mirror of
https://github.com/run-llama/llama_cloud_services.git
synced 2026-07-21 03:55:22 -04:00
Compare commits
14 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Sacha Bron
|
ae38f406fd | ||
|
Pierre-Loic Doulcet
|
4897d01cb0 | ||
|
Logan
|
bd7b563463 | ||
|
apostoli
|
530241dd0b | ||
|
Pierre-Loic Doulcet
|
6338641107 | ||
|
Bharath Lakshman Kumar
|
6d62fb89c3 | ||
|
Ravi Theja
|
7d4df3b6e5 | ||
|
Ravi Theja
|
bc28db5b92 | ||
|
Jerry Liu
|
f78186c0f7 | ||
|
Laurie Voss
|
e3292f5566 | ||
|
Jerry Liu
|
58f980f411 | ||
|
Ravi Theja
|
4740d0611d | ||
|
Laurie Voss
|
3651a10e80 | ||
|
Pierre-Loic Doulcet
|
483b51c51c |
@@ -31,10 +31,10 @@ jobs:
|
||||
shell: bash
|
||||
run: pip install -e .
|
||||
- name: Build and publish to pypi
|
||||
uses: JRubics/poetry-publish@v1.17
|
||||
uses: JRubics/poetry-publish@v2.1
|
||||
with:
|
||||
pypi_token: ${{ secrets.LLAMA_PARSE_PYPI_TOKEN }}
|
||||
ignore_dev_requirements: "yes"
|
||||
poetry_install_options: "--without dev"
|
||||
|
||||
- name: Create GitHub Release
|
||||
id: create_release
|
||||
|
||||
@@ -17,7 +17,7 @@ jobs:
|
||||
# You can use PyPy versions in python-version.
|
||||
# For example, pypy-2.7 and pypy-3.8
|
||||
matrix:
|
||||
python-version: ["3.8", "3.10", "3.11"]
|
||||
python-version: ["3.9", "3.10", "3.11", "3.12"]
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
with:
|
||||
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
@@ -1,415 +1,357 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "97c79c38-38a3-40f3-ba2e-250649347d63",
|
||||
"metadata": {
|
||||
"id": "97c79c38-38a3-40f3-ba2e-250649347d63"
|
||||
},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_starter_multimodal.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4e081457",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Multimodal Parsing using LlamaParse\n",
|
||||
"\n",
|
||||
"This cookbook shows you how to use LlamaParse to parse any document with the multimodal capabilities of Multi-Modal LLMs from Anthropic/ OpenAI.\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": "qOdqBxCS51Ow",
|
||||
"metadata": {
|
||||
"id": "qOdqBxCS51Ow"
|
||||
},
|
||||
"source": [
|
||||
"### Installation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "H_Vqcylb50vm",
|
||||
"metadata": {
|
||||
"id": "H_Vqcylb50vm"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install llama-parse"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "15e60ecf-519c-41fc-911b-765adaf8bad4",
|
||||
"metadata": {
|
||||
"id": "15e60ecf-519c-41fc-911b-765adaf8bad4"
|
||||
},
|
||||
"source": [
|
||||
"### Setup\n",
|
||||
"\n",
|
||||
"Here we setup `LLAMA_CLOUD_API_KEY` for using `LlamaParse`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "91a9e532-1454-40e0-bbf0-fd442c350121",
|
||||
"metadata": {
|
||||
"id": "91a9e532-1454-40e0-bbf0-fd442c350121"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import nest_asyncio\n",
|
||||
"\n",
|
||||
"nest_asyncio.apply()\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# API access to llama-cloud\n",
|
||||
"os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<YOUR LLAMACLOUD API KEY>\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "LGwBNPNotZRQ",
|
||||
"metadata": {
|
||||
"id": "LGwBNPNotZRQ"
|
||||
},
|
||||
"source": [
|
||||
"## Download Data\n",
|
||||
"\n",
|
||||
"For this demonstration, we will use OpenAI's recent paper `Evaluation of OpenAI o1: Opportunities and Challenges of AGI`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "IjtKDQRLrylI",
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "IjtKDQRLrylI",
|
||||
"outputId": "31df0fac-51f2-4697-f78b-0b7c0b8cd145"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--2024-12-05 18:54:24-- https://arxiv.org/pdf/2409.18486\n",
|
||||
"Resolving arxiv.org (arxiv.org)... 151.101.67.42, 151.101.131.42, 151.101.3.42, ...\n",
|
||||
"Connecting to arxiv.org (arxiv.org)|151.101.67.42|:443... connected.\n",
|
||||
"HTTP request sent, awaiting response... 200 OK\n",
|
||||
"Length: 13986265 (13M) [application/pdf]\n",
|
||||
"Saving to: ‘o1.pdf’\n",
|
||||
"\n",
|
||||
"o1.pdf 100%[===================>] 13.34M 11.8MB/s in 1.1s \n",
|
||||
"\n",
|
||||
"2024-12-05 18:54:26 (11.8 MB/s) - ‘o1.pdf’ saved [13986265/13986265]\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!wget \"https://arxiv.org/pdf/2409.18486\" -O \"o1.pdf\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4e29a9d7-5bd9-4fb8-8ec1-4c128a748662",
|
||||
"metadata": {
|
||||
"id": "4e29a9d7-5bd9-4fb8-8ec1-4c128a748662"
|
||||
},
|
||||
"source": [
|
||||
"## Initialize LlamaParse\n",
|
||||
"\n",
|
||||
"Initialize LlamaParse in multimodal mode, and specify the vendor.\n",
|
||||
"\n",
|
||||
"**NOTE**: optionally you can specify the Anthropic/ OpenAI API key. If you choose to do so LlamaParse will only charge you 1 credit (0.3c) per page. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Using your own API key may incur additional costs from your model provider and could result in failed pages or documents if you do not have sufficient usage limits."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "dc921729-3446-42ca-8e1b-a6fd26195ed9",
|
||||
"metadata": {
|
||||
"id": "dc921729-3446-42ca-8e1b-a6fd26195ed9"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from llama_index.core.schema import TextNode\n",
|
||||
"from typing import List\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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1b5d6da6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### With anthropic-sonnet-3.5"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "f2e9d9cf-8189-4fcb-b34f-cde6cc0b59c8",
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "f2e9d9cf-8189-4fcb-b34f-cde6cc0b59c8",
|
||||
"outputId": "a337cbdd-60db-4a73-b66b-2bd6159e81f2"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id dd9d5e0f-160e-486a-89a2-6005e5a1c2ac\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",
|
||||
" target_pages=\"24\"\n",
|
||||
" # invalidate_cache=True\n",
|
||||
")\n",
|
||||
"json_objs = parser.get_json_result(\"o1.pdf\")\n",
|
||||
"json_list = json_objs[0][\"pages\"]\n",
|
||||
"docs = get_text_nodes(json_list)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4f3c51b0-7878-48d7-9bc3-02b516500128",
|
||||
"metadata": {
|
||||
"id": "4f3c51b0-7878-48d7-9bc3-02b516500128"
|
||||
},
|
||||
"source": [
|
||||
"### With GPT-4o\n",
|
||||
"\n",
|
||||
"For comparison, we will also parse the document using GPT-4o."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "6fc3f258-50ae-4988-b904-c105463a498f",
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "6fc3f258-50ae-4988-b904-c105463a498f",
|
||||
"outputId": "89c525c4-2b93-4909-9657-55646e034637"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id 6a4dea44-4f90-406b-b290-9e98620b1232\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",
|
||||
" target_pages=\"24\",\n",
|
||||
" # invalidate_cache=True\n",
|
||||
")\n",
|
||||
"json_objs_gpt4o = parser_gpt4o.get_json_result(\"o1.pdf\")\n",
|
||||
"json_list_gpt4o = json_objs_gpt4o[0][\"pages\"]\n",
|
||||
"docs_gpt4o = get_text_nodes(json_list_gpt4o)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "44c20f7a-2901-4dd0-b635-a4b33c5664c1",
|
||||
"metadata": {
|
||||
"id": "44c20f7a-2901-4dd0-b635-a4b33c5664c1"
|
||||
},
|
||||
"source": [
|
||||
"### View Results\n",
|
||||
"\n",
|
||||
"Let's visualize the results along with the original document page."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "778698aa-da7e-4081-b3b5-0372f228536f",
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "778698aa-da7e-4081-b3b5-0372f228536f",
|
||||
"outputId": "bb89e323-7041-4fc3-d835-95e373189d02"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"page: 25\n",
|
||||
"\n",
|
||||
"| Participant_ID | clinical Description Reference |\n",
|
||||
"|-----------------|----------------------------------|\n",
|
||||
"| Attribute | Value | Basic Personal Information: Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia. |\n",
|
||||
"| Age | 72.0 |\n",
|
||||
"| Sex | Female |\n",
|
||||
"| Education | 15 |\n",
|
||||
"| Race | White | Biomarker Measurements: The subject's genetic profile includes an ApoE4 status of 0.0... |\n",
|
||||
"| DX_bl | AD |\n",
|
||||
"| DX | Dementia |\n",
|
||||
"| ... | ... | Cognitive and Neurofunctional Assessments: The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall... |\n",
|
||||
"| APOE4 | 1.0 |\n",
|
||||
"| TAU | 212.5 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| MMSE | 29.0 | Volumetric Data: Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 54422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 2782.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0.... |\n",
|
||||
"| CDRSB | 0.0 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| FLDSTRENG | 1.5 Tesla MRI |\n",
|
||||
"| Ventricles | 84599 |\n",
|
||||
"| Hippocampus | 5319 |\n",
|
||||
"| ... | ... |\n",
|
||||
"\n",
|
||||
"Figure 2: An example of a patient table and its corresponding clinical description.\n",
|
||||
"\n",
|
||||
"skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview's performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model's logical reasoning across varying levels of complexity.\n",
|
||||
"\n",
|
||||
"In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview's solutions.\n",
|
||||
"\n",
|
||||
"In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview's solutions. By comparing o1-preview's solutions with the dataset's solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview's overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# using Sonnet-3.5\n",
|
||||
"print(docs[0].get_content(metadata_mode=\"all\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "1511a30f-3efc-4142-9668-7dc056a24d0c",
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"base_uri": "https://localhost:8080/"
|
||||
},
|
||||
"id": "1511a30f-3efc-4142-9668-7dc056a24d0c",
|
||||
"outputId": "2e5e8e20-2b41-4183-f21f-dff503a03089"
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"page: 25\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"| Participant_ID | clinical Description Reference |\n",
|
||||
"|----------------|--------------------------------|\n",
|
||||
"| **Attribute** | **Value** |\n",
|
||||
"| Age | 72.0 |\n",
|
||||
"| Sex | Female |\n",
|
||||
"| Education | 15 |\n",
|
||||
"| Race | White |\n",
|
||||
"| DX_bl | AD |\n",
|
||||
"| DX | Dementia |\n",
|
||||
"| ... | ... |\n",
|
||||
"| APOE4 | 1.0 |\n",
|
||||
"| TAU | 212.5 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| MMSE | 29.0 |\n",
|
||||
"| CDRSB | 0.0 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| FLDSTRENG | 1.5 Tesla MRI |\n",
|
||||
"| Ventricles | 84599 |\n",
|
||||
"| Hippocampus | 5319 |\n",
|
||||
"| ... | ... |\n",
|
||||
"\n",
|
||||
"**Basic Personal Information:** Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia.\n",
|
||||
"\n",
|
||||
"**Biomarker Measurements:** The subject's genetic profile includes an ApoE4 status of 0.0...\n",
|
||||
"\n",
|
||||
"**Cognitive and Neurofunctional Assessments:** The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall...\n",
|
||||
"\n",
|
||||
"**Volumetric Data:** Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross-Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 84422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 27820.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0...\n",
|
||||
"\n",
|
||||
"Figure 2: An example of a patient table and its corresponding clinical description.\n",
|
||||
"\n",
|
||||
"----\n",
|
||||
"\n",
|
||||
"Skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview’s performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model’s logical reasoning across varying levels of complexity.\n",
|
||||
"\n",
|
||||
"In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview’s solutions.\n",
|
||||
"\n",
|
||||
"In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview’s solutions. By comparing o1-preview’s solutions with the dataset’s solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview’s overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# using GPT-4o\n",
|
||||
"print(docs_gpt4o[0].get_content(metadata_mode=\"all\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1c75bb85",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "llamacloud",
|
||||
"language": "python",
|
||||
"name": "llamacloud"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.4"
|
||||
}
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "97c79c38-38a3-40f3-ba2e-250649347d63",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_starter_multimodal.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
||||
]
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4e081457",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Multimodal Parsing using LlamaParse\n",
|
||||
"\n",
|
||||
"This cookbook shows you how to use LlamaParse to parse any document with the multimodal capabilities of Multi-Modal LLMs from Anthropic/ OpenAI.\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": "qOdqBxCS51Ow",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Installation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "H_Vqcylb50vm",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install llama-parse"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "15e60ecf-519c-41fc-911b-765adaf8bad4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup\n",
|
||||
"\n",
|
||||
"Here we setup `LLAMA_CLOUD_API_KEY` for using `LlamaParse`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "91a9e532-1454-40e0-bbf0-fd442c350121",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import nest_asyncio\n",
|
||||
"\n",
|
||||
"nest_asyncio.apply()\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"# API access to llama-cloud\n",
|
||||
"os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<YOUR LLAMACLOUD API KEY>\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "LGwBNPNotZRQ",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Download Data\n",
|
||||
"\n",
|
||||
"For this demonstration, we will use OpenAI's recent paper `Evaluation of OpenAI o1: Opportunities and Challenges of AGI`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "IjtKDQRLrylI",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--2024-12-05 18:54:24-- https://arxiv.org/pdf/2409.18486\n",
|
||||
"Resolving arxiv.org (arxiv.org)... 151.101.67.42, 151.101.131.42, 151.101.3.42, ...\n",
|
||||
"Connecting to arxiv.org (arxiv.org)|151.101.67.42|:443... connected.\n",
|
||||
"HTTP request sent, awaiting response... 200 OK\n",
|
||||
"Length: 13986265 (13M) [application/pdf]\n",
|
||||
"Saving to: ‘o1.pdf’\n",
|
||||
"\n",
|
||||
"o1.pdf 100%[===================>] 13.34M 11.8MB/s in 1.1s \n",
|
||||
"\n",
|
||||
"2024-12-05 18:54:26 (11.8 MB/s) - ‘o1.pdf’ saved [13986265/13986265]\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!wget \"https://arxiv.org/pdf/2409.18486\" -O \"o1.pdf\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"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/ OpenAI API key. If you choose to do so LlamaParse will only charge you 1 credit (0.3c) per page. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Using your own API key may incur additional costs from your model provider and could result in failed pages or documents if you do not have sufficient usage limits."
|
||||
]
|
||||
},
|
||||
{
|
||||
"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",
|
||||
"\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"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1b5d6da6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### With anthropic-sonnet-3.5"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 dd9d5e0f-160e-486a-89a2-6005e5a1c2ac\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",
|
||||
" target_pages=\"24\"\n",
|
||||
" # invalidate_cache=True\n",
|
||||
")\n",
|
||||
"json_objs = parser.get_json_result(\"o1.pdf\")\n",
|
||||
"json_list = json_objs[0][\"pages\"]\n",
|
||||
"docs = get_text_nodes(json_list)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4f3c51b0-7878-48d7-9bc3-02b516500128",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### With GPT-4o\n",
|
||||
"\n",
|
||||
"For comparison, we will also parse the document using GPT-4o."
|
||||
]
|
||||
},
|
||||
{
|
||||
"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 6a4dea44-4f90-406b-b290-9e98620b1232\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",
|
||||
" target_pages=\"24\",\n",
|
||||
" # invalidate_cache=True\n",
|
||||
")\n",
|
||||
"json_objs_gpt4o = parser_gpt4o.get_json_result(\"o1.pdf\")\n",
|
||||
"json_list_gpt4o = json_objs_gpt4o[0][\"pages\"]\n",
|
||||
"docs_gpt4o = get_text_nodes(json_list_gpt4o)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "778698aa-da7e-4081-b3b5-0372f228536f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"page: 25\n",
|
||||
"\n",
|
||||
"| Participant_ID | clinical Description Reference |\n",
|
||||
"|-----------------|----------------------------------|\n",
|
||||
"| Attribute | Value | Basic Personal Information: Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia. |\n",
|
||||
"| Age | 72.0 |\n",
|
||||
"| Sex | Female |\n",
|
||||
"| Education | 15 |\n",
|
||||
"| Race | White | Biomarker Measurements: The subject's genetic profile includes an ApoE4 status of 0.0... |\n",
|
||||
"| DX_bl | AD |\n",
|
||||
"| DX | Dementia |\n",
|
||||
"| ... | ... | Cognitive and Neurofunctional Assessments: The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall... |\n",
|
||||
"| APOE4 | 1.0 |\n",
|
||||
"| TAU | 212.5 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| MMSE | 29.0 | Volumetric Data: Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 54422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 2782.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0.... |\n",
|
||||
"| CDRSB | 0.0 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| FLDSTRENG | 1.5 Tesla MRI |\n",
|
||||
"| Ventricles | 84599 |\n",
|
||||
"| Hippocampus | 5319 |\n",
|
||||
"| ... | ... |\n",
|
||||
"\n",
|
||||
"Figure 2: An example of a patient table and its corresponding clinical description.\n",
|
||||
"\n",
|
||||
"skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview's performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model's logical reasoning across varying levels of complexity.\n",
|
||||
"\n",
|
||||
"In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview's solutions.\n",
|
||||
"\n",
|
||||
"In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview's solutions. By comparing o1-preview's solutions with the dataset's solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview's overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# using Sonnet-3.5\n",
|
||||
"print(docs[0].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: 25\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"| Participant_ID | clinical Description Reference |\n",
|
||||
"|----------------|--------------------------------|\n",
|
||||
"| **Attribute** | **Value** |\n",
|
||||
"| Age | 72.0 |\n",
|
||||
"| Sex | Female |\n",
|
||||
"| Education | 15 |\n",
|
||||
"| Race | White |\n",
|
||||
"| DX_bl | AD |\n",
|
||||
"| DX | Dementia |\n",
|
||||
"| ... | ... |\n",
|
||||
"| APOE4 | 1.0 |\n",
|
||||
"| TAU | 212.5 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| MMSE | 29.0 |\n",
|
||||
"| CDRSB | 0.0 |\n",
|
||||
"| ... | ... |\n",
|
||||
"| FLDSTRENG | 1.5 Tesla MRI |\n",
|
||||
"| Ventricles | 84599 |\n",
|
||||
"| Hippocampus | 5319 |\n",
|
||||
"| ... | ... |\n",
|
||||
"\n",
|
||||
"**Basic Personal Information:** Subject 098_S_0896 is a 72.0-year-old Female who has completed 15 years of education. The ethnicity is Not Hisp/Latino and race is White. Marital status is Married. Initially diagnosed as AD, as of the date 2007-10-24, the final diagnosis was Dementia.\n",
|
||||
"\n",
|
||||
"**Biomarker Measurements:** The subject's genetic profile includes an ApoE4 status of 0.0...\n",
|
||||
"\n",
|
||||
"**Cognitive and Neurofunctional Assessments:** The Mini-Mental State Examination score stands at 29.0. The Clinical Dementia Rating, sum of boxes, is 1.0. ADAS 11 and 13 scores are 4.67 and 4.67 respectively, with a score of 1.0 in delayed word recall...\n",
|
||||
"\n",
|
||||
"**Volumetric Data:** Under MRI conditions at a field strength of 1.5 Tesla MRI Tesla, using Cross-Sectional FreeSurfer (FreeSurfer Version 4.3), the imaging data recorded includes ventricles volume at 84422.0, hippocampus volume at 6677.0, whole brain volume at 1147980.0, entorhinal cortex volume at 27820.0, fusiform gyrus volume at 19432.0, and middle temporal area volume at 24951.0. The intracranial volume measured is 1799580.0...\n",
|
||||
"\n",
|
||||
"Figure 2: An example of a patient table and its corresponding clinical description.\n",
|
||||
"\n",
|
||||
"----\n",
|
||||
"\n",
|
||||
"Skills. Mathematics, as a highly structured and logic-driven discipline, provides an ideal testing ground for evaluating this reasoning ability. To investigate o1-preview’s performance, we designed a series of tests covering various difficulty levels. We begin with high school-level math competition problems in this section, followed by college-level mathematics problems in the next section, allowing us to observe the model’s logical reasoning across varying levels of complexity.\n",
|
||||
"\n",
|
||||
"In this section, we selected two primary areas of mathematics: algebra and counting and probability in this section. We chose these two topics because of their heavy reliance on problem-solving skills and their frequent use in assessing logical and abstract thinking [46]. The dataset used in testing is from the MATH dataset [46]. The problems in the dataset cover a wide range of subjects, including Prealgebra, Intermediate Algebra, Algebra, Geometry, Counting and Probability, Number Theory, and Precalculus. Each problem is categorized based on difficulty, ranked from level 1 to 5, according to the Art of Problem Solving (AoPS). The dataset mainly comprises problems from various high school math competitions, including the American Mathematics Competitions (AMC) 10 and 12, as well as the American Invitational Mathematics Examination (AIME), and other similar contests. Each problem comes with detailed reference solutions, allowing for a comprehensive comparison of o1-preview’s solutions.\n",
|
||||
"\n",
|
||||
"In addition to evaluating the final answers produced by o1-preview, our analysis delves into the step-by-step reasoning process of the o1-preview’s solutions. By comparing o1-preview’s solutions with the dataset’s solutions, we assess its ability to engage in logical reasoning, handle abstract problem-solving tasks, and apply structured approaches to reach correct answers. This deeper analysis offers insights into o1-preview’s overall reasoning capabilities, using mathematics as a reliable indicator for logical and structured thought processes.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# using GPT-4o\n",
|
||||
"print(docs_gpt4o[0].get_content(metadata_mode=\"all\"))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"provenance": []
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "llamacloud",
|
||||
"language": "python",
|
||||
"name": "llamacloud"
|
||||
},
|
||||
"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
|
||||
}
|
||||
|
||||
@@ -43,7 +43,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -69,7 +69,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -105,7 +105,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -119,17 +119,14 @@
|
||||
"source": [
|
||||
"from llama_parse import LlamaParse\n",
|
||||
"\n",
|
||||
"parser = LlamaParse(\n",
|
||||
" target_pages=\"0,1,2\",\n",
|
||||
" result_type=\"markdown\"\n",
|
||||
")\n",
|
||||
"parser = LlamaParse(target_pages=\"0,1,2\", result_type=\"markdown\")\n",
|
||||
"\n",
|
||||
"documents = parser.load_data('./uber_2021.pdf')"
|
||||
"documents = parser.load_data(\"./uber_2021.pdf\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -140,7 +137,7 @@
|
||||
" Document(id_='ad988239-3ab5-498d-85ba-a29241db24d4', embedding=None, metadata={}, excluded_embed_metadata_keys=[], excluded_llm_metadata_keys=[], relationships={}, metadata_template='{key}: {value}', metadata_separator='\\n', text='# UBER TECHNOLOGIES, INC.\\n\\n# TABLE OF CONTENTS\\n\\n|Special Note Regarding Forward-Looking Statements|2|\\n|---|---|\\n|PART I|PART I|\\n|Item 1. Business|4|\\n|Item 1A. Risk Factors|11|\\n|Item 1B. Unresolved Staff Comments|46|\\n|Item 2. Properties|46|\\n|Item 3. Legal Proceedings|46|\\n|Item 4. Mine Safety Disclosures|47|\\n|PART II|PART II|\\n|Item 5. Market for Registrant’s Common Equity, Related Stockholder Matters and Issuer Purchases of Equity Securities|47|\\n|Item 6. [Reserved]|48|\\n|Item 7. Management’s Discussion and Analysis of Financial Condition and Results of Operations|48|\\n|Item 7A. Quantitative and Qualitative Disclosures About Market Risk|69|\\n|Item 8. Financial Statements and Supplementary Data|70|\\n|Item 9. Changes in and Disagreements with Accountants on Accounting and Financial Disclosure|146|\\n|Item 9A. Controls and Procedures|147|\\n|Item 9B. Other Information|147|\\n|Item 9C. Disclosure Regarding Foreign Jurisdictions that Prevent Inspections|147|\\n|PART III|PART III|\\n|Item 10. Directors, Executive Officers and Corporate Governance|147|\\n|Item 11. Executive Compensation|147|\\n|Item 12. Security Ownership of Certain Beneficial Owners and Management and Related Stockholder Matters|148|\\n|Item 13. Certain Relationships and Related Transactions, and Director Independence|148|\\n|Item 14. Principal Accounting Fees and Services|148|\\n|PART IV|PART IV|\\n|Item 15. Exhibits, Financial Statement Schedules|148|\\n|Item 16. Form 10-K Summary|148|\\n|Exhibit Index|149|\\n|Signatures|152|', mimetype='text/plain', start_char_idx=None, end_char_idx=None, metadata_seperator='\\n', text_template='{metadata_str}\\n\\n{content}')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -148,13 +145,6 @@
|
||||
"source": [
|
||||
"documents"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -172,8 +162,7 @@
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.12.4"
|
||||
"pygments_lexer": "ipython3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 72 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 173 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 72 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 88 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 200 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 115 KiB |
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 350 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 47 KiB |
@@ -0,0 +1,602 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/parsing_instructions.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
|
||||
"\n",
|
||||
"# Parsing documents with Instructions\n",
|
||||
"\n",
|
||||
"Parsing instructions allow you to guide our parsing model in the same way you would instruct an LLM.\n",
|
||||
"\n",
|
||||
"These instructions can be useful for improving the parser's performance on complex document layouts, extracting data in a specific format, or transforming the document in other ways.\n",
|
||||
"\n",
|
||||
"### Why This Matters:\n",
|
||||
"Traditional document parsing can be rigid and error-prone, often missing crucial context and nuances in complex layouts. Our instruction-based parsing allows you to:\n",
|
||||
"\n",
|
||||
"1. Extract specific information with pinpoint accuracy\n",
|
||||
"2. Handle complex document layouts with ease\n",
|
||||
"3. Transform unstructured data into structured formats effortlessly\n",
|
||||
"4. Save hours of manual data entry and verification\n",
|
||||
"5. Reduce errors in document processing workflows\n",
|
||||
"\n",
|
||||
"In this demonstration, we showcase how parsing instructions can be used to extract specific information from unstructured documents. Below are the documents we use for testing:\n",
|
||||
"\n",
|
||||
"1. McDonald's Receipt - Extracting the price of each order and the final amount to be paid.\n",
|
||||
"\n",
|
||||
"2. Expense Report Document - Extracting employee name, employee ID, position, department, date ranges, individual expense items with dates, categories, and amounts.\n",
|
||||
"\n",
|
||||
"3. Purchase Order Document - Identifying the PO number, vendor details, shipping terms, and an itemized list of products with quantities and unit prices.\n",
|
||||
"\n",
|
||||
"Let's jump into these real-world examples and see how parsing instructions can help us extract specific information."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Installation"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install llama-parse"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup API Key"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import nest_asyncio\n",
|
||||
"\n",
|
||||
"nest_asyncio.apply()\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"llx-...\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### McDonald's Receipt\n",
|
||||
"\n",
|
||||
"Here we extract the price of each order and the final amount to be paid."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<img src=\"mcdonalds_receipt.png\" alt=\"Alt Text\" width=\"500\">"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id 66643b81-e2f4-408b-890b-8e116472210b\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from llama_parse import LlamaParse\n",
|
||||
"\n",
|
||||
"vanilaParsing = LlamaParse(result_type=\"markdown\").load_data(\"./mcdonalds_receipt.png\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"# Rate us HIGHLY SATISFIED\n",
|
||||
"\n",
|
||||
"Purchase any sandwich and receive a FREE ITEM\n",
|
||||
"\n",
|
||||
"Go to WWW.mcdvoice.com within 7 days of purchase of equal or lesser value and tell us about your visit.\n",
|
||||
"\n",
|
||||
"Validation Code: 31278-01121-21018-20481-00081-0\n",
|
||||
"\n",
|
||||
"Valid at participating US McDonald's\n",
|
||||
"\n",
|
||||
"Expires 30 days after receipt date\n",
|
||||
"\n",
|
||||
"# McDonald's Restaurant #312782378\n",
|
||||
"\n",
|
||||
"PINE RD NW\n",
|
||||
"\n",
|
||||
"RICE MN 56367-9740\n",
|
||||
"\n",
|
||||
"TEL# 320 393 4600\n",
|
||||
"\n",
|
||||
"KS# 12/08/2022 08:48 PM\n",
|
||||
"\n",
|
||||
"# Order\n",
|
||||
"\n",
|
||||
"|Happy Meal 6 Pc|$4.89|\n",
|
||||
"|---|---|\n",
|
||||
"|Creamy Ranch Cup| |\n",
|
||||
"|Extra Kids Fry| |\n",
|
||||
"|Wreck It Ralph 2 Snack| |\n",
|
||||
"|Oreo McFlurry|$2.69|\n",
|
||||
"\n",
|
||||
"# Summary\n",
|
||||
"\n",
|
||||
"|Subtotal|$7.58|\n",
|
||||
"|---|---|\n",
|
||||
"|Tax|$0.52|\n",
|
||||
"|Take-Out Total|$8.10|\n",
|
||||
"|Cash Tendered|$10.00|\n",
|
||||
"|Change|$1.90|\n",
|
||||
"\n",
|
||||
"### Not ACCEPTING APPLICATIONS *++ McDonald's Restaurant Rice\n",
|
||||
"\n",
|
||||
"Text to #36453 apply 31278\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(vanilaParsing[0].text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id 1a04fdbb-5415-4a36-a1bd-26bfb5d618fa\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"parsingInstruction = \"\"\"The provided document is a McDonald's receipt.\n",
|
||||
" Provide the price of each order and final amount to be paid.\"\"\"\n",
|
||||
"withInstructionParsing = LlamaParse(\n",
|
||||
" result_type=\"markdown\", parsing_instruction=parsingInstruction\n",
|
||||
").load_data(\"./mcdonalds_receipt.png\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Here are the prices for each order from the McDonald's receipt:\n",
|
||||
"\n",
|
||||
"1. Happy Meal 6 Pc: $4.89\n",
|
||||
"2. Snack Oreo McFlurry: $2.69\n",
|
||||
"\n",
|
||||
"**Subtotal:** $7.58\n",
|
||||
"**Tax:** $0.52\n",
|
||||
"**Total Amount to be Paid:** $8.10\n",
|
||||
"\n",
|
||||
"The cash tendered was $10.00, and the change given was $1.90.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(withInstructionParsing[0].text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Expense Report Document\n",
|
||||
"\n",
|
||||
"Here we extract employee name, employee ID, position, department, date ranges, individual expense items with dates, categories, and amounts."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<img src=\"expense_report_document.png\" alt=\"Alt Text\" width=\"500\">"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id b6bcc6e1-7d30-4522-9abd-ace196781a70\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"vanilaParsing = LlamaParse(result_type=\"markdown\").load_data(\n",
|
||||
" \"./expense_report_document.pdf\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"# QUANTUM DYNAMICS CORPORATION\n",
|
||||
"\n",
|
||||
"# EMPLOYEE EXPENSE REPORT\n",
|
||||
"\n",
|
||||
"# FISCAL YEAR 2024\n",
|
||||
"\n",
|
||||
"# EMPLOYEE INFORMATION:\n",
|
||||
"\n",
|
||||
"Name: Dr. Alexandra Chen-Martinez, PhD\n",
|
||||
"\n",
|
||||
"Employee ID: QD-2022-1457\n",
|
||||
"\n",
|
||||
"Department: Advanced Research & Development\n",
|
||||
"\n",
|
||||
"Cost Center: CC-ARD-NA-003\n",
|
||||
"\n",
|
||||
"Project Codes: QD-QUANTUM-2024-01, QD-AI-2024-03\n",
|
||||
"\n",
|
||||
"Position: Principal Research Scientist\n",
|
||||
"\n",
|
||||
"Reporting Manager: Dr. James Thompson\n",
|
||||
"\n",
|
||||
"# TRIP/EXPENSE PERIOD:\n",
|
||||
"\n",
|
||||
"Start Date: November 15, 2024\n",
|
||||
"\n",
|
||||
"End Date: December 10, 2024\n",
|
||||
"\n",
|
||||
"Purpose: International Conference Attendance & Client Meetings\n",
|
||||
"\n",
|
||||
"Locations: Tokyo, Japan → Singapore → Sydney, Australia\n",
|
||||
"\n",
|
||||
"# CURRENCY CONVERSION RATES APPLIED:\n",
|
||||
"\n",
|
||||
"JPY (¥) → USD: 0.0068 (as of 11/15/2024)\n",
|
||||
"\n",
|
||||
"SGD (S$) → USD: 0.74 (as of 11/28/2024)\n",
|
||||
"\n",
|
||||
"AUD (A$) → USD: 0.65 (as of 12/03/2024)\n",
|
||||
"\n",
|
||||
"# ITEMIZED EXPENSES:\n",
|
||||
"\n",
|
||||
"|Date|Category|Description|Original|Currency|USD|\n",
|
||||
"|---|---|---|---|---|---|\n",
|
||||
"|11/15/2024|Transportation|JFK → NRT Business Class|4,250.00|USD|4,250.00|\n",
|
||||
"|Booking Ref: QF78956 - Corporate Rate Applied|Booking Ref: QF78956 - Corporate Rate Applied|Booking Ref: QF78956 - Corporate Rate Applied|Booking Ref: QF78956 - Corporate Rate Applied|Booking Ref: QF78956 - Corporate Rate Applied|Booking Ref: QF78956 - Corporate Rate Applied|\n",
|
||||
"|Project Code: QD-QUANTUM-2024-01|Project Code: QD-QUANTUM-2024-01|Project Code: QD-QUANTUM-2024-01|Project Code: QD-QUANTUM-2024-01|Project Code: QD-QUANTUM-2024-01|Project Code: QD-QUANTUM-2024-01|\n",
|
||||
"|11/16/2024|Accommodation|Hilton Tokyo - 5 nights|225,000|JPY|1,530.00|\n",
|
||||
"|Confirmation: HTK-2024-78956|Confirmation: HTK-2024-78956|Confirmation: HTK-2024-78956|Confirmation: HTK-2024-78956|Confirmation: HTK-2024-78956|Confirmation: HTK-2024-78956|\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(vanilaParsing[0].text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id 7b0d05bb-947b-4475-8d0f-f10386f7446e\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"parsingInstruction = \"\"\"You are provided with an expense report. \n",
|
||||
"Extract employee name, employee id, position, department, date ranges, individual expense items with dates, categories, and amounts.\"\"\"\n",
|
||||
"\n",
|
||||
"withInstructionParsing = LlamaParse(\n",
|
||||
" result_type=\"markdown\", parsing_instruction=parsingInstruction\n",
|
||||
").load_data(\"./expense_report_document.pdf\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"**Employee Information:**\n",
|
||||
"- **Name:** Dr. Alexandra Chen-Martinez, PhD\n",
|
||||
"- **Employee ID:** QD-2022-1457\n",
|
||||
"- **Position:** Principal Research Scientist\n",
|
||||
"- **Department:** Advanced Research & Development\n",
|
||||
"\n",
|
||||
"**Trip/Expense Period:**\n",
|
||||
"- **Start Date:** November 15, 2024\n",
|
||||
"- **End Date:** December 10, 2024\n",
|
||||
"\n",
|
||||
"**Expense Items:**\n",
|
||||
"1. **Date:** 11/15/2024\n",
|
||||
"- **Category:** Transportation\n",
|
||||
"- **Description:** JFK → NRT Business Class\n",
|
||||
"- **Original Amount:** $4,250.00\n",
|
||||
"- **Currency:** USD\n",
|
||||
"- **USD Amount:** $4,250.00\n",
|
||||
"- **Booking Reference:** QF78956 - Corporate Rate Applied\n",
|
||||
"- **Project Code:** QD-QUANTUM-2024-01\n",
|
||||
"\n",
|
||||
"2. **Date:** 11/16/2024\n",
|
||||
"- **Category:** Accommodation\n",
|
||||
"- **Description:** Hilton Tokyo - 5 nights\n",
|
||||
"- **Original Amount:** ¥225,000\n",
|
||||
"- **Currency:** JPY\n",
|
||||
"- **USD Amount:** $1,530.00\n",
|
||||
"- **Confirmation:** HTK-2024-78956\n",
|
||||
"\n",
|
||||
"**Locations:**\n",
|
||||
"- Tokyo, Japan\n",
|
||||
"- Singapore\n",
|
||||
"- Sydney, Australia\n",
|
||||
"\n",
|
||||
"**Currency Conversion Rates Applied:**\n",
|
||||
"- JPY (¥) → USD: 0.0068 (as of 11/15/2024)\n",
|
||||
"- SGD (S$) → USD: 0.74 (as of 11/28/2024)\n",
|
||||
"- AUD (A$) → USD: 0.65 (as of 12/03/2024)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(withInstructionParsing[0].text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Purchase Order Document \n",
|
||||
"\n",
|
||||
"Here we identify the PO number, vendor details, shipping terms, and an itemized list of products with quantities and unit prices."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"<img src=\"purchase_order_document.png\" alt=\"Alt Text\" width=\"500\">"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id b8cb11c3-7dce-4e6a-94bb-1a4e50e45e55\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"vanilaParsing = LlamaParse(result_type=\"markdown\").load_data(\n",
|
||||
" \"./purchase_order_document.pdf\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"# GLOBAL TECH SOLUTIONS, INC.\n",
|
||||
"\n",
|
||||
"# PURCHASE ORDER\n",
|
||||
"\n",
|
||||
"Document Reference: PO-2024-GT-9876/REV.2\n",
|
||||
"\n",
|
||||
"[Original: PO-2024-GT-9876]\n",
|
||||
"\n",
|
||||
"Amendment Date: 12/10/2024\n",
|
||||
"\n",
|
||||
"# VENDOR INFORMATION:\n",
|
||||
"\n",
|
||||
"Quantum Electronics Manufacturing\n",
|
||||
"\n",
|
||||
"DUNS: 78-456-7890\n",
|
||||
"\n",
|
||||
"Tax ID: EU8976543210\n",
|
||||
"\n",
|
||||
"Hoofdorp, Netherlands\n",
|
||||
"\n",
|
||||
"Vendor #: QEM-EU-2024-001\n",
|
||||
"\n",
|
||||
"# SHIP TO:\n",
|
||||
"\n",
|
||||
"Global Tech Solutions, Inc.\n",
|
||||
"\n",
|
||||
"Building 7A, Innovation Park\n",
|
||||
"\n",
|
||||
"2100 Technology Drive\n",
|
||||
"\n",
|
||||
"Austin, TX 78701\n",
|
||||
"\n",
|
||||
"USA\n",
|
||||
"\n",
|
||||
"Attn: Sarah Martinez, Receiving Manager\n",
|
||||
"\n",
|
||||
"Tel: +1 (512) 555-0123\n",
|
||||
"\n",
|
||||
"# PAYMENT TERMS:\n",
|
||||
"\n",
|
||||
"Net 45\n",
|
||||
"\n",
|
||||
"2% discount if paid within 15 days\n",
|
||||
"\n",
|
||||
"# SHIPPING TERMS:\n",
|
||||
"\n",
|
||||
"DDP (Delivered Duty Paid) - Incoterms 2020\n",
|
||||
"\n",
|
||||
"Insurance Required: Yes\n",
|
||||
"\n",
|
||||
"Preferred Carrier: DHL/FedEx\n",
|
||||
"\n",
|
||||
"Required Delivery Date: 01/15/2025\n",
|
||||
"\n",
|
||||
"# SPECIAL INSTRUCTIONS:\n",
|
||||
"\n",
|
||||
"1. All shipments must include Certificate of Conformance\n",
|
||||
"2. ESD-sensitive items must be properly packaged\n",
|
||||
"3. Temperature logging required for items marked with *\n",
|
||||
"4. Partial shipments accepted with prior approval\n",
|
||||
"5. Quote PO number on all correspondence\n",
|
||||
"\n",
|
||||
"# ITEM DETAILS:\n",
|
||||
"\n",
|
||||
"|Line|Part Number|Description|Qty|UOM|Unit Price|Total|\n",
|
||||
"|---|---|---|---|---|---|---|\n",
|
||||
"|1|QE-MCU-5590|Microcontroller Unit|500|EA|$12.50|$6,250.00|\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(vanilaParsing[0].text)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Started parsing the file under job_id d2731305-984d-4633-8a52-0493748cf10b\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"parsingInstruction = \"\"\"You are provided with a purchase order. \n",
|
||||
"Identify the PO number, vendor details, shipping terms, and itemized list of products with quantities and unit prices.\"\"\"\n",
|
||||
"\n",
|
||||
"withInstructionParsing = LlamaParse(\n",
|
||||
" result_type=\"markdown\", parsing_instruction=parsingInstruction\n",
|
||||
").load_data(\"./purchase_order_document.pdf\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Here are the details extracted from the purchase order:\n",
|
||||
"\n",
|
||||
"**PO Number:** PO-2024-GT-9876/REV.2\n",
|
||||
"\n",
|
||||
"**Vendor Details:**\n",
|
||||
"- **Vendor Name:** Quantum Electronics Manufacturing\n",
|
||||
"- **DUNS:** 78-456-7890\n",
|
||||
"- **Tax ID:** EU8976543210\n",
|
||||
"- **Address:** Hoofdorp, Netherlands\n",
|
||||
"- **Vendor Number:** QEM-EU-2024-001\n",
|
||||
"- **Contact Person:** Sarah Martinez, Receiving Manager\n",
|
||||
"- **Phone:** +1 (512) 555-0123\n",
|
||||
"\n",
|
||||
"**Shipping Terms:**\n",
|
||||
"- **Terms:** DDP (Delivered Duty Paid) - Incoterms 2020\n",
|
||||
"- **Insurance Required:** Yes\n",
|
||||
"- **Preferred Carrier:** DHL/FedEx\n",
|
||||
"- **Required Delivery Date:** 01/15/2025\n",
|
||||
"\n",
|
||||
"**Itemized List of Products:**\n",
|
||||
"1. **Part Number:** QE-MCU-5590\n",
|
||||
"- **Description:** Microcontroller Unit\n",
|
||||
"- **Quantity:** 500 EA\n",
|
||||
"- **Unit Price:** $12.50\n",
|
||||
"- **Total:** $6,250.00\n",
|
||||
"\n",
|
||||
"**Payment Terms:**\n",
|
||||
"- Net 45\n",
|
||||
"- 2% discount if paid within 15 days\n",
|
||||
"\n",
|
||||
"**Special Instructions:**\n",
|
||||
"1. All shipments must include Certificate of Conformance\n",
|
||||
"2. ESD-sensitive items must be properly packaged\n",
|
||||
"3. Temperature logging required for items marked with *\n",
|
||||
"4. Partial shipments accepted with prior approval\n",
|
||||
"5. Quote PO number on all correspondence\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(withInstructionParsing[0].text)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "llamacloud",
|
||||
"language": "python",
|
||||
"name": "llamacloud"
|
||||
},
|
||||
"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
|
||||
}
|
||||
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 344 KiB |
File diff suppressed because it is too large
Load Diff
Binary file not shown.
|
After Width: | Height: | Size: 2.3 MiB |
Binary file not shown.
|
After Width: | Height: | Size: 100 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 464 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 410 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 444 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 610 KiB |
+286
-111
@@ -1,29 +1,29 @@
|
||||
import os
|
||||
import asyncio
|
||||
import mimetypes
|
||||
import os
|
||||
import time
|
||||
from contextlib import asynccontextmanager
|
||||
from copy import deepcopy
|
||||
from io import BufferedIOBase
|
||||
from pathlib import Path, PurePath, PurePosixPath
|
||||
from typing import Any, AsyncGenerator, Dict, List, Optional, Union
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import httpx
|
||||
import mimetypes
|
||||
import time
|
||||
from pathlib import Path, PurePath, PurePosixPath
|
||||
from typing import AsyncGenerator, Any, Dict, List, Optional, Union
|
||||
from contextlib import asynccontextmanager
|
||||
from io import BufferedIOBase
|
||||
|
||||
from fsspec import AbstractFileSystem
|
||||
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.bridge.pydantic import Field, PrivateAttr, 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 (
|
||||
SUPPORTED_FILE_TYPES,
|
||||
ResultType,
|
||||
nest_asyncio_err,
|
||||
nest_asyncio_msg,
|
||||
ResultType,
|
||||
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
|
||||
@@ -32,6 +32,11 @@ FileInput = Union[str, bytes, BufferedIOBase]
|
||||
_DEFAULT_SEPARATOR = "\n---\n"
|
||||
|
||||
|
||||
JOB_RESULT_URL = "/api/parsing/job/{job_id}/result/{result_type}"
|
||||
JOB_STATUS_ROUTE = "/api/parsing/job/{job_id}"
|
||||
JOB_UPLOAD_ROUTE = "/api/parsing/upload"
|
||||
|
||||
|
||||
class LlamaParse(BasePydanticReader):
|
||||
"""A smart-parser for files."""
|
||||
|
||||
@@ -49,9 +54,11 @@ class LlamaParse(BasePydanticReader):
|
||||
default=1,
|
||||
description="The interval in seconds to check if the parsing is done.",
|
||||
)
|
||||
|
||||
custom_client: Optional[httpx.AsyncClient] = Field(
|
||||
default=None, description="A custom HTTPX client to use for sending requests."
|
||||
)
|
||||
|
||||
ignore_errors: bool = Field(
|
||||
default=True,
|
||||
description="Whether or not to ignore and skip errors raised during parsing.",
|
||||
@@ -133,6 +140,14 @@ class LlamaParse(BasePydanticReader):
|
||||
default=None,
|
||||
description="The top margin of the bounding box to use to extract text from documents expressed as a float between 0 and 1 representing the percentage of the page height.",
|
||||
)
|
||||
complemental_formatting_instruction: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The complemental formatting instruction for the parser. Tell llamaParse how some thing should to be formatted, while retaining the markdown output.",
|
||||
)
|
||||
content_guideline_instruction: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The content guideline for the parser. Tell LlamaParse how the content should be changed / transformed.",
|
||||
)
|
||||
continuous_mode: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Parse documents continuously, leading to better results on documents where tables span across two pages.",
|
||||
@@ -157,10 +172,18 @@ class LlamaParse(BasePydanticReader):
|
||||
default=False,
|
||||
description="If set to true, the parser will extract/tag charts from the document.",
|
||||
)
|
||||
extract_layout: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will extract the layout information of the document. Cost 1 credit per page.",
|
||||
)
|
||||
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.",
|
||||
)
|
||||
formatting_instruction: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The Formatting instruction for the parser. Override default llamaParse behavior. In most case you want to use complemental_formatting_instruction instead.",
|
||||
)
|
||||
guess_xlsx_sheet_names: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Whether to guess the sheet names of the xlsx file.",
|
||||
@@ -173,17 +196,33 @@ class LlamaParse(BasePydanticReader):
|
||||
default=False,
|
||||
description="If set to true, when parsing HTML the parser will remove fixed elements. Useful to hide cookie banners.",
|
||||
)
|
||||
html_remove_navigation_elements: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, when parsing HTML the parser will remove navigation elements. Useful to hide menus, header, footer.",
|
||||
)
|
||||
http_proxy: Optional[str] = Field(
|
||||
default=None,
|
||||
description="(optional) If set with input_url will use the specified http proxy to download the file.",
|
||||
)
|
||||
ignore_document_elements_for_layout_detection: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will ignore document elements for layout detection and only rely on a vision model.",
|
||||
)
|
||||
input_s3_region: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The region of the input S3 bucket if input_s3_path is specified.",
|
||||
)
|
||||
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.",
|
||||
)
|
||||
is_formatting_instruction: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Allow the parsing instruction to also format the output. Disable to have a cleaner markdown output.",
|
||||
job_timeout_extra_time_per_page_in_seconds: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The extra time in seconds to wait for the parsing to finish per page. Get added to job_timeout_in_seconds.",
|
||||
)
|
||||
job_timeout_in_seconds: Optional[float] = Field(
|
||||
default=None,
|
||||
description="The maximum timeout in seconds to wait for the parsing to finish. Override default timeout of 30 minutes. Minimum is 120 seconds.",
|
||||
)
|
||||
language: Optional[str] = Field(
|
||||
default="en", description="The language of the text to parse."
|
||||
@@ -200,6 +239,14 @@ class LlamaParse(BasePydanticReader):
|
||||
default=None,
|
||||
description="An S3 path prefix to store the output of the parsing job. If set, the parser will upload the output to S3. The bucket need to be accessible from the LlamaIndex organization.",
|
||||
)
|
||||
output_s3_region: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The AWS region of the output S3 bucket defined in output_s3_path_prefix.",
|
||||
)
|
||||
output_tables_as_HTML: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will output tables as HTML in the markdown.",
|
||||
)
|
||||
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.",
|
||||
@@ -212,9 +259,6 @@ class LlamaParse(BasePydanticReader):
|
||||
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.",
|
||||
)
|
||||
parsing_instruction: Optional[str] = Field(
|
||||
default="", description="The parsing instruction for the parser."
|
||||
)
|
||||
premium_mode: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Use our best parser mode if set to True.",
|
||||
@@ -223,6 +267,31 @@ class LlamaParse(BasePydanticReader):
|
||||
default=False,
|
||||
description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
|
||||
)
|
||||
spreadsheet_extract_sub_tables: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will extract sub-tables from the spreadsheet when possible (more than one table per sheet).",
|
||||
)
|
||||
|
||||
strict_mode_buggy_font: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will fail if it can't extract text from a document because of a buggy font.",
|
||||
)
|
||||
|
||||
strict_mode_image_extraction: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will fail if it can't extract an image from the document.",
|
||||
)
|
||||
|
||||
strict_mode_image_ocr: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will fail if it can't OCR an image from the document.",
|
||||
)
|
||||
|
||||
strict_mode_reconstruction: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will fail if it can't reconstruct a table or a heading from the document.",
|
||||
)
|
||||
|
||||
structured_output: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="If set to true, the parser will output structured data based on the provided JSON Schema.",
|
||||
@@ -273,6 +342,13 @@ class LlamaParse(BasePydanticReader):
|
||||
default=None,
|
||||
description="The API key for the GPT-4o API. Lowers the cost of parsing.",
|
||||
)
|
||||
is_formatting_instruction: Optional[bool] = Field(
|
||||
default=False,
|
||||
description="Allow the parsing instruction to also format the output. Disable to have a cleaner markdown output.",
|
||||
)
|
||||
parsing_instruction: Optional[str] = Field(
|
||||
default="", description="The parsing instruction for the parser."
|
||||
)
|
||||
|
||||
@field_validator("api_key", mode="before", check_fields=True)
|
||||
@classmethod
|
||||
@@ -295,6 +371,25 @@ class LlamaParse(BasePydanticReader):
|
||||
url = os.getenv("LLAMA_CLOUD_BASE_URL", None)
|
||||
return url or v or DEFAULT_BASE_URL
|
||||
|
||||
_aclient: Union[httpx.AsyncClient, None] = PrivateAttr(default=None, init=False)
|
||||
|
||||
@property
|
||||
def aclient(self) -> httpx.AsyncClient:
|
||||
if not self._aclient:
|
||||
self._aclient = self.custom_client or httpx.AsyncClient()
|
||||
|
||||
# need to do this outside instantiation in case user
|
||||
# updates base_url, api_key, or max_timeout later
|
||||
# ... you wouldn't usually expect that, except
|
||||
# if someone does do it and it doesn't reflect on
|
||||
# the client they'll end up pretty confused, so
|
||||
# for the sake of ergonomics...
|
||||
self._aclient.base_url = self.base_url
|
||||
self._aclient.headers["Authorization"] = f"Bearer {self.api_key}"
|
||||
self._aclient.timeout = self.max_timeout
|
||||
|
||||
return self._aclient
|
||||
|
||||
@asynccontextmanager
|
||||
async def client_context(self) -> AsyncGenerator[httpx.AsyncClient, None]:
|
||||
"""Create a context for the HTTPX client."""
|
||||
@@ -343,8 +438,6 @@ class LlamaParse(BasePydanticReader):
|
||||
extra_info: Optional[dict] = None,
|
||||
fs: Optional[AbstractFileSystem] = None,
|
||||
) -> str:
|
||||
headers = {"Authorization": f"Bearer {self.api_key}"}
|
||||
url = f"{self.base_url}/api/parsing/upload"
|
||||
files = None
|
||||
file_handle = None
|
||||
input_url = file_input if self._is_input_url(file_input) else None
|
||||
@@ -435,6 +528,14 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.bbox_top is not None:
|
||||
data["bbox_top"] = self.bbox_top
|
||||
|
||||
if self.complemental_formatting_instruction:
|
||||
data[
|
||||
"complemental_formatting_instruction"
|
||||
] = self.complemental_formatting_instruction
|
||||
|
||||
if self.content_guideline_instruction:
|
||||
data["content_guideline_instruction"] = self.content_guideline_instruction
|
||||
|
||||
if self.continuous_mode:
|
||||
data["continuous_mode"] = self.continuous_mode
|
||||
|
||||
@@ -453,9 +554,15 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.extract_charts:
|
||||
data["extract_charts"] = self.extract_charts
|
||||
|
||||
if self.extract_layout:
|
||||
data["extract_layout"] = self.extract_layout
|
||||
|
||||
if self.fast_mode:
|
||||
data["fast_mode"] = self.fast_mode
|
||||
|
||||
if self.formatting_instruction:
|
||||
data["formatting_instruction"] = self.formatting_instruction
|
||||
|
||||
if self.guess_xlsx_sheet_names:
|
||||
data["guess_xlsx_sheet_names"] = self.guess_xlsx_sheet_names
|
||||
|
||||
@@ -465,9 +572,19 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.html_remove_fixed_elements:
|
||||
data["html_remove_fixed_elements"] = self.html_remove_fixed_elements
|
||||
|
||||
if self.html_remove_navigation_elements:
|
||||
data[
|
||||
"html_remove_navigation_elements"
|
||||
] = self.html_remove_navigation_elements
|
||||
|
||||
if self.http_proxy is not None:
|
||||
data["http_proxy"] = self.http_proxy
|
||||
|
||||
if self.ignore_document_elements_for_layout_detection:
|
||||
data[
|
||||
"ignore_document_elements_for_layout_detection"
|
||||
] = self.ignore_document_elements_for_layout_detection
|
||||
|
||||
if input_url is not None:
|
||||
files = None
|
||||
data["input_url"] = str(input_url)
|
||||
@@ -476,12 +593,23 @@ class LlamaParse(BasePydanticReader):
|
||||
files = None
|
||||
data["input_s3_path"] = str(input_s3_path)
|
||||
|
||||
if self.input_s3_region is not None:
|
||||
data["input_s3_region"] = self.input_s3_region
|
||||
|
||||
if self.invalidate_cache:
|
||||
data["invalidate_cache"] = self.invalidate_cache
|
||||
|
||||
if self.is_formatting_instruction:
|
||||
data["is_formatting_instruction"] = self.is_formatting_instruction
|
||||
|
||||
if self.job_timeout_extra_time_per_page_in_seconds is not None:
|
||||
data[
|
||||
"job_timeout_extra_time_per_page_in_seconds"
|
||||
] = self.job_timeout_extra_time_per_page_in_seconds
|
||||
|
||||
if self.job_timeout_in_seconds is not None:
|
||||
data["job_timeout_in_seconds"] = self.job_timeout_in_seconds
|
||||
|
||||
if self.language:
|
||||
data["language"] = self.language
|
||||
|
||||
@@ -494,6 +622,12 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.output_s3_path_prefix is not None:
|
||||
data["output_s3_path_prefix"] = self.output_s3_path_prefix
|
||||
|
||||
if self.output_s3_region is not None:
|
||||
data["output_s3_region"] = self.output_s3_region
|
||||
|
||||
if self.output_tables_as_HTML:
|
||||
data["output_tables_as_HTML"] = self.output_tables_as_HTML
|
||||
|
||||
if self.page_prefix is not None:
|
||||
data["page_prefix"] = self.page_prefix
|
||||
|
||||
@@ -506,6 +640,9 @@ class LlamaParse(BasePydanticReader):
|
||||
data["page_suffix"] = self.page_suffix
|
||||
|
||||
if self.parsing_instruction is not None:
|
||||
print(
|
||||
"WARNING: parsing_instruction is deprecated. Use complemental_formatting_instruction or content_guideline_instruction instead."
|
||||
)
|
||||
data["parsing_instruction"] = self.parsing_instruction
|
||||
|
||||
if self.premium_mode:
|
||||
@@ -514,6 +651,21 @@ class LlamaParse(BasePydanticReader):
|
||||
if self.skip_diagonal_text:
|
||||
data["skip_diagonal_text"] = self.skip_diagonal_text
|
||||
|
||||
if self.spreadsheet_extract_sub_tables:
|
||||
data["spreadsheet_extract_sub_tables"] = self.spreadsheet_extract_sub_tables
|
||||
|
||||
if self.strict_mode_buggy_font:
|
||||
data["strict_mode_buggy_font"] = self.strict_mode_buggy_font
|
||||
|
||||
if self.strict_mode_image_extraction:
|
||||
data["strict_mode_image_extraction"] = self.strict_mode_image_extraction
|
||||
|
||||
if self.strict_mode_image_ocr:
|
||||
data["strict_mode_image_ocr"] = self.strict_mode_image_ocr
|
||||
|
||||
if self.strict_mode_reconstruction:
|
||||
data["strict_mode_reconstruction"] = self.strict_mode_reconstruction
|
||||
|
||||
if self.structured_output:
|
||||
data["structured_output"] = self.structured_output
|
||||
|
||||
@@ -554,17 +706,12 @@ class LlamaParse(BasePydanticReader):
|
||||
data["gpt4o_api_key"] = self.gpt4o_api_key
|
||||
|
||||
try:
|
||||
async with self.client_context() as client:
|
||||
response = await client.post(
|
||||
url,
|
||||
files=files,
|
||||
headers=headers,
|
||||
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
|
||||
resp = await self.aclient.post(JOB_UPLOAD_ROUTE, files=files, data=data) # type: ignore
|
||||
resp.raise_for_status() # this raises if status is not 2xx
|
||||
return resp.json()["id"]
|
||||
except httpx.HTTPStatusError as err: # this catches it
|
||||
msg = f"Failed to parse the file: {err.response.text}"
|
||||
raise Exception(msg) from err # this preserves the exception context
|
||||
finally:
|
||||
if file_handle is not None:
|
||||
file_handle.close()
|
||||
@@ -572,52 +719,51 @@ class LlamaParse(BasePydanticReader):
|
||||
async def _get_job_result(
|
||||
self, job_id: str, result_type: str, verbose: bool = False
|
||||
) -> 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}"}
|
||||
|
||||
start = time.time()
|
||||
tries = 0
|
||||
|
||||
# so we're not re-setting the headers & stuff on each
|
||||
# usage... assume that there is not some other
|
||||
# coro also modifying base_url and the other client related configs.
|
||||
client = self.aclient
|
||||
while True:
|
||||
await asyncio.sleep(self.check_interval)
|
||||
async with self.client_context() as client:
|
||||
tries += 1
|
||||
tries += 1
|
||||
result = await client.get(JOB_STATUS_ROUTE.format(job_id=job_id))
|
||||
if result.status_code != 200:
|
||||
end = time.time()
|
||||
if end - start > self.max_timeout:
|
||||
raise Exception(f"Timeout while parsing the file: {job_id}")
|
||||
if verbose and tries % 10 == 0:
|
||||
print(".", end="", flush=True)
|
||||
await asyncio.sleep(self.check_interval)
|
||||
continue
|
||||
|
||||
result = await client.get(status_url, headers=headers)
|
||||
# Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
|
||||
result_json = result.json()
|
||||
status = result_json["status"]
|
||||
if status == "SUCCESS":
|
||||
parsed_result = await client.get(
|
||||
JOB_RESULT_URL.format(job_id=job_id, result_type=result_type),
|
||||
)
|
||||
return parsed_result.json()
|
||||
|
||||
if result.status_code != 200:
|
||||
end = time.time()
|
||||
if end - start > self.max_timeout:
|
||||
raise Exception(f"Timeout while parsing the file: {job_id}")
|
||||
if verbose and tries % 10 == 0:
|
||||
print(".", end="", flush=True)
|
||||
elif status == "PENDING":
|
||||
end = time.time()
|
||||
if end - start > self.max_timeout:
|
||||
raise Exception(f"Timeout while parsing the file: {job_id}")
|
||||
if verbose and tries % 10 == 0:
|
||||
print(".", end="", flush=True)
|
||||
await asyncio.sleep(self.check_interval)
|
||||
|
||||
await asyncio.sleep(self.check_interval)
|
||||
else:
|
||||
error_code = result_json.get("error_code", "No error code found")
|
||||
error_message = result_json.get(
|
||||
"error_message", "No error message found"
|
||||
)
|
||||
|
||||
continue
|
||||
|
||||
# Allowed values "PENDING", "SUCCESS", "ERROR", "CANCELED"
|
||||
result_json = result.json()
|
||||
status = result_json["status"]
|
||||
if status == "SUCCESS":
|
||||
parsed_result = await client.get(result_url, headers=headers)
|
||||
return parsed_result.json()
|
||||
elif status == "PENDING":
|
||||
end = time.time()
|
||||
if end - start > self.max_timeout:
|
||||
raise Exception(f"Timeout while parsing the file: {job_id}")
|
||||
if verbose and tries % 10 == 0:
|
||||
print(".", end="", flush=True)
|
||||
|
||||
await asyncio.sleep(self.check_interval)
|
||||
else:
|
||||
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)
|
||||
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,
|
||||
@@ -778,54 +924,77 @@ class LlamaParse(BasePydanticReader):
|
||||
else:
|
||||
raise e
|
||||
|
||||
async def aget_images(
|
||||
self, json_result: List[dict], download_path: str
|
||||
async def aget_assets(
|
||||
self, json_result: List[dict], download_path: str, asset_key: str
|
||||
) -> List[dict]:
|
||||
"""Download images from the parsed result."""
|
||||
headers = {"Authorization": f"Bearer {self.api_key}"}
|
||||
|
||||
# make the download path
|
||||
"""Download assets (images or charts) from the parsed result."""
|
||||
# Make the download path
|
||||
if not os.path.exists(download_path):
|
||||
os.makedirs(download_path)
|
||||
|
||||
client = self.aclient
|
||||
try:
|
||||
images = []
|
||||
assets = []
|
||||
for result in json_result:
|
||||
job_id = result["job_id"]
|
||||
for page in result["pages"]:
|
||||
if self.verbose:
|
||||
print(f"> Image for page {page['page']}: {page['images']}")
|
||||
for image in page["images"]:
|
||||
image_name = image["name"]
|
||||
print(
|
||||
f"> {asset_key.capitalize()} for page {page['page']}: {page[asset_key]}"
|
||||
)
|
||||
for asset in page[asset_key]:
|
||||
asset_name = asset["name"]
|
||||
|
||||
# get the full path
|
||||
image_path = os.path.join(
|
||||
download_path, f"{job_id}-{image_name}"
|
||||
# Get the full path
|
||||
asset_path = os.path.join(
|
||||
download_path, f"{job_id}-{asset_name}"
|
||||
)
|
||||
|
||||
# get a valid image path
|
||||
if not image_path.endswith(".png"):
|
||||
if not image_path.endswith(".jpg"):
|
||||
image_path += ".png"
|
||||
# Get a valid asset path
|
||||
if not asset_path.endswith(".png"):
|
||||
if not asset_path.endswith(".jpg"):
|
||||
asset_path += ".png"
|
||||
|
||||
image["path"] = image_path
|
||||
image["job_id"] = job_id
|
||||
asset["path"] = asset_path
|
||||
asset["job_id"] = job_id
|
||||
asset["original_file_path"] = result.get("file_path", None)
|
||||
asset["page_number"] = page["page"]
|
||||
|
||||
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}"
|
||||
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
|
||||
with open(asset_path, "wb") as f:
|
||||
asset_url = f"{self.base_url}/api/parsing/job/{job_id}/result/image/{asset_name}"
|
||||
resp = await client.get(asset_url)
|
||||
resp.raise_for_status()
|
||||
f.write(resp.content)
|
||||
assets.append(asset)
|
||||
return assets
|
||||
except Exception as e:
|
||||
print("Error while downloading images from the parsed result:", e)
|
||||
print(f"Error while downloading {asset_key} from the parsed result:", e)
|
||||
if self.ignore_errors:
|
||||
return []
|
||||
else:
|
||||
raise e
|
||||
|
||||
async def aget_images(
|
||||
self, json_result: List[dict], download_path: str
|
||||
) -> List[dict]:
|
||||
"""Download images from the parsed result."""
|
||||
try:
|
||||
return await self.aget_assets(json_result, download_path, "images")
|
||||
except Exception as e:
|
||||
print("Error while downloading images:", e)
|
||||
if self.ignore_errors:
|
||||
return []
|
||||
else:
|
||||
raise e
|
||||
|
||||
async def aget_charts(
|
||||
self, json_result: List[dict], download_path: str
|
||||
) -> List[dict]:
|
||||
"""Download charts from the parsed result."""
|
||||
try:
|
||||
return await self.aget_assets(json_result, download_path, "charts")
|
||||
except Exception as e:
|
||||
print("Error while downloading charts:", e)
|
||||
if self.ignore_errors:
|
||||
return []
|
||||
else:
|
||||
@@ -841,15 +1010,24 @@ class LlamaParse(BasePydanticReader):
|
||||
else:
|
||||
raise e
|
||||
|
||||
def get_charts(self, json_result: List[dict], download_path: str) -> List[dict]:
|
||||
"""Download charts from the parsed result."""
|
||||
try:
|
||||
return asyncio_run(self.aget_charts(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}"}
|
||||
|
||||
"""Download xlsx from the parsed result."""
|
||||
# make the download path
|
||||
if not os.path.exists(download_path):
|
||||
os.makedirs(download_path)
|
||||
client = self.aclient
|
||||
try:
|
||||
xlsx_list = []
|
||||
for result in json_result:
|
||||
@@ -869,12 +1047,9 @@ class LlamaParse(BasePydanticReader):
|
||||
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)
|
||||
res = await client.get(xlsx_url)
|
||||
res.raise_for_status()
|
||||
f.write(res.content)
|
||||
xlsx_list.append(xlsx)
|
||||
return xlsx_list
|
||||
|
||||
|
||||
@@ -191,4 +191,11 @@ SUPPORTED_FILE_TYPES = [
|
||||
".xlr",
|
||||
".eth",
|
||||
".tsv",
|
||||
".mp3",
|
||||
".mp4",
|
||||
".mpeg",
|
||||
".mpga",
|
||||
".m4a",
|
||||
".wav",
|
||||
".webm",
|
||||
]
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
|
||||
|
||||
[tool.poetry]
|
||||
name = "llama-parse"
|
||||
version = "0.5.16"
|
||||
version = "0.5.20"
|
||||
description = "Parse files into RAG-Optimized formats."
|
||||
authors = ["Logan Markewich <logan@llamaindex.ai>"]
|
||||
license = "MIT"
|
||||
|
||||
@@ -153,10 +153,10 @@ async def test_input_url() -> None:
|
||||
@pytest.mark.asyncio
|
||||
async def test_input_url_with_website_input() -> None:
|
||||
parser = LlamaParse(result_type="markdown")
|
||||
input_url = "https://www.google.com"
|
||||
input_url = "https://www.example.com"
|
||||
result = await parser.aload_data(input_url)
|
||||
assert len(result) == 1
|
||||
assert "google" in result[0].text.lower()
|
||||
assert "example" in result[0].text.lower()
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
|
||||
Reference in New Issue
Block a user