It is of course a valid experiment to compare RAG where multimodal extraction only happens during indexing, vs. the current multimodal RAG implementation where images are fed during synthesis to the LLM. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0b15a48-d177-4666-aec2-98ee90664642",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_nodes(docs):\n",
+    "    \"\"\"Split docs into nodes, by separator.\"\"\"\n",
+    "    nodes = []\n",
+    "    for doc in docs:\n",
+    "        doc_chunks = doc.text.split(\"\\n---\\n\")\n",
+    "        for doc_chunk in doc_chunks:\n",
+    "            node = TextNode(\n",
+    "                text=doc_chunk,\n",
+    "                metadata=deepcopy(doc.metadata),\n",
+    "            )\n",
+    "            nodes.append(node)\n",
+    "\n",
+    "    return nodes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2065d2c6-d6ba-4ee3-8e9e-dbc83cbcec1b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_nodes = get_nodes(docs_text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bcaea1a8-26c9-4385-8f62-32855aa898b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Our Differentiated Portfolio: Deep; Durable and Diverse\n",
+      "                              20 BBOE of Resource                                           Diverse Production Base\n",
+      "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
+      "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
+      "                    Average Cost of Supply\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
+      "                                                                                                                      GPA     WNS\n",
+      "      $30                                                                                                             EMENA\n",
+      "  3                                                                                                                              Norway\n",
+      "  8   $20\n",
+      "  E                                                                                                                   Qatar      Libya\n",
+      "                                                                                                                      Asia Pacific Canada\n",
+      "      $10                                                                          Permian\n",
+      "                                                                                                                      APLNG        Montney\n",
+      "       S0\n",
+      "                                               10              15              20                         Bakken\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
+      "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
+      "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
+      "                                                                                                                                           ConocoPhillips\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_nodes[13].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f6bcfbc6-4e9b-41ad-ad81-1c4245b95cd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "base_index = VectorStoreIndex(base_nodes, embed_model=embed_model)\n",
+    "base_query_engine = base_index.as_query_engine(llm=llm, similarity_top_k=9)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1f94ef26-0df5-4468-a156-903d686f02ce",
+   "metadata": {},
+   "source": [
+    "## Build a Multimodal Agent\n",
+    "\n",
+    "Build an agent around the multimodal query engine. This gives you agent capabilities like query planning/decomposition and memory around a central QA interface."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b7a8c5f-39fc-4d04-8c56-3642f5718437",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.tools import QueryEngineTool\n",
+    "from llama_index.core.agent import FunctionCallingAgentWorker\n",
+    "\n",
+    "\n",
+    "vector_tool = QueryEngineTool.from_defaults(\n",
+    "    query_engine=query_engine,\n",
+    "    name=\"vector_tool\",\n",
+    "    description=(\n",
+    "        \"Useful for retrieving specific context from the data. Do NOT select if question asks for a summary of the data.\"\n",
+    "    ),\n",
+    ")\n",
+    "agent = FunctionCallingAgentWorker.from_tools(\n",
+    "    [vector_tool], llm=llm, verbose=True\n",
+    ").as_agent()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2b4f7eb1-d247-45fa-bb41-c02fc353a22a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# define a similar agent for the baseline\n",
+    "base_vector_tool = QueryEngineTool.from_defaults(\n",
+    "    query_engine=base_query_engine,\n",
+    "    name=\"vector_tool\",\n",
+    "    description=(\n",
+    "        \"Useful for retrieving specific context from the data. Do NOT select if question asks for a summary of the data.\"\n",
+    "    ),\n",
+    ")\n",
+    "base_agent = FunctionCallingAgentWorker.from_tools(\n",
+    "    [base_vector_tool], llm=llm, verbose=True\n",
+    ").as_agent()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2336f98b-c0a1-413a-849d-8a89bacb90b5",
+   "metadata": {},
+   "source": [
+    "## Try out Queries\n",
+    "\n",
+    "Let's try out queries against these documents and compare against each other."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d78e53cf-35cb-4ef8-b03e-1b47ba15ae64",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added user message to memory: Tell me about the diverse geographies where Conoco Phillips has a production base\n",
+      "=== Calling Function ===\n",
+      "Calling function: vector_tool with args: {\"input\": \"Conoco Phillips production base geographies\"}\n",
+      "=== Function Output ===\n",
+      "ConocoPhillips' production base geographies include:\n",
+      "\n",
+      "1. **Lower 48** (Permian, Eagle Ford, Bakken, Other)\n",
+      "2. **Alaska** (GKA, GWA, GPA, WNS)\n",
+      "3. **EMENA** (Norway, Libya, Qatar)\n",
+      "4. **Asia Pacific** (APLNG, Malaysia, China)\n",
+      "5. **Canada** (Montney, Surmont)\n",
+      "\n",
+      "This information was derived from the image on page 14, which provides a detailed breakdown of the diverse production base and the regions involved. The parsed markdown and raw text also support this information, but the image provides the clearest and most comprehensive view. There are no discrepancies between the image and the parsed text in this case.\n",
+      "=== LLM Response ===\n",
+      "ConocoPhillips has a diverse production base spread across various geographies, including:\n",
+      "\n",
+      "1. **Lower 48**:\n",
+      "   - Permian Basin\n",
+      "   - Eagle Ford\n",
+      "   - Bakken\n",
+      "   - Other regions within the continental United States\n",
+      "\n",
+      "2. **Alaska**:\n",
+      "   - Greater Kuparuk Area (GKA)\n",
+      "   - Greater Prudhoe Area (GPA)\n",
+      "   - Greater Willow Area (GWA)\n",
+      "   - Western North Slope (WNS)\n",
+      "\n",
+      "3. **EMENA (Europe, Middle East, and North Africa)**:\n",
+      "   - Norway\n",
+      "   - Libya\n",
+      "   - Qatar\n",
+      "\n",
+      "4. **Asia Pacific**:\n",
+      "   - Australia Pacific LNG (APLNG)\n",
+      "   - Malaysia\n",
+      "   - China\n",
+      "\n",
+      "5. **Canada**:\n",
+      "   - Montney\n",
+      "   - Surmont\n",
+      "\n",
+      "These regions highlight the global reach and diverse geographical footprint of ConocoPhillips' production operations.\n",
+      "Added user message to memory: Tell me about the diverse geographies where Conoco Phillips has a production base\n",
+      "=== Calling Function ===\n",
+      "Calling function: vector_tool with args: {\"input\": \"diverse geographies where Conoco Phillips has a production base\"}\n",
+      "=== Function Output ===\n",
+      "ConocoPhillips has a diverse production base that includes the Lower 48 (Permian, Bakken, Eagle Ford), Alaska, Canada (Montney, Surmont), EMENA (Norway, Libya), Asia Pacific (Malaysia, China, APLNG), and Qatar.\n",
+      "=== LLM Response ===\n",
+      "ConocoPhillips has a diverse production base spanning several key geographies:\n",
+      "\n",
+      "1. **Lower 48 (United States)**: This includes major production areas such as the Permian Basin, Bakken Formation, and Eagle Ford Shale.\n",
+      "2. **Alaska**: Significant operations in the North Slope region.\n",
+      "3. **Canada**: Operations in the Montney Formation and the Surmont oil sands project.\n",
+      "4. **EMENA (Europe, Middle East, and North Africa)**: Notable operations in Norway and Libya.\n",
+      "5. **Asia Pacific**: Includes operations in Malaysia, China, and the Australia Pacific LNG (APLNG) project.\n",
+      "6. **Qatar**: Involvement in the country's energy sector.\n",
+      "\n",
+      "These regions highlight the company's extensive and varied geographical footprint in the energy production industry.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = (\n",
+    "    \"Tell me about the diverse geographies where Conoco Phillips has a production base\"\n",
+    ")\n",
+    "response = agent.query(query)\n",
+    "base_response = base_agent.query(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "355d2aa4-c26f-480e-b512-4446acbd9227",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ConocoPhillips has a diverse production base spread across various geographies, including:\n",
+      "\n",
+      "1. **Lower 48**:\n",
+      "   - Permian Basin\n",
+      "   - Eagle Ford\n",
+      "   - Bakken\n",
+      "   - Other regions within the continental United States\n",
+      "\n",
+      "2. **Alaska**:\n",
+      "   - Greater Kuparuk Area (GKA)\n",
+      "   - Greater Prudhoe Area (GPA)\n",
+      "   - Greater Willow Area (GWA)\n",
+      "   - Western North Slope (WNS)\n",
+      "\n",
+      "3. **EMENA (Europe, Middle East, and North Africa)**:\n",
+      "   - Norway\n",
+      "   - Libya\n",
+      "   - Qatar\n",
+      "\n",
+      "4. **Asia Pacific**:\n",
+      "   - Australia Pacific LNG (APLNG)\n",
+      "   - Malaysia\n",
+      "   - China\n",
+      "\n",
+      "5. **Canada**:\n",
+      "   - Montney\n",
+      "   - Surmont\n",
+      "\n",
+      "These regions highlight the global reach and diverse geographical footprint of ConocoPhillips' production operations.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d584c560-8f49-4c10-a4db-2e0d3b7085d2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page_num: 14\n",
+      "image_path: data_images/1ddd5654-062b-4e19-b488-d66efc9c509d-page_12.jpg\n",
+      "parsed_text_markdown: # Our Differentiated Portfolio: Deep, Durable and Diverse\n",
+      "\n",
+      "## ~20 BBOE of Resource\n",
+      "Under $40/BBL Cost of Supply\n",
+      "\n",
+      "### ~ $32/BBL\n",
+      "Average Cost of Supply\n",
+      "\n",
+      "### WTI Cost of Supply ($/BBL)\n",
+      "\n",
+      "| Cost ($/BBL) | Resource (BBOE) |\n",
+      "|--------------|-----------------|\n",
+      "| $0           | 0               |\n",
+      "| $10          |                 |\n",
+      "| $20          |                 |\n",
+      "| $30          |                 |\n",
+      "| $40          |                 |\n",
+      "| $50          |                 |\n",
+      "\n",
+      "- **Legend:**\n",
+      "  - Lower 48\n",
+      "  - Canada\n",
+      "  - Alaska\n",
+      "  - EMENA\n",
+      "  - Asia Pacific\n",
+      "\n",
+      "*Costs assume a mid-cycle price environment of $60/BBL WTI.*\n",
+      "\n",
+      "## Diverse Production Base\n",
+      "10-Year Plan Cumulative Production (BBOE)\n",
+      "\n",
+      "| Region       | Sub-region      |\n",
+      "|--------------|-----------------|\n",
+      "| Lower 48     | Permian         |\n",
+      "|              | Eagle Ford      |\n",
+      "|              | Bakken          |\n",
+      "|              | Other           |\n",
+      "| Alaska       | GKA             |\n",
+      "|              | GWA             |\n",
+      "|              | GPA             |\n",
+      "|              | WNS             |\n",
+      "| EMENA        | Norway          |\n",
+      "|              | Libya           |\n",
+      "|              | Qatar           |\n",
+      "| Asia Pacific | APLNG           |\n",
+      "|              | Malaysia        |\n",
+      "|              | China           |\n",
+      "| Canada       | Montney         |\n",
+      "|              | Surmont         |\n",
+      "parsed_text: Our Differentiated Portfolio: Deep; Durable and Diverse\n",
+      "                              20 BBOE of Resource                                           Diverse Production Base\n",
+      "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
+      "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
+      "                    Average Cost of Supply\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
+      "                                                                                                                      GPA     WNS\n",
+      "      $30                                                                                                             EMENA\n",
+      "  3                                                                                                                              Norway\n",
+      "  8   $20\n",
+      "  E                                                                                                                   Qatar      Libya\n",
+      "                                                                                                                      Asia Pacific Canada\n",
+      "      $10                                                                          Permian\n",
+      "                                                                                                                      APLNG        Montney\n",
+      "       S0\n",
+      "                                               10              15              20                         Bakken\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
+      "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
+      "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
+      "                                                                                                                                           ConocoPhillips\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response.source_nodes[7].get_content(metadata_mode=\"all\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d21d694b-6618-4d04-a6f6-8b0c2625f539",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ConocoPhillips has a diverse production base spanning several key geographies:\n",
+      "\n",
+      "1. **Lower 48 (United States)**: This includes major production areas such as the Permian Basin, Bakken Formation, and Eagle Ford Shale.\n",
+      "2. **Alaska**: Significant operations in the North Slope region.\n",
+      "3. **Canada**: Operations in the Montney Formation and the Surmont oil sands project.\n",
+      "4. **EMENA (Europe, Middle East, and North Africa)**: Notable operations in Norway and Libya.\n",
+      "5. **Asia Pacific**: Includes operations in Malaysia, China, and the Australia Pacific LNG (APLNG) project.\n",
+      "6. **Qatar**: Involvement in the country's energy sector.\n",
+      "\n",
+      "These regions highlight the company's extensive and varied geographical footprint in the energy production industry.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(base_response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d3afccae-ad8d-4c5d-9d93-810dba413a5d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Our Differentiated Portfolio: Deep; Durable and Diverse\n",
+      "                              20 BBOE of Resource                                           Diverse Production Base\n",
+      "                            Under $40/BBL Cost of Supply                              10-Year Plan Cumulative Production (BBOE)\n",
+      "      S50                   S32/BBL                                                Lower 48                           Alaska\n",
+      "                    Average Cost of Supply\n",
+      "  3 $40                                                                                                                       GKA        GWA\n",
+      "                                                                                                                      GPA     WNS\n",
+      "      $30                                                                                                             EMENA\n",
+      "  3                                                                                                                              Norway\n",
+      "  8   $20\n",
+      "  E                                                                                                                   Qatar      Libya\n",
+      "                                                                                                                      Asia Pacific Canada\n",
+      "      $10                                                                          Permian\n",
+      "                                                                                                                      APLNG        Montney\n",
+      "       S0\n",
+      "                                               10              15              20                         Bakken\n",
+      "                                         Resource (BBOE)                           Eagle Ford             Other       Malaysia ChinaSurmont\n",
+      "                 Lower 48      Canada       Alaska      EMENA    Asia Pacific\n",
+      "Costs assumemid-cycle price environment of S60/BBL WTI:\n",
+      "                                                                                                                                           ConocoPhillips\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(base_response.source_nodes[1].get_content(metadata_mode=\"all\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_index_v3",
+   "language": "python",
+   "name": "llama_index_v3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

examples/multimodal/product_manual_rag.ipynb

@@ -0,0 +1,834 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Building a RAG Pipeline over IKEA Product Instruction Manuals\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/multimodal/product_manual_rag.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This cookbook shows how to use LlamaParse and OpenAI's multimodal models to query over IKEA instruction manual PDFs, which mainly contain images and diagrams to show how one can assemble the product.\n",
+    "\n",
+    "LlamaParse and multimodal LLMs can interpret these diagrams and translate them into textual instructions. With textual assistance, confusing visual instructions within the IKEA product manuals can be made easier to understand and interpret. Additionally, textual instructions can be helpful for those who are visually impaired."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Install and Setup\n",
+    "\n",
+    "Install LlamaIndex, download the data, and apply `nest_asyncio`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index llama-parse llama-index-multi-modal-llms-openai git+https://github.com/openai/CLIP.git"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!wget https://github.com/user-attachments/files/16461058/data.zip -O data.zip\n",
+    "!unzip -o data.zip\n",
+    "!rm data.zip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up your OpenAI and LlamaCloud keys."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"<Your OpenAI API Key>\"\n",
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<Your LlamaCloud API Key>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Code Implementation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Set up LlamaParse. We will parse the PDF files into markdown and use the GPT-4o multimodal model to parse the PDFs."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Load data from the parser."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    parsing_instruction=\"You are given IKEA assembly instruction manuals\",\n",
+    "    use_vendor_multimodal_model=True,\n",
+    "    vendor_multimodal_model_name=\"openai-gpt4o\",\n",
+    "    show_progress=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DATA_DIR = \"data\"\n",
+    "\n",
+    "\n",
+    "def get_data_files(data_dir=DATA_DIR) -> list[str]:\n",
+    "    files = []\n",
+    "    for f in os.listdir(data_dir):\n",
+    "        fname = os.path.join(data_dir, f)\n",
+    "        if os.path.isfile(fname):\n",
+    "            files.append(fname)\n",
+    "    return files\n",
+    "\n",
+    "\n",
+    "files = get_data_files()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Load data into docs, and save images from PDFs into `data_images` directory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "md_json_objs = parser.get_json_result(files)\n",
+    "md_json_list = md_json_objs[0][\"pages\"]\n",
+    "image_dicts = parser.get_images(md_json_objs, download_path=\"data_images\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create helper functions to create a list of `TextNode`s from the markdown tables to feed into the `VectorStoreIndex`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "from pathlib import Path\n",
+    "import typing as t\n",
+    "from llama_index.core.schema import TextNode\n",
+    "\n",
+    "\n",
+    "def get_page_number(file_name):\n",
+    "    \"\"\"Gets page number of images using regex on file names\"\"\"\n",
+    "    match = re.search(r\"-page-(\\d+)\\.jpg$\", str(file_name))\n",
+    "    if match:\n",
+    "        return int(match.group(1))\n",
+    "    return 0\n",
+    "\n",
+    "\n",
+    "def _get_sorted_image_files(image_dir):\n",
+    "    \"\"\"Get image files sorted by page.\"\"\"\n",
+    "    raw_files = [f for f in list(Path(image_dir).iterdir()) if f.is_file()]\n",
+    "    sorted_files = sorted(raw_files, key=get_page_number)\n",
+    "    return sorted_files\n",
+    "\n",
+    "\n",
+    "def get_text_nodes(json_dicts, image_dir) -> t.List[TextNode]:\n",
+    "    \"\"\"Creates nodes from json + images\"\"\"\n",
+    "\n",
+    "    nodes = []\n",
+    "\n",
+    "    docs = [doc[\"md\"] for doc in json_dicts]  # extract text\n",
+    "    image_files = _get_sorted_image_files(image_dir)  # extract images\n",
+    "\n",
+    "    for idx, doc in enumerate(docs):\n",
+    "        # adds both a text node and the corresponding image node (jpg of the page) for each page\n",
+    "        node = TextNode(\n",
+    "            text=doc,\n",
+    "            metadata={\"image_path\": str(image_files[idx]), \"page_num\": idx + 1},\n",
+    "        )\n",
+    "        nodes.append(node)\n",
+    "\n",
+    "    return nodes\n",
+    "\n",
+    "\n",
+    "text_nodes = get_text_nodes(md_json_list, \"data_images\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Index the documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import (\n",
+    "    VectorStoreIndex,\n",
+    "    StorageContext,\n",
+    "    load_index_from_storage,\n",
+    "    Settings,\n",
+    ")\n",
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "\n",
+    "embed_model = OpenAIEmbedding(model=\"text-embedding-3-large\")\n",
+    "llm = OpenAI(\"gpt-4o\")\n",
+    "\n",
+    "Settings.llm = llm\n",
+    "Settings.embed_model = embed_model\n",
+    "\n",
+    "if not os.path.exists(\"storage_ikea\"):\n",
+    "    index = VectorStoreIndex(text_nodes, embed_model=embed_model)\n",
+    "    index.storage_context.persist(persist_dir=\"./storage_ikea\")\n",
+    "else:\n",
+    "    ctx = StorageContext.from_defaults(persist_dir=\"./storage_ikea\")\n",
+    "    index = load_index_from_storage(ctx)\n",
+    "\n",
+    "retriever = index.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a custom query engine that uses GPT-4o's multimodal model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.query_engine import CustomQueryEngine\n",
+    "from llama_index.core.retrievers import BaseRetriever\n",
+    "from llama_index.multi_modal_llms.openai import OpenAIMultiModal\n",
+    "from llama_index.core.schema import NodeWithScore, MetadataMode\n",
+    "from llama_index.core.base.response.schema import Response\n",
+    "from llama_index.core.prompts import PromptTemplate\n",
+    "from llama_index.core.schema import ImageNode\n",
+    "\n",
+    "QA_PROMPT_TMPL = \"\"\"\\\n",
+    "Below we give parsed text from slides in two different formats, as well as the image.\n",
+    "\n",
+    "We parse the text in both 'markdown' mode as well as 'raw text' mode. Markdown mode attempts \\\n",
+    "to convert relevant diagrams into tables, whereas raw text tries to maintain the rough spatial \\\n",
+    "layout of the text.\n",
+    "\n",
+    "Use the image information first and foremost. ONLY use the text/markdown information \n",
+    "if you can't understand the image.\n",
+    "\n",
+    "---------------------\n",
+    "{context_str}\n",
+    "---------------------\n",
+    "Given the context information and not prior knowledge, answer the query. Explain whether you got the answer\n",
+    "from the parsed markdown or raw text or image, and if there's discrepancies, and your reasoning for the final answer.\n",
+    "\n",
+    "Query: {query_str}\n",
+    "Answer: \"\"\"\n",
+    "\n",
+    "QA_PROMPT = PromptTemplate(QA_PROMPT_TMPL)\n",
+    "\n",
+    "gpt_4o_mm = OpenAIMultiModal(model=\"gpt-4o\", max_new_tokens=4096)\n",
+    "\n",
+    "\n",
+    "class MultimodalQueryEngine(CustomQueryEngine):\n",
+    "    qa_prompt: PromptTemplate\n",
+    "    retriever: BaseRetriever\n",
+    "    multi_modal_llm: OpenAIMultiModal\n",
+    "\n",
+    "    def __init__(\n",
+    "        self,\n",
+    "        qa_prompt: PromptTemplate,\n",
+    "        retriever: BaseRetriever,\n",
+    "        multi_modal_llm: OpenAIMultiModal,\n",
+    "    ):\n",
+    "        super().__init__(\n",
+    "            qa_prompt=qa_prompt, retriever=retriever, multi_modal_llm=multi_modal_llm\n",
+    "        )\n",
+    "\n",
+    "    def custom_query(self, query_str: str):\n",
+    "        # retrieve most relevant nodes\n",
+    "        nodes = self.retriever.retrieve(query_str)\n",
+    "\n",
+    "        # create image nodes from the image associated with those nodes\n",
+    "        image_nodes = [\n",
+    "            NodeWithScore(node=ImageNode(image_path=n.node.metadata[\"image_path\"]))\n",
+    "            for n in nodes\n",
+    "        ]\n",
+    "\n",
+    "        # create context string from parsed markdown text\n",
+    "        ctx_str = \"\\n\\n\".join(\n",
+    "            [r.node.get_content(metadata_mode=MetadataMode.LLM) for r in nodes]\n",
+    "        )\n",
+    "        # prompt for the LLM\n",
+    "        fmt_prompt = self.qa_prompt.format(context_str=ctx_str, query_str=query_str)\n",
+    "\n",
+    "        # use the multimodal LLM to interpret images and generate a response to the prompt\n",
+    "        llm_repsonse = self.multi_modal_llm.complete(\n",
+    "            prompt=fmt_prompt,\n",
+    "            image_documents=[image_node.node for image_node in image_nodes],\n",
+    "        )\n",
+    "        return Response(\n",
+    "            response=str(llm_repsonse),\n",
+    "            source_nodes=nodes,\n",
+    "            metadata={\"text_nodes\": text_nodes, \"image_nodes\": image_nodes},\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Create a query engine instance."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = MultimodalQueryEngine(\n",
+    "    qa_prompt=QA_PROMPT,\n",
+    "    retriever=index.as_retriever(similarity_top_k=9),\n",
+    "    multi_modal_llm=gpt_4o_mm,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "## Example Queries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The query asks about the parts included in the Uppspel, but the provided images and parsed text do not contain any information about the Uppspel. Instead, they contain information about other IKEA products such as SMÅGÖRA, FREDDE, and TUFFING.\n",
+       "\n",
+       "Therefore, based on the provided images and parsed text, I cannot determine the parts included in the Uppspel. The answer cannot be derived from the given information."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import display, Markdown\n",
+    "\n",
+    "response = query_engine.query(\"What parts are included in the Uppspel?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The Tuffing is a bunk bed frame with a minimalist design, featuring a metal frame and safety rails on the top bunk. The image provided shows the Tuffing bunk bed with a ladder for access to the top bunk and a simple, sturdy construction.\n",
+       "\n",
+       "I got the answer from the image provided. The image clearly shows the design and structure of the Tuffing bunk bed. There were no discrepancies between the parsed markdown or raw text and the image. The image was the primary source for understanding what the Tuffing looks like."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"What does the Tuffing look like?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "The query asks for step 4 of assembling the Nordli. Based on the provided information, step 4 is described in the parsed text as follows:\n",
+       "\n",
+       "**Step 4:**\n",
+       "- Insert the provided tool into the hole as shown.\n",
+       "- Ensure the structure is properly aligned and secure.\n",
+       "- Push down firmly to lock the structure in place.\n",
+       "\n",
+       "This information was derived from the parsed text, as the image provided does not contain step-by-step instructions for the Nordli assembly. There are no discrepancies between the parsed markdown and raw text for this step."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"What is step 4 of assembling the Nordli?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "If you're confused with reading the manual, you should contact IKEA customer service for assistance. This information is derived from the image on page 2, which shows a person with a question mark next to an IKEA box and another person making a phone call to IKEA. This visual cue indicates that contacting IKEA customer service is the recommended action if you need help."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What should I do if I'm confused with reading the manual?\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also create an agent around the query engine and chat with the agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.agent import FunctionCallingAgentWorker\n",
+    "from llama_index.core.tools import QueryEngineTool\n",
+    "\n",
+    "query_engine_tool = QueryEngineTool.from_defaults(\n",
+    "    query_engine=query_engine,\n",
+    "    name=\"query_engine_tool\",\n",
+    "    description=\"Useful for retrieving specific context from the data. Do NOT select if question asks for a summary of the data.\",\n",
+    ")\n",
+    "agent = FunctionCallingAgentWorker.from_tools(\n",
+    "    [query_engine_tool], llm=llm, verbose=True\n",
+    ").as_agent()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added user message to memory: Give a step-by-step instruction guide on how to assemble the Smagora\n",
+      "=== Calling Function ===\n",
+      "Calling function: query_engine_tool with args: {\"input\": \"step-by-step instruction guide on how to assemble the Smagora\"}\n",
+      "=== Function Output ===\n",
+      "The step-by-step instruction guide on how to assemble the Smågåra crib is provided in the images. The images show detailed visual instructions for each step of the assembly process, including the tools required, the parts involved, and the specific actions to be taken.\n",
+      "\n",
+      "Here is a summary of the steps based on the images:\n",
+      "\n",
+      "1. **Tools Required**:\n",
+      "   - Flathead screwdriver\n",
+      "   - Phillips screwdriver\n",
+      "   - Hammer\n",
+      "\n",
+      "2. **Preparation**:\n",
+      "   - Do not assemble alone; assemble with a partner.\n",
+      "   - Do not assemble on a hard surface; use a soft surface to avoid damage.\n",
+      "   - If you have questions or need assistance, contact IKEA customer service.\n",
+      "\n",
+      "3. **Step 1**:\n",
+      "   - Insert 12 screws into the designated holes on the frame.\n",
+      "\n",
+      "4. **Step 2**:\n",
+      "   - Align the side panels with the headboard and footboard.\n",
+      "   - Use 4 connectors and secure them with bolts and washers.\n",
+      "   - Tighten using the provided tool.\n",
+      "   - Carefully flip the structure as shown.\n",
+      "\n",
+      "5. **Step 3**:\n",
+      "   - Use the provided Allen key to tighten the screws into the designated holes.\n",
+      "   - Ensure the screws are properly aligned and tightened.\n",
+      "   - Repeat this process for all four screws.\n",
+      "   - Make sure the screws are flush with the surface.\n",
+      "\n",
+      "6. **Step 4**:\n",
+      "   - Insert the provided tool into the hole as shown.\n",
+      "   - Ensure the structure is properly aligned and secure.\n",
+      "   - Push down firmly to lock the structure in place.\n",
+      "\n",
+      "7. **Step 5**:\n",
+      "   - Insert 4 dowels into the designated holes on the board.\n",
+      "\n",
+      "8. **Step 6**:\n",
+      "   - Align the board with the dowels and insert it into the corresponding slots on the frame.\n",
+      "\n",
+      "9. **Step 7**:\n",
+      "   - Insert the top panel into the side panels.\n",
+      "   - Use 4 screws to secure the top panel.\n",
+      "   - Ensure the screws are properly aligned and tightened using the provided tool.\n",
+      "\n",
+      "10. **Step 8**:\n",
+      "    - Carefully flip the assembled structure upright.\n",
+      "    - Use 2 screws to secure the bottom panel.\n",
+      "    - Tighten the screws with the provided tool.\n",
+      "\n",
+      "These steps are derived from the images provided, which offer a clear and detailed visual guide for assembling the Smågåra crib.\n",
+      "=== LLM Response ===\n",
+      "Here is a step-by-step instruction guide on how to assemble the Smågåra crib:\n",
+      "\n",
+      "### Tools Required:\n",
+      "- Flathead screwdriver\n",
+      "- Phillips screwdriver\n",
+      "- Hammer\n",
+      "- Allen key (provided in the package)\n",
+      "\n",
+      "### Preparation:\n",
+      "- **Safety First**: Assemble with a partner to ensure safety and ease.\n",
+      "- **Surface**: Assemble on a soft surface to avoid damaging the parts.\n",
+      "- **Assistance**: If you have questions or need help, contact IKEA customer service.\n",
+      "\n",
+      "### Step-by-Step Assembly:\n",
+      "\n",
+      "#### Step 1: Insert Screws into the Frame\n",
+      "1. Insert 12 screws into the designated holes on the frame.\n",
+      "2. Ensure the screws are properly aligned.\n",
+      "\n",
+      "#### Step 2: Align and Secure Side Panels\n",
+      "1. Align the side panels with the headboard and footboard.\n",
+      "2. Use 4 connectors and secure them with bolts and washers.\n",
+      "3. Tighten the bolts using the provided tool.\n",
+      "4. Carefully flip the structure as shown in the instructions.\n",
+      "\n",
+      "#### Step 3: Tighten Screws\n",
+      "1. Use the provided Allen key to tighten the screws into the designated holes.\n",
+      "2. Ensure the screws are properly aligned and tightened.\n",
+      "3. Repeat this process for all four screws.\n",
+      "4. Make sure the screws are flush with the surface.\n",
+      "\n",
+      "#### Step 4: Lock the Structure\n",
+      "1. Insert the provided tool into the hole as shown.\n",
+      "2. Ensure the structure is properly aligned and secure.\n",
+      "3. Push down firmly to lock the structure in place.\n",
+      "\n",
+      "#### Step 5: Insert Dowels\n",
+      "1. Insert 4 dowels into the designated holes on the board.\n",
+      "\n",
+      "#### Step 6: Align and Insert the Board\n",
+      "1. Align the board with the dowels.\n",
+      "2. Insert the board into the corresponding slots on the frame.\n",
+      "\n",
+      "#### Step 7: Secure the Top Panel\n",
+      "1. Insert the top panel into the side panels.\n",
+      "2. Use 4 screws to secure the top panel.\n",
+      "3. Ensure the screws are properly aligned and tightened using the provided tool.\n",
+      "\n",
+      "#### Step 8: Secure the Bottom Panel\n",
+      "1. Carefully flip the assembled structure upright.\n",
+      "2. Use 2 screws to secure the bottom panel.\n",
+      "3. Tighten the screws with the provided tool.\n",
+      "\n",
+      "By following these steps, you should be able to assemble the Smågåra crib successfully. If you encounter any issues, refer to the visual instructions provided in the package or contact IKEA customer service for assistance.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/markdown": [
+       "Here is a step-by-step instruction guide on how to assemble the Smågåra crib:\n",
+       "\n",
+       "### Tools Required:\n",
+       "- Flathead screwdriver\n",
+       "- Phillips screwdriver\n",
+       "- Hammer\n",
+       "- Allen key (provided in the package)\n",
+       "\n",
+       "### Preparation:\n",
+       "- **Safety First**: Assemble with a partner to ensure safety and ease.\n",
+       "- **Surface**: Assemble on a soft surface to avoid damaging the parts.\n",
+       "- **Assistance**: If you have questions or need help, contact IKEA customer service.\n",
+       "\n",
+       "### Step-by-Step Assembly:\n",
+       "\n",
+       "#### Step 1: Insert Screws into the Frame\n",
+       "1. Insert 12 screws into the designated holes on the frame.\n",
+       "2. Ensure the screws are properly aligned.\n",
+       "\n",
+       "#### Step 2: Align and Secure Side Panels\n",
+       "1. Align the side panels with the headboard and footboard.\n",
+       "2. Use 4 connectors and secure them with bolts and washers.\n",
+       "3. Tighten the bolts using the provided tool.\n",
+       "4. Carefully flip the structure as shown in the instructions.\n",
+       "\n",
+       "#### Step 3: Tighten Screws\n",
+       "1. Use the provided Allen key to tighten the screws into the designated holes.\n",
+       "2. Ensure the screws are properly aligned and tightened.\n",
+       "3. Repeat this process for all four screws.\n",
+       "4. Make sure the screws are flush with the surface.\n",
+       "\n",
+       "#### Step 4: Lock the Structure\n",
+       "1. Insert the provided tool into the hole as shown.\n",
+       "2. Ensure the structure is properly aligned and secure.\n",
+       "3. Push down firmly to lock the structure in place.\n",
+       "\n",
+       "#### Step 5: Insert Dowels\n",
+       "1. Insert 4 dowels into the designated holes on the board.\n",
+       "\n",
+       "#### Step 6: Align and Insert the Board\n",
+       "1. Align the board with the dowels.\n",
+       "2. Insert the board into the corresponding slots on the frame.\n",
+       "\n",
+       "#### Step 7: Secure the Top Panel\n",
+       "1. Insert the top panel into the side panels.\n",
+       "2. Use 4 screws to secure the top panel.\n",
+       "3. Ensure the screws are properly aligned and tightened using the provided tool.\n",
+       "\n",
+       "#### Step 8: Secure the Bottom Panel\n",
+       "1. Carefully flip the assembled structure upright.\n",
+       "2. Use 2 screws to secure the bottom panel.\n",
+       "3. Tighten the screws with the provided tool.\n",
+       "\n",
+       "By following these steps, you should be able to assemble the Smågåra crib successfully. If you encounter any issues, refer to the visual instructions provided in the package or contact IKEA customer service for assistance."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = agent.chat(\n",
+    "    \"Give a step-by-step instruction guide on how to assemble the Smagora\"\n",
+    ")\n",
+    "display(Markdown(str(response)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Added user message to memory: How do I assemble the Fredde?\n",
+      "=== Calling Function ===\n",
+      "Calling function: query_engine_tool with args: {\"input\": \"step-by-step instruction guide on how to assemble the Fredde\"}\n",
+      "=== Function Output ===\n",
+      "The query asks for a step-by-step instruction guide on how to assemble the Fredde. However, based on the provided images and parsed text, there is no specific mention or visual representation of the Fredde assembly instructions. The images and text provided are related to other IKEA products such as Tuffing and Smågöra, but not Fredde.\n",
+      "\n",
+      "Therefore, I cannot provide the step-by-step instructions for assembling the Fredde from the given information. If you have the specific instructions for Fredde, please provide them, and I can assist you further.\n",
+      "=== LLM Response ===\n",
+      "It appears that the specific step-by-step instructions for assembling the Fredde desk are not available in the provided data. However, I can offer a general guide based on typical assembly procedures for IKEA furniture. For the most accurate and detailed instructions, please refer to the assembly manual that comes with the product.\n",
+      "\n",
+      "### General Assembly Guide for Fredde Desk:\n",
+      "\n",
+      "#### Tools Required:\n",
+      "- Phillips screwdriver\n",
+      "- Flathead screwdriver\n",
+      "- Allen key (usually provided in the package)\n",
+      "- Hammer (if needed for dowels)\n",
+      "\n",
+      "### Step-by-Step Assembly:\n",
+      "\n",
+      "#### Step 1: Unpack and Organize\n",
+      "1. **Unpack** all the parts and hardware.\n",
+      "2. **Organize** the parts by type and size to make the assembly process easier.\n",
+      "\n",
+      "#### Step 2: Assemble the Main Frame\n",
+      "1. **Connect the Side Panels**: Attach the side panels to the back panel using screws and dowels as indicated in the manual.\n",
+      "2. **Secure the Bottom Panel**: Attach the bottom panel to the side panels.\n",
+      "\n",
+      "#### Step 3: Attach the Shelves\n",
+      "1. **Install the Lower Shelves**: Insert the lower shelves into the designated slots and secure them with screws.\n",
+      "2. **Install the Upper Shelves**: Repeat the process for the upper shelves.\n",
+      "\n",
+      "#### Step 4: Attach the Desktop\n",
+      "1. **Align the Desktop**: Place the desktop on top of the frame, ensuring it is properly aligned.\n",
+      "2. **Secure the Desktop**: Use screws to secure the desktop to the frame.\n",
+      "\n",
+      "#### Step 5: Install Additional Features\n",
+      "1. **Attach Monitor Shelf**: If the Fredde desk includes a monitor shelf, attach it to the back panel using screws.\n",
+      "2. **Install Side Extensions**: Attach any side extensions or additional shelves as per the instructions.\n",
+      "\n",
+      "#### Step 6: Final Adjustments\n",
+      "1. **Check Stability**: Ensure all screws are tightened and the desk is stable.\n",
+      "2. **Adjust Height**: If the desk has adjustable height features, set it to the desired height.\n",
+      "\n",
+      "#### Step 7: Clean Up\n",
+      "1. **Remove Packaging**: Dispose of any packaging materials.\n",
+      "2. **Organize Tools**: Put away your tools and clean the workspace.\n",
+      "\n",
+      "For the most accurate and detailed instructions, please refer to the assembly manual that comes with the Fredde desk. If you encounter any issues, IKEA customer service can provide additional support.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/markdown": [
+       "It appears that the specific step-by-step instructions for assembling the Fredde desk are not available in the provided data. However, I can offer a general guide based on typical assembly procedures for IKEA furniture. For the most accurate and detailed instructions, please refer to the assembly manual that comes with the product.\n",
+       "\n",
+       "### General Assembly Guide for Fredde Desk:\n",
+       "\n",
+       "#### Tools Required:\n",
+       "- Phillips screwdriver\n",
+       "- Flathead screwdriver\n",
+       "- Allen key (usually provided in the package)\n",
+       "- Hammer (if needed for dowels)\n",
+       "\n",
+       "### Step-by-Step Assembly:\n",
+       "\n",
+       "#### Step 1: Unpack and Organize\n",
+       "1. **Unpack** all the parts and hardware.\n",
+       "2. **Organize** the parts by type and size to make the assembly process easier.\n",
+       "\n",
+       "#### Step 2: Assemble the Main Frame\n",
+       "1. **Connect the Side Panels**: Attach the side panels to the back panel using screws and dowels as indicated in the manual.\n",
+       "2. **Secure the Bottom Panel**: Attach the bottom panel to the side panels.\n",
+       "\n",
+       "#### Step 3: Attach the Shelves\n",
+       "1. **Install the Lower Shelves**: Insert the lower shelves into the designated slots and secure them with screws.\n",
+       "2. **Install the Upper Shelves**: Repeat the process for the upper shelves.\n",
+       "\n",
+       "#### Step 4: Attach the Desktop\n",
+       "1. **Align the Desktop**: Place the desktop on top of the frame, ensuring it is properly aligned.\n",
+       "2. **Secure the Desktop**: Use screws to secure the desktop to the frame.\n",
+       "\n",
+       "#### Step 5: Install Additional Features\n",
+       "1. **Attach Monitor Shelf**: If the Fredde desk includes a monitor shelf, attach it to the back panel using screws.\n",
+       "2. **Install Side Extensions**: Attach any side extensions or additional shelves as per the instructions.\n",
+       "\n",
+       "#### Step 6: Final Adjustments\n",
+       "1. **Check Stability**: Ensure all screws are tightened and the desk is stable.\n",
+       "2. **Adjust Height**: If the desk has adjustable height features, set it to the desired height.\n",
+       "\n",
+       "#### Step 7: Clean Up\n",
+       "1. **Remove Packaging**: Dispose of any packaging materials.\n",
+       "2. **Organize Tools**: Put away your tools and clean the workspace.\n",
+       "\n",
+       "For the most accurate and detailed instructions, please refer to the assembly manual that comes with the Fredde desk. If you encounter any issues, IKEA customer service can provide additional support."
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "response = agent.chat(\"How do I assemble the Fredde?\")\n",
+    "display(Markdown(str(response)))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama-parse-5ZmnAQ0r-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

examples/test_tesla_impact_report/test_gpt4o.ipynb

@@ -0,0 +1,359 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f20600ce-d57a-446e-b033-3aadeec39c1b",
+   "metadata": {},
+   "source": [
+    "# LlamaParse with GPT-4o\n",
+    "\n",
+    "\n",
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/test_tesla_impact_report/test_gpt4o.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
+    "\n",
+    "GPT-4o is a [fully multimodal model by OpenAI](https://openai.com/index/hello-gpt-4o/) released in May 2024. It matches GPT-4 Turbo performance in text and code, and has significantly improved vision and audio capabilities.\n",
+    "\n",
+    "The expanded vision/audio capabilities mean that it can be used for document parsing, by treating each page as an image and performing document extraction. We support using GPT-4o natively in LlamaParse for document parsing. The notebook below walks you through an example of using GPT-4o over the Tesla impact report.\n",
+    "\n",
+    "**NOTE**: The pricing for LlamaParse + gpt4o is an order more expensive than using LlamaParse by default. Currently, every page parsed with gpt4o counts for 10 pages in the LlamaParse usage tracker.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86b173ac-9fce-4813-bdf1-6dd7d93a491d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ecc5eba5-96ce-4db7-bba1-f9ece33e681c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b805592b-d1a5-4cd2-b916-348f66ca7941",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<LLAMA_CLOUD_API_KEY>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6e73e3c4-9e09-4cba-805f-326c82be812d",
+   "metadata": {},
+   "source": [
+    "### Use LlamaParse with `gpt4o_mode=True`\n",
+    "\n",
+    "By turning on gpt4o, we use GPT-4o multimodal capabilities to do document parsing per page instead of the LlamaParse default pipeline.\n",
+    "\n",
+    "We load a snippet of the [2019 Tesla impact report](https://www.tesla.com/ns_videos/2019-tesla-impact-report.pdf). **NOTE**: The report is 57 pages, but will count for 570 pages in LlamaParse due to GPT-4o usage (which is approximately $1.71 USD).\n",
+    "\n",
+    "You can optionally choose to provide a `gpt4o_api_key`. If you do this, then we will use your API key to make GPT-4o calls, and your LlamaParse usage will be counted as if `gpt4o_mode` was not turned on (each page will be counted as a page instead of 10 pages). "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaa2ec5d-f27c-4262-80bf-e57daacff182",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-05-21 00:10:32--  https://www.dropbox.com/scl/fi/vu6w1dsfo5eddydz13ssm/2019-tesla-impact-report-15.pdf?rlkey=ik8lfqbg2p1ervss4qqt3xose&st=70j04z8j&dl=1\n",
+      "Resolving www.dropbox.com (www.dropbox.com)... 2620:100:6057:18::a27d:d12, 162.125.13.18\n",
+      "Connecting to www.dropbox.com (www.dropbox.com)|2620:100:6057:18::a27d:d12|:443... connected.\n",
+      "HTTP request sent, awaiting response... 302 Found\n",
+      "Location: https://uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com/cd/0/inline/CTTnZs8U4V1GtUCNxoB7INwmLq2yU97Q6QbWS6uVnb_XdHe368GrqF0zLDEKTnpc-x7utwNUUpMvWjLyrujrqNVrbGKTKa6hwHu5BxYPA2zXYrzdAEZyeve274xpHZKFywQ/file?dl=1# [following]\n",
+      "--2024-05-21 00:10:33--  https://uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com/cd/0/inline/CTTnZs8U4V1GtUCNxoB7INwmLq2yU97Q6QbWS6uVnb_XdHe368GrqF0zLDEKTnpc-x7utwNUUpMvWjLyrujrqNVrbGKTKa6hwHu5BxYPA2zXYrzdAEZyeve274xpHZKFywQ/file?dl=1\n",
+      "Resolving uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com (uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com)... 2620:100:6057:15::a27d:d0f, 162.125.13.15\n",
+      "Connecting to uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com (uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com)|2620:100:6057:15::a27d:d0f|:443... connected.\n",
+      "HTTP request sent, awaiting response... 302 Found\n",
+      "Location: /cd/0/inline2/CTSaARDHbxvyEEgefshmsHLbuXkgV1Rmr-ItVhk5lPuZXkLlNnZMZWCF9YF5j4t2lLs4VurFW2VI1Q4A6ZFi8D2RXJmUG3wdgJhR6qSaBpwRZxjB_vk8qkJb8h1jRDaL7ATK6XYTHncab_aoPWzB62vrZ9yXUM0Mr-EdCX1k-hMbzXLV2dorA71IuFPY8ICkTemRWaG6VhBd3bV0C5AkMsAqy90w6Kez1ySFO06UkrxLSmkCaKdFgVoLcUVO2PLv4rGv6AuZOF_kqwsHdh82J9DQU4PMMyg-f5ChSGGSCKgmUfTBE2qP1eISP-GXSB91yWwMf-7rxGtM8MpDp-AL5jxYZxhZcmZn1cU8Or_8OOZrxg/file?dl=1 [following]\n",
+      "--2024-05-21 00:10:33--  https://uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com/cd/0/inline2/CTSaARDHbxvyEEgefshmsHLbuXkgV1Rmr-ItVhk5lPuZXkLlNnZMZWCF9YF5j4t2lLs4VurFW2VI1Q4A6ZFi8D2RXJmUG3wdgJhR6qSaBpwRZxjB_vk8qkJb8h1jRDaL7ATK6XYTHncab_aoPWzB62vrZ9yXUM0Mr-EdCX1k-hMbzXLV2dorA71IuFPY8ICkTemRWaG6VhBd3bV0C5AkMsAqy90w6Kez1ySFO06UkrxLSmkCaKdFgVoLcUVO2PLv4rGv6AuZOF_kqwsHdh82J9DQU4PMMyg-f5ChSGGSCKgmUfTBE2qP1eISP-GXSB91yWwMf-7rxGtM8MpDp-AL5jxYZxhZcmZn1cU8Or_8OOZrxg/file?dl=1\n",
+      "Reusing existing connection to [uc872df1ff4ea2fecd3d024fa97a.dl.dropboxusercontent.com]:443.\n",
+      "HTTP request sent, awaiting response... 200 OK\n",
+      "Length: 26199694 (25M) [application/binary]\n",
+      "Saving to: ‘2019-tesla-impact-report-15.pdf’\n",
+      "\n",
+      "2019-tesla-impact-r 100%[===================>]  24.99M  30.5MB/s    in 0.8s    \n",
+      "\n",
+      "2024-05-21 00:10:35 (30.5 MB/s) - ‘2019-tesla-impact-report-15.pdf’ saved [26199694/26199694]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget \"https://www.dropbox.com/scl/fi/vu6w1dsfo5eddydz13ssm/2019-tesla-impact-report-15.pdf?rlkey=ik8lfqbg2p1ervss4qqt3xose&st=70j04z8j&dl=1\" -O \"2019-tesla-impact-report-15.pdf\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f46991c1-031b-461f-b9a6-9237a821f4c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_parse import LlamaParse\n",
+    "\n",
+    "parser_gpt4o = LlamaParse(\n",
+    "    result_type=\"markdown\",\n",
+    "    # api_key=api_key,\n",
+    "    gpt4o_mode=True,\n",
+    "    split_by_page=True,\n",
+    "    # gpt4o_api_key=\"<gpt4o_api_key>\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1136ba82-074b-489d-9b0a-d609ccbf02b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Started parsing the file under job_id bf7d4619-3e26-479d-80e9-25702186ef32\n",
+      "."
+     ]
+    }
+   ],
+   "source": [
+    "documents_gpt4o = parser_gpt4o.load_data(\"./2019-tesla-impact-report-15.pdf\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e65c54f-3e4c-4c78-b1e8-a55ebeba1f24",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Mission & Tesla Ecosystem\n",
+      "\n",
+      "Climate change is reaching alarming levels in large part due to emissions from burning fossil fuels for transportation and electricity generation. In 2016, carbon dioxide (CO2) concentration levels in the atmosphere exceeded the 400 parts per million threshold on a sustained basis - a level that climate scientists believe will have a catastrophic impact on the environment. Worse, annual global CO2 emissions continue to increase and have approximately doubled over the past 50 years to over 43 gigatons in 2019. The world’s current path is unwise and unsustainable.\n",
+      "\n",
+      "The world cannot reduce CO2 emissions without addressing both energy generation and consumption. And the world cannot address its energy habits without first directly reducing emissions in the transportation and energy sectors. We are focused on creating a complete energy and transportation ecosystem from solar generation and energy storage to all-electric vehicles that produce zero tailpipe emissions.\n",
+      "\n",
+      "Since the onset of shelter-in-place orders and travel restrictions due to COVID-19, we have seen dramatic increases in air quality across the planet, as well as projections for CO2 emissions to drop in excess of 4% in 2020 compared to pre-COVID-19 levels, according to researchers. Because these improvements in air quality and reductions in CO2 are a result of a global economic disruption and not due to systemic changes in how we produce and consume energy, they are not expected to be sustained absent intervention. However, these changes have shown us the positive impacts of reduced pollution in a very short period of time. At Tesla, we believe that we all have an unprecedented opportunity to learn from this disruption and accelerate the deployment of clean energy solutions as part of a recovery for all economies throughout the world, and we will actively continue to advocate for the realization of these long-term changes.\n",
+      "\n",
+      "| Global Greenhouse Gas (GHG) Emissions by Economic Sector |\n",
+      "|----------------------------------------------------------|\n",
+      "| ![Pie Chart](image_url)                                  |\n",
+      "\n",
+      "| Sector                                      | Percentage |\n",
+      "|---------------------------------------------|------------|\n",
+      "| Electricity & Heat Production*              | 31%        |\n",
+      "| Agriculture, Forestry & Other Land Use      | 20%        |\n",
+      "| Industry                                    | 18%        |\n",
+      "| Transportation*                             | 16%        |\n",
+      "| Other Energy                                | 9%         |\n",
+      "| Buildings                                   | 6%         |\n",
+      "\n",
+      "*Tesla-related sectors. Source: World Resources Institute\n",
+      "\n",
+      "According to the Global Carbon project, when fully tallied, total carbon emissions from 2019 are expected to hit another record high of over 43 gigatons for the year. Energy use through electricity and heat production (31%) and transportation (16%) are significant drivers of these GHG emissions.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(documents_gpt4o[3].get_content())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d62cbb62-37ea-4370-9411-d979aa3a627e",
+   "metadata": {},
+   "source": [
+    "## Build RAG pipeline over the Parsed Report\n",
+    "\n",
+    "We now try building a RAG pipeline over this parsed report. It's not a lot of text, but we split it into chunks and load it into a simple in-memory vector store.\n",
+    "\n",
+    "We ask a question over the parsed markdown table and get back the right answer! We also ask a question over the text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d8b7c3ad-2147-448c-bcbe-3e6fcd8d5361",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core import VectorStoreIndex\n",
+    "\n",
+    "vector_index = VectorStoreIndex(documents_gpt4o)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8013351a-180d-4947-9f81-513042175c19",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = vector_index.as_query_engine(similarity_top_k=6)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "795dc5c4-e122-4ff3-94d2-747fa51d5add",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"What are the greenhouse emissions for agriculture and transportation?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39d2e6bd-3316-49b5-9a5d-5b4b95343e5a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Agriculture accounts for 20% of global greenhouse gas emissions, while transportation contributes 16% of these emissions.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9beb5cd4-4041-48c7-b22b-de5540f92a6d",
+   "metadata": {},
+   "source": [
+    "Let's also try asking a question over another piece of the text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "543c8b63-5cd1-47a1-a8a1-81abbfd3e52b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"How does the EPA range of Teslas compare with other vehicles? Give details\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e739eabf-732b-4f59-9628-972c4bf6c857",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The EPA range of Tesla vehicles varies across different models. The Model 3 Standard Range Plus (SR+) achieves an EPA range of 4.8 miles/kWh, making it the most efficient electric vehicle in production. The Model Y all-wheel drive (AWD) achieves 4.1 miles/kWh, which positions it as the most efficient electric SUV produced to date. The energy efficiency of Tesla vehicles is highlighted by these EPA range figures, showcasing their advancements in powertrain efficiency compared to other electric vehicles on the market.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "04b05c53-1a81-41a7-97f2-98a960211957",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Reducing Carbon Footprint Even Further\n",
+      "## Improving Powertrain Efficiency\n",
+      "\n",
+      "Tesla vehicles are known to have the highest energy efficiency of any EV built to date. In the early days of Model S production, we were able to achieve energy efficiency of 3.1 EPA miles / kWh. Today, our most efficient Model 3 Standard Range Plus (SR+) achieves an EPA range of 4.8 miles / kWh, more than any EV in production. Model Y all-wheel drive (AWD) achieves 4.1 EPA miles / kWh, which makes it the most efficient electric SUV produced to date.\n",
+      "\n",
+      "The energy efficiency of Tesla vehicles will continue to improve further over time as we continue to improve our technology and powertrain efficiency. It is also reasonable to assume that our high-mileage products, such as our future Tesla Robotaxis, will be designed for maximum energy efficiency as handling, acceleration, and top speed become less relevant. That way, we will minimize cost for our customers as well as reduce the carbon footprint per mile driven.\n",
+      "\n",
+      "### Average Lifecycle Emissions in U.S. (gCO2e/mi)\n",
+      "\n",
+      "| Vehicle Type                          | Manufacturing Phase | Use Phase | Total Emissions |\n",
+      "|---------------------------------------|---------------------|-----------|-----------------|\n",
+      "| Avg. Mid-Size Premium ICE             |                     |           |                 |\n",
+      "| Model 3 Personal Use (grid charged)   |                     |           |                 |\n",
+      "| Model 3 Ridesharing Use (grid charged)|                     |           |                 |\n",
+      "| Model 3 Personal Use (solar charged)  |                     |           |                 |\n",
+      "| Model 3 Ridesharing Use (solar charged)|                    |           |                 |\n",
+      "\n",
+      "*Note: The chart shows that the emissions depend on powertrain efficiency.*\n",
+      "\n",
+      "### Energy Efficiency EPA range in miles/kWh\n",
+      "\n",
+      "| Vehicle Model       | EPA Range (miles/kWh) |\n",
+      "|---------------------|-----------------------|\n",
+      "| Model 3 SR+         | 4.8                   |\n",
+      "| Model 3 AWD         |                       |\n",
+      "| Model Y AWD         |                       |\n",
+      "| Hyundai Kona        |                       |\n",
+      "| Chevy Bolt          |                       |\n",
+      "| Model S LR+         |                       |\n",
+      "| Nissan Leaf         |                       |\n",
+      "| Model X LR+         |                       |\n",
+      "| Jaguar iPace        |                       |\n",
+      "| Mercedes EQC*       |                       |\n",
+      "| Ford Mach E AWD     |                       |\n",
+      "| Audi e-tron         |                       |\n",
+      "| Porsche Taycan      |                       |\n",
+      "\n",
+      "*Tesla estimate. Source: OEM websites*\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(response.source_nodes[0].get_content())"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_parse",
+   "language": "python",
+   "name": "llama_parse"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

llama_parse/base.py

@@ -1,15 +1,22 @@
 import os
 import asyncio
+from io import TextIOWrapper
+
 import httpx
 import mimetypes
 import time
-from pathlib import Path
-from typing import List, Optional, Union
+from pathlib import Path, PurePath, PurePosixPath
+from typing import AsyncGenerator, Any, Dict, List, Optional, Union
+from contextlib import asynccontextmanager
+from io import BufferedIOBase
 
-from llama_index.core.async_utils import run_jobs
-from llama_index.core.bridge.pydantic import Field, validator
+from fsspec import AbstractFileSystem
+from fsspec.spec import AbstractBufferedFile
+from llama_index.core.async_utils import asyncio_run, run_jobs
+from llama_index.core.bridge.pydantic import Field, field_validator
 from llama_index.core.constants import DEFAULT_BASE_URL
 from llama_index.core.readers.base import BasePydanticReader
+from llama_index.core.readers.file.base import get_default_fs
 from llama_index.core.schema import Document
 from llama_parse.utils import (
     nest_asyncio_err,
@@ -18,12 +25,23 @@ from llama_parse.utils import (
     Language,
     SUPPORTED_FILE_TYPES,
 )
+from copy import deepcopy
+
+# can put in a path to the file or the file bytes itself
+# if passing as bytes or a buffer, must provide the file_name in extra_info
+FileInput = Union[str, bytes, BufferedIOBase]
+
+_DEFAULT_SEPARATOR = "\n---\n"
 
 
 class LlamaParse(BasePydanticReader):
     """A smart-parser for files."""
 
-    api_key: str = Field(default="", description="The API key for the LlamaParse API.")
+    api_key: str = Field(
+        default="",
+        description="The API key for the LlamaParse API.",
+        validate_default=True,
+    )
     base_url: str = Field(
         default=DEFAULT_BASE_URL,
         description="The base URL of the Llama Parsing API.",
@@ -57,6 +75,46 @@ class LlamaParse(BasePydanticReader):
     parsing_instruction: Optional[str] = Field(
         default="", description="The parsing instruction for the parser."
     )
+    skip_diagonal_text: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
+    )
+    invalidate_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice.",
+    )
+    do_not_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the document will not be cached. This mean that you will be re-charged it you reprocess them as they will not be cached.",
+    )
+    fast_mode: Optional[bool] = Field(
+        default=False,
+        description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
+    )
+    premium_mode: bool = Field(
+        default=False,
+        description="Use our best parser mode if set to True.",
+    )
+    continuous_mode: bool = Field(
+        default=False,
+        description="Parse documents continuously, leading to better results on documents where tables span across two pages.",
+    )
+    do_not_unroll_columns: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.",
+    )
+    page_separator: Optional[str] = Field(
+        default=None,
+        description="A templated  page separator to use to split the text.  If it contain `{page_number}`,it will be replaced by the next page number. If not set will the default separator '\\n---\\n' will be used.",
+    )
+    page_prefix: Optional[str] = Field(
+        default=None,
+        description="A templated prefix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
+    )
+    page_suffix: Optional[str] = Field(
+        default=None,
+        description="A templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
+    )
     gpt4o_mode: bool = Field(
         default=False,
         description="Whether to use gpt-4o extract text from documents.",
@@ -65,12 +123,76 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="The API key for the GPT-4o API. Lowers the cost of parsing.",
     )
+    guess_xlsx_sheet_names: Optional[bool] = Field(
+        default=False,
+        description="Whether to guess the sheet names of the xlsx file.",
+    )
+    bounding_box: Optional[str] = Field(
+        default=None,
+        description="The bounding box to use to extract text from documents describe as a string containing the bounding box margins",
+    )
+    target_pages: Optional[str] = Field(
+        default=None,
+        description="The target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0",
+    )
     ignore_errors: bool = Field(
         default=True,
         description="Whether or not to ignore and skip errors raised during parsing.",
     )
+    split_by_page: bool = Field(
+        default=True,
+        description="Whether to split by page using the page separator",
+    )
+    vendor_multimodal_api_key: Optional[str] = Field(
+        default=None,
+        description="The API key for the multimodal API.",
+    )
+    use_vendor_multimodal_model: bool = Field(
+        default=False,
+        description="Whether to use the vendor multimodal API.",
+    )
+    vendor_multimodal_model_name: Optional[str] = Field(
+        default=None,
+        description="The model name for the vendor multimodal API.",
+    )
+    take_screenshot: bool = Field(
+        default=False,
+        description="Whether to take screenshot of each page of the document.",
+    )
+    custom_client: Optional[httpx.AsyncClient] = Field(
+        default=None, description="A custom HTTPX client to use for sending requests."
+    )
+    disable_ocr: bool = Field(
+        default=False,
+        description="Disable the OCR on the document. LlamaParse will only extract the copyable text from the document.",
+    )
+    is_formatting_instruction: bool = Field(
+        default=True,
+        description="Allow the parsing instruction to also format the output. Disable to have a cleaner markdown output.",
+    )
+    annotate_links: bool = Field(
+        default=False,
+        description="Annotate links found in the document to extract their URL.",
+    )
+    webhook_url: Optional[str] = Field(
+        default=None,
+        description="A URL that needs to be called at the end of the parsing job.",
+    )
+    azure_openai_deployment_name: Optional[str] = Field(
+        default=None, description="Azure Openai Deployment Name"
+    )
+    azure_openai_endpoint: Optional[str] = Field(
+        default=None, description="Azure Openai Endpoint"
+    )
+    azure_openai_api_version: Optional[str] = Field(
+        default=None, description="Azure Openai API Version"
+    )
+    azure_openai_key: Optional[str] = Field(
+        default=None, description="Azure Openai Key"
+    )
 
-    @validator("api_key", pre=True, always=True)
+    @field_validator("api_key", mode="before", check_fields=True)
+    @classmethod
     def validate_api_key(cls, v: str) -> str:
         """Validate the API key."""
         if not v:
@@ -83,58 +205,142 @@ class LlamaParse(BasePydanticReader):
 
         return v
 
-    @validator("base_url", pre=True, always=True)
+    @field_validator("base_url", mode="before", check_fields=True)
+    @classmethod
     def validate_base_url(cls, v: str) -> str:
         """Validate the base URL."""
         url = os.getenv("LLAMA_CLOUD_BASE_URL", None)
         return url or v or DEFAULT_BASE_URL
 
+    @asynccontextmanager
+    async def client_context(self) -> AsyncGenerator[httpx.AsyncClient, None]:
+        """Create a context for the HTTPX client."""
+        if self.custom_client is not None:
+            yield self.custom_client
+        else:
+            async with httpx.AsyncClient(timeout=self.max_timeout) as client:
+                yield client
+
     # upload a document and get back a job_id
     async def _create_job(
-        self, file_path: str, extra_info: Optional[dict] = None
+        self,
+        file_input: FileInput,
+        extra_info: Optional[dict] = None,
+        fs: Optional[AbstractFileSystem] = None,
     ) -> str:
-        file_path = str(file_path)
-        file_ext = os.path.splitext(file_path)[1]
-        if file_ext not in SUPPORTED_FILE_TYPES:
-            raise Exception(
-                f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
-                f"Current file type: {file_ext}"
+        headers = {"Authorization": f"Bearer {self.api_key}"}
+        url = f"{self.base_url}/api/parsing/upload"
+        files = None
+        file_handle = None
+
+        if isinstance(file_input, (bytes, BufferedIOBase)):
+            if not extra_info or "file_name" not in extra_info:
+                raise ValueError(
+                    "file_name must be provided in extra_info when passing bytes"
+                )
+            file_name = extra_info["file_name"]
+            mime_type = mimetypes.guess_type(file_name)[0]
+            files = {"file": (file_name, file_input, mime_type)}
+        elif isinstance(file_input, (str, Path, PurePosixPath, PurePath)):
+            file_path = str(file_input)
+            file_ext = os.path.splitext(file_path)[1].lower()
+            if file_ext not in SUPPORTED_FILE_TYPES:
+                raise Exception(
+                    f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
+                    f"Current file type: {file_ext}"
+                )
+            mime_type = mimetypes.guess_type(file_path)[0]
+            # Open the file here for the duration of the async context
+            # load data, set the mime type
+            fs = fs or get_default_fs()
+            file_handle = fs.open(file_input, "rb")
+            files = {"file": (os.path.basename(file_path), file_handle, mime_type)}
+        else:
+            raise ValueError(
+                "file_input must be either a file path string, file bytes, or buffer object"
             )
 
-        extra_info = extra_info or {}
-        extra_info["file_path"] = file_path
+        data = {
+            "language": self.language.value,
+            "parsing_instruction": self.parsing_instruction,
+            "invalidate_cache": self.invalidate_cache,
+            "skip_diagonal_text": self.skip_diagonal_text,
+            "do_not_cache": self.do_not_cache,
+            "fast_mode": self.fast_mode,
+            "premium_mode": self.premium_mode,
+            "continuous_mode": self.continuous_mode,
+            "do_not_unroll_columns": self.do_not_unroll_columns,
+            "gpt4o_mode": self.gpt4o_mode,
+            "gpt4o_api_key": self.gpt4o_api_key,
+            "vendor_multimodal_api_key": self.vendor_multimodal_api_key,
+            "use_vendor_multimodal_model": self.use_vendor_multimodal_model,
+            "vendor_multimodal_model_name": self.vendor_multimodal_model_name,
+            "take_screenshot": self.take_screenshot,
+            "disable_ocr": self.disable_ocr,
+            "guess_xlsx_sheet_names": self.guess_xlsx_sheet_names,
+            "is_formatting_instruction": self.is_formatting_instruction,
+            "annotate_links": self.annotate_links,
+            "from_python_package": True,
+        }
 
-        headers = {"Authorization": f"Bearer {self.api_key}"}
+        # only send page separator to server if it is not None
+        # as if a null, "" string is sent the server will then ignore the page separator instead of using the default
+        if self.page_separator is not None:
+            data["page_separator"] = self.page_separator
 
-        # load data, set the mime type
-        with open(file_path, "rb") as f:
-            mime_type = mimetypes.guess_type(file_path)[0]
-            files = {"file": (f.name, f, mime_type)}
+        if self.page_prefix is not None:
+            data["page_prefix"] = self.page_prefix
 
-            # send the request, start job
-            url = f"{self.base_url}/api/parsing/upload"
-            async with httpx.AsyncClient(timeout=self.max_timeout) as client:
+        if self.page_suffix is not None:
+            data["page_suffix"] = self.page_suffix
+
+        if self.bounding_box is not None:
+            data["bounding_box"] = self.bounding_box
+
+        if self.target_pages is not None:
+            data["target_pages"] = self.target_pages
+
+        if self.webhook_url is not None:
+            data["webhook_url"] = self.webhook_url
+
+        # Azure OpenAI
+        if self.azure_openai_deployment_name is not None:
+            data["azure_openai_deployment_name"] = self.azure_openai_deployment_name
+
+        if self.azure_openai_endpoint is not None:
+            data["azure_openai_endpoint"] = self.azure_openai_endpoint
+
+        if self.azure_openai_api_version is not None:
+            data["azure_openai_api_version"] = self.azure_openai_api_version
+
+        if self.azure_openai_key is not None:
+            data["azure_openai_key"] = self.azure_openai_key
+
+        try:
+            async with self.client_context() as client:
                 response = await client.post(
                     url,
                     files=files,
                     headers=headers,
-                    data={
-                        "language": self.language.value,
-                        "parsing_instruction": self.parsing_instruction,
-                        "gpt4o_mode": self.gpt4o_mode,
-                        "gpt4o_api_key": self.gpt4o_api_key,
-                    },
+                    data=data,
                 )
                 if not response.is_success:
                     raise Exception(f"Failed to parse the file: {response.text}")
+                job_id = response.json()["id"]
+                return job_id
+        finally:
+            if file_handle is not None:
+                file_handle.close()
 
-        # check the status of the job, return when done
-        job_id = response.json()["id"]
-        return job_id
+    @staticmethod
+    def __get_filename(f: Union[TextIOWrapper, AbstractBufferedFile]) -> str:
+        if isinstance(f, TextIOWrapper):
+            return f.name
+        return f.full_name
 
     async def _get_job_result(
         self, job_id: str, result_type: str, verbose: bool = False
-    ) -> dict:
+    ) -> Dict[str, Any]:
         result_url = f"{self.base_url}/api/parsing/job/{job_id}/result/{result_type}"
         status_url = f"{self.base_url}/api/parsing/job/{job_id}"
         headers = {"Authorization": f"Bearer {self.api_key}"}
@@ -143,7 +349,7 @@ class LlamaParse(BasePydanticReader):
         tries = 0
         while True:
             await asyncio.sleep(self.check_interval)
-            async with httpx.AsyncClient(timeout=self.max_timeout) as client:
+            async with self.client_context() as client:
                 tries += 1
 
                 result = await client.get(status_url, headers=headers)
@@ -160,7 +366,8 @@ class LlamaParse(BasePydanticReader):
                     continue
 
                 # Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
-                status = result.json()["status"]
+                result_json = result.json()
+                status = result_json["status"]
                 if status == "SUCCESS":
                     parsed_result = await client.get(result_url, headers=headers)
                     return parsed_result.json()
@@ -172,19 +379,25 @@ class LlamaParse(BasePydanticReader):
                         print(".", end="", flush=True)
 
                     await asyncio.sleep(self.check_interval)
-
-                    continue
                 else:
-                    raise Exception(
-                        f"Failed to parse the file: {job_id}, status: {status}"
+                    error_code = result_json.get("error_code", "No error code found")
+                    error_message = result_json.get(
+                        "error_message", "No error message found"
                     )
 
+                    exception_str = f"Job ID: {job_id} failed with status: {status}, Error code: {error_code}, Error message: {error_message}"
+                    raise Exception(exception_str)
+
     async def _aload_data(
-        self, file_path: str, extra_info: Optional[dict] = None, verbose: bool = False
+        self,
+        file_path: FileInput,
+        extra_info: Optional[dict] = None,
+        fs: Optional[AbstractFileSystem] = None,
+        verbose: bool = False,
     ) -> List[Document]:
         """Load data from the input path."""
         try:
-            job_id = await self._create_job(file_path, extra_info=extra_info)
+            job_id = await self._create_job(file_path, extra_info=extra_info, fs=fs)
             if verbose:
                 print("Started parsing the file under job_id %s" % job_id)
 
@@ -192,33 +405,42 @@ class LlamaParse(BasePydanticReader):
                 job_id, self.result_type.value, verbose=verbose
             )
 
-            return [
+            docs = [
                 Document(
                     text=result[self.result_type.value],
                     metadata=extra_info or {},
                 )
             ]
+            if self.split_by_page:
+                return self._get_sub_docs(docs)
+            else:
+                return docs
 
         except Exception as e:
-            print(f"Error while parsing the file '{file_path}':", e)
+            file_repr = file_path if isinstance(file_path, str) else "<bytes/buffer>"
+            print(f"Error while parsing the file '{file_repr}':", e)
             if self.ignore_errors:
                 return []
             else:
                 raise e
 
     async def aload_data(
-        self, file_path: Union[List[str], str], extra_info: Optional[dict] = None
+        self,
+        file_path: Union[List[FileInput], FileInput],
+        extra_info: Optional[dict] = None,
+        fs: Optional[AbstractFileSystem] = None,
     ) -> List[Document]:
         """Load data from the input path."""
-        if isinstance(file_path, (str, Path)):
+        if isinstance(file_path, (str, PurePosixPath, Path, bytes, BufferedIOBase)):
             return await self._aload_data(
-                file_path, extra_info=extra_info, verbose=self.verbose
+                file_path, extra_info=extra_info, fs=fs, verbose=self.verbose
             )
         elif isinstance(file_path, list):
             jobs = [
                 self._aload_data(
                     f,
                     extra_info=extra_info,
+                    fs=fs,
                     verbose=self.verbose and not self.show_progress,
                 )
                 for f in file_path
@@ -244,11 +466,14 @@ class LlamaParse(BasePydanticReader):
             )
 
     def load_data(
-        self, file_path: Union[List[str], str], extra_info: Optional[dict] = None
+        self,
+        file_path: Union[List[FileInput], FileInput],
+        extra_info: Optional[dict] = None,
+        fs: Optional[AbstractFileSystem] = None,
     ) -> List[Document]:
         """Load data from the input path."""
         try:
-            return asyncio.run(self.aload_data(file_path, extra_info))
+            return asyncio_run(self.aload_data(file_path, extra_info, fs=fs))
         except RuntimeError as e:
             if nest_asyncio_err in str(e):
                 raise RuntimeError(nest_asyncio_msg)
@@ -256,28 +481,32 @@ class LlamaParse(BasePydanticReader):
                 raise e
 
     async def _aget_json(
-        self, file_path: str, extra_info: Optional[dict] = None
+        self, file_path: FileInput, extra_info: Optional[dict] = None
     ) -> List[dict]:
         """Load data from the input path."""
         try:
             job_id = await self._create_job(file_path, extra_info=extra_info)
             if self.verbose:
                 print("Started parsing the file under job_id %s" % job_id)
-
             result = await self._get_job_result(job_id, "json")
             result["job_id"] = job_id
-            result["file_path"] = file_path
-            return [result]
 
+            if not isinstance(file_path, (bytes, BufferedIOBase)):
+                result["file_path"] = str(file_path)
+
+            return [result]
         except Exception as e:
-            print(f"Error while parsing the file '{file_path}':", e)
+            file_repr = file_path if isinstance(file_path, str) else "<bytes/buffer>"
+            print(f"Error while parsing the file '{file_repr}':", e)
             if self.ignore_errors:
                 return []
             else:
                 raise e
 
     async def aget_json(
-        self, file_path: Union[List[str], str], extra_info: Optional[dict] = None
+        self,
+        file_path: Union[List[FileInput], FileInput],
+        extra_info: Optional[dict] = None,
     ) -> List[dict]:
         """Load data from the input path."""
         if isinstance(file_path, (str, Path)):
@@ -305,18 +534,22 @@ class LlamaParse(BasePydanticReader):
             )
 
     def get_json_result(
-        self, file_path: Union[List[str], str], extra_info: Optional[dict] = None
+        self,
+        file_path: Union[List[FileInput], FileInput],
+        extra_info: Optional[dict] = None,
     ) -> List[dict]:
         """Parse the input path."""
         try:
-            return asyncio.run(self.aget_json(file_path, extra_info))
+            return asyncio_run(self.aget_json(file_path, extra_info))
         except RuntimeError as e:
             if nest_asyncio_err in str(e):
                 raise RuntimeError(nest_asyncio_msg)
             else:
                 raise e
 
-    def get_images(self, json_result: List[dict], download_path: str) -> List[dict]:
+    async def aget_images(
+        self, json_result: List[dict], download_path: str
+    ) -> List[dict]:
         """Download images from the parsed result."""
         headers = {"Authorization": f"Bearer {self.api_key}"}
 
@@ -341,15 +574,23 @@ class LlamaParse(BasePydanticReader):
 
                         # get a valid image path
                         if not image_path.endswith(".png"):
-                            image_path += ".png"
+                            if not image_path.endswith(".jpg"):
+                                image_path += ".png"
 
                         image["path"] = image_path
                         image["job_id"] = job_id
-                        image["original_pdf_path"] = result["file_path"]
+
+                        image["original_file_path"] = result.get("file_path", None)
+
                         image["page_number"] = page["page"]
                         with open(image_path, "wb") as f:
                             image_url = f"{self.base_url}/api/parsing/job/{job_id}/result/image/{image_name}"
-                            f.write(httpx.get(image_url, headers=headers).content)
+                            async with self.client_context() as client:
+                                res = await client.get(
+                                    image_url, headers=headers, timeout=self.max_timeout
+                                )
+                                res.raise_for_status()
+                                f.write(res.content)
                         images.append(image)
             return images
         except Exception as e:
@@ -358,3 +599,82 @@ class LlamaParse(BasePydanticReader):
                 return []
             else:
                 raise e
+
+    def get_images(self, json_result: List[dict], download_path: str) -> List[dict]:
+        """Download images from the parsed result."""
+        try:
+            return asyncio_run(self.aget_images(json_result, download_path))
+        except RuntimeError as e:
+            if nest_asyncio_err in str(e):
+                raise RuntimeError(nest_asyncio_msg)
+            else:
+                raise e
+
+    async def aget_xlsx(
+        self, json_result: List[dict], download_path: str
+    ) -> List[dict]:
+        """Download images from the parsed result."""
+        headers = {"Authorization": f"Bearer {self.api_key}"}
+
+        # make the download path
+        if not os.path.exists(download_path):
+            os.makedirs(download_path)
+        try:
+            xlsx_list = []
+            for result in json_result:
+                job_id = result["job_id"]
+                if self.verbose:
+                    print("> XLSX")
+
+                xlsx_path = os.path.join(download_path, f"{job_id}.xlsx")
+
+                xlsx = {}
+
+                xlsx["path"] = xlsx_path
+                xlsx["job_id"] = job_id
+                xlsx["original_file_path"] = result.get("file_path", None)
+
+                with open(xlsx_path, "wb") as f:
+                    xlsx_url = (
+                        f"{self.base_url}/api/parsing/job/{job_id}/result/raw/xlsx"
+                    )
+                    async with self.client_context() as client:
+                        res = await client.get(
+                            xlsx_url, headers=headers, timeout=self.max_timeout
+                        )
+                        res.raise_for_status()
+                        f.write(res.content)
+                xlsx_list.append(xlsx)
+            return xlsx_list
+
+        except Exception as e:
+            print("Error while downloading xlsx:", e)
+            if self.ignore_errors:
+                return []
+            else:
+                raise e
+
+    def get_xlsx(self, json_result: List[dict], download_path: str) -> List[dict]:
+        """Download xlsx from the parsed result."""
+        try:
+            return asyncio_run(self.aget_xlsx(json_result, download_path))
+        except RuntimeError as e:
+            if nest_asyncio_err in str(e):
+                raise RuntimeError(nest_asyncio_msg)
+            else:
+                raise e
+
+    def _get_sub_docs(self, docs: List[Document]) -> List[Document]:
+        """Split docs into pages, by separator."""
+        sub_docs = []
+        separator = self.page_separator or _DEFAULT_SEPARATOR
+        for doc in docs:
+            doc_chunks = doc.text.split(separator)
+            for doc_chunk in doc_chunks:
+                sub_doc = Document(
+                    text=doc_chunk,
+                    metadata=deepcopy(doc.metadata),
+                )
+                sub_docs.append(sub_doc)
+
+        return sub_docs

llama_parse/cli/main.py

@@ -0,0 +1,92 @@
+import click
+import json
+from enum import Enum
+from pathlib import Path
+from pydantic.fields import FieldInfo
+from typing import Any, Callable, List
+
+from llama_parse.base import LlamaParse
+
+
+def pydantic_field_to_click_option(name: str, field: FieldInfo) -> click.Option:
+    """Convert a Pydantic field to a Click option."""
+    kwargs = {
+        "default": field.default if field.default else None,
+        "help": field.description,
+    }
+
+    if isinstance(kwargs["default"], Enum):
+        kwargs["default"] = kwargs["default"].value
+
+    if field.annotation is bool:
+        kwargs["is_flag"] = True
+        if field.default and field.default is True:
+            name = f"no-{name}"
+    return click.option(f'--{name.replace("_", "-")}', **kwargs)
+
+
+def add_options(options: List[click.Option]) -> Callable:
+    def _add_options(func: Callable) -> Callable:
+        for option in reversed(options):
+            func = option(func)
+        return func
+
+    return _add_options
+
+
+@click.command()
+@click.argument("file_paths", nargs=-1, type=click.Path(exists=True, path_type=Path))
+@click.option(
+    "--output-file", type=click.Path(path_type=Path), help="Path to save the output"
+)
+@click.option("--output-raw-json", is_flag=True, help="Output the raw JSON result")
+@add_options(
+    [
+        pydantic_field_to_click_option(name, field)
+        for name, field in LlamaParse.model_fields.items()
+        if name not in ["custom_client"]
+    ]
+)
+def parse(**kwargs: Any) -> None:
+    """Parse files using LlamaParse and output the results."""
+    file_paths = kwargs.pop("file_paths")
+    output_file = kwargs.pop("output_file")
+    output_raw_json = kwargs.pop("output_raw_json")
+
+    # Remove None values to use LlamaParse defaults
+    kwargs = {k: v for k, v in kwargs.items() if v is not None}
+
+    # Remove no- prefix for boolean flags
+    kwargs = {k.replace("no_", ""): v for k, v in kwargs.items()}
+
+    parser = LlamaParse(**kwargs)
+    if output_raw_json:
+        results = parser.get_json_result(list(file_paths))
+
+        if output_file:
+            with output_file.open("w") as f:
+                json.dump(results, f)
+            click.echo(f"Results saved to {output_file}")
+        else:
+            click.echo(results)
+    else:
+        results = parser.load_data(list(file_paths))
+
+        if output_file:
+            with output_file.open("w") as f:
+                for i, doc in enumerate(results):
+                    f.write(f"File: {doc.metadata.get('file_path', 'Unknown')}\n")  # type: ignore
+                    f.write(doc.text)  # type: ignore
+                    if i < len(results) - 1:
+                        f.write("\n\n---\n\n")
+            click.echo(f"Results saved to {output_file}")
+        else:
+            for i, doc in enumerate(results):
+                click.echo(f"File: {doc.metadata.get('file_path', 'Unknown')}")  # type: ignore
+                click.echo(doc.text)  # type: ignore
+                if i < len(results) - 1:
+                    click.echo("\n---\n")
+
+
+if __name__ == "__main__":
+    parse()

llama_parse/utils.py

@@ -10,7 +10,6 @@ class ResultType(str, Enum):
 
     TXT = "text"
     MD = "markdown"
-    JSON = "json"
 
 
 class Language(str, Enum):
@@ -101,52 +100,93 @@ class Language(str, Enum):
 
 SUPPORTED_FILE_TYPES = [
     ".pdf",
-    # Microsoft word - all versions
+    # document and presentations
+    ".602",
+    ".abw",
+    ".cgm",
+    ".cwk",
     ".doc",
     ".docx",
     ".docm",
     ".dot",
-    ".dotx",
     ".dotm",
-    # Rich text format
+    ".hwp",
+    ".key",
+    ".lwp",
+    ".mw",
+    ".mcw",
+    ".pages",
+    ".pbd",
+    ".ppt",
+    ".pptm",
+    ".pptx",
+    ".pot",
+    ".potm",
+    ".potx",
     ".rtf",
-    # Microsoft Works
-    ".wps",
-    # Word Perfect
-    ".wpd",
-    # Open Office
+    ".sda",
+    ".sdd",
+    ".sdp",
+    ".sdw",
+    ".sgl",
+    ".sti",
+    ".sxi",
     ".sxw",
     ".stw",
     ".sxg",
-    # Apple
-    ".pages",
-    # Mac Write
-    ".mw",
-    ".mcw",
-    # Unified Office Format text
-    ".uot",
+    ".txt",
     ".uof",
-    ".uos",
     ".uop",
-    # Microsoft powerpoints
-    ".ppt",
-    ".pptx",
-    ".pot",
-    ".pptm",
-    ".potx",
-    ".potm",
-    # Apple keynote
-    ".key",
-    # Open Office Presentations
-    ".odp",
-    ".odg",
-    ".otp",
-    ".fopd",
-    ".sxi",
-    ".sti",
-    # ebook
+    ".uot",
+    ".vor",
+    ".wpd",
+    ".wps",
+    ".xml",
+    ".zabw",
     ".epub",
-    # html
-    ".html",
+    # images
+    ".jpg",
+    ".jpeg",
+    ".png",
+    ".gif",
+    ".bmp",
+    ".svg",
+    ".tiff",
+    ".webp",
+    # web
     ".htm",
+    ".html",
+    # spreadsheets
+    ".xlsx",
+    ".xls",
+    ".xlsm",
+    ".xlsb",
+    ".xlw",
+    ".csv",
+    ".dif",
+    ".sylk",
+    ".slk",
+    ".prn",
+    ".numbers",
+    ".et",
+    ".ods",
+    ".fods",
+    ".uos1",
+    ".uos2",
+    ".dbf",
+    ".wk1",
+    ".wk2",
+    ".wk3",
+    ".wk4",
+    ".wks",
+    ".123",
+    ".wq1",
+    ".wq2",
+    ".wb1",
+    ".wb2",
+    ".wb3",
+    ".qpw",
+    ".xlr",
+    ".eth",
+    ".tsv",
 ]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.4.3"
+version = "0.5.13"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -13,8 +13,12 @@ packages = [{include = "llama_parse"}]
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-llama-index-core = ">=0.10.29"
+llama-index-core = ">=0.11.0"
+click = "^8.1.7"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"
 ipykernel = "^6.29.0"
+
+[tool.poetry.scripts]
+llama-parse = "llama_parse.cli.main:parse"

tests/test_reader.py

@@ -1,5 +1,8 @@
 import os
 import pytest
+from fsspec.implementations.local import LocalFileSystem
+from httpx import AsyncClient
+
 from llama_parse import LlamaParse
 
 
@@ -18,21 +21,71 @@ def test_simple_page_text() -> None:
     assert len(result[0].text) > 0
 
 
-@pytest.mark.skipif(
-    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
-    reason="LLAMA_CLOUD_API_KEY not set",
-)
-def test_simple_page_markdown() -> None:
-    parser = LlamaParse(result_type="markdown")
+@pytest.fixture
+def markdown_parser() -> LlamaParse:
+    if os.environ.get("LLAMA_CLOUD_API_KEY", "") == "":
+        pytest.skip("LLAMA_CLOUD_API_KEY not set")
+    return LlamaParse(result_type="markdown", ignore_errors=False)
+
+
+def test_simple_page_markdown(markdown_parser: LlamaParse) -> None:
+    filepath = os.path.join(
+        os.path.dirname(__file__), "test_files/attention_is_all_you_need.pdf"
+    )
+    result = markdown_parser.load_data(filepath)
+    assert len(result) == 1
+    assert len(result[0].text) > 0
+
+
+def test_simple_page_markdown_bytes(markdown_parser: LlamaParse) -> None:
+    markdown_parser = LlamaParse(result_type="markdown", ignore_errors=False)
 
     filepath = os.path.join(
         os.path.dirname(__file__), "test_files/attention_is_all_you_need.pdf"
     )
-    result = parser.load_data(filepath)
+    with open(filepath, "rb") as f:
+        file_bytes = f.read()
+    # client must provide extra_info with file_name
+    with pytest.raises(ValueError):
+        result = markdown_parser.load_data(file_bytes)
+    result = markdown_parser.load_data(
+        file_bytes, extra_info={"file_name": "attention_is_all_you_need.pdf"}
+    )
     assert len(result) == 1
     assert len(result[0].text) > 0
 
 
+def test_simple_page_markdown_buffer(markdown_parser: LlamaParse) -> None:
+    markdown_parser = LlamaParse(result_type="markdown", ignore_errors=False)
+
+    filepath = os.path.join(
+        os.path.dirname(__file__), "test_files/attention_is_all_you_need.pdf"
+    )
+    with open(filepath, "rb") as f:
+        # client must provide extra_info with file_name
+        with pytest.raises(ValueError):
+            result = markdown_parser.load_data(f)
+        result = markdown_parser.load_data(
+            f, extra_info={"file_name": "attention_is_all_you_need.pdf"}
+        )
+        assert len(result) == 1
+        assert len(result[0].text) > 0
+
+
+@pytest.mark.skipif(
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
+    reason="LLAMA_CLOUD_API_KEY not set",
+)
+def test_simple_page_with_custom_fs() -> None:
+    parser = LlamaParse(result_type="markdown")
+    fs = LocalFileSystem()
+    filepath = os.path.join(
+        os.path.dirname(__file__), "test_files/attention_is_all_you_need.pdf"
+    )
+    result = parser.load_data(filepath, fs=fs)
+    assert len(result) == 1
+
+
 @pytest.mark.skipif(
     os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
     reason="LLAMA_CLOUD_API_KEY not set",
@@ -57,3 +110,18 @@ def test_simple_page_progress_workers() -> None:
     result = parser.load_data([filepath, filepath])
     assert len(result) == 2
     assert len(result[0].text) > 0
+
+
+@pytest.mark.skipif(
+    os.environ.get("LLAMA_CLOUD_API_KEY", "") == "",
+    reason="LLAMA_CLOUD_API_KEY not set",
+)
+def test_custom_client() -> None:
+    custom_client = AsyncClient(verify=False, timeout=10)
+    parser = LlamaParse(result_type="markdown", custom_client=custom_client)
+    filepath = os.path.join(
+        os.path.dirname(__file__), "test_files/attention_is_all_you_need.pdf"
+    )
+    result = parser.load_data(filepath)
+    assert len(result) == 1
+    assert len(result[0].text) > 0