mirror of
https://github.com/run-llama/llama_cloud_services.git
synced 2026-07-21 12:05:23 -04:00
Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Jerry Liu
|
b1877c8983 | ||
|
Jerry Liu
|
56d73c1a3f | ||
|
Jerry Liu
|
0d2ad9faab | ||
|
Logan
|
4572f00657 | ||
|
Logan
|
9ed208131f | ||
|
Pierre-Loic Doulcet
|
91b03b2ea7 |
@@ -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
|
||||
}
|
||||
Binary file not shown.
@@ -0,0 +1,327 @@
|
||||
{
|
||||
"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/demo_gpt4o/gpt4o_tesla_impact_report.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 200 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). To help you save tokens, we only load 4 pages of this report (which will count as 800 pages of LlamaParse pages). \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 200 pages). "
|
||||
]
|
||||
},
|
||||
{
|
||||
"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",
|
||||
" # base_url=\"https://api.staging.llamaindex.ai\",\n",
|
||||
" api_key=api_key,\n",
|
||||
" gpt4o_mode=True,\n",
|
||||
" # gpt4o_api_key=\"<gpt4o_api_key>\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1136ba82-074b-489d-9b0a-d609ccbf02b6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"documents_gpt4o = parser_gpt4o.load_data(\"./2019-tesla-impact-report-short.pdf\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9e65c54f-3e4c-4c78-b1e8-a55ebeba1f24",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"# Impact Report\n",
|
||||
"## 2019\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"---\n",
|
||||
"# Introduction 03\n",
|
||||
"\n",
|
||||
"# Mission and Tesla Ecosystem 04\n",
|
||||
"\n",
|
||||
"# Environmental Impact 06\n",
|
||||
"- Lifecycle Analysis of Tesla Vehicles versus Average ICE\n",
|
||||
"- Battery Recycling\n",
|
||||
"- NOx, Particulates and Other Pollutants\n",
|
||||
"- Water Used per Vehicle Manufactured\n",
|
||||
"- Emissions Credits\n",
|
||||
"- Net Energy Impact of Our Products\n",
|
||||
"\n",
|
||||
"# Product Impact 20\n",
|
||||
"- Price Equivalency\n",
|
||||
"- Primary Driver\n",
|
||||
"- Long Distance Travel\n",
|
||||
"- Active Safety\n",
|
||||
"- Passive Safety\n",
|
||||
"- Tesla Safety Awards\n",
|
||||
"- Fire Safety\n",
|
||||
"- Cyber Security\n",
|
||||
"- Disaster Relief\n",
|
||||
"- Resilience of the Grid\n",
|
||||
"- Megapack\n",
|
||||
"- Solar Roof\n",
|
||||
"\n",
|
||||
"# Supply Chain 33\n",
|
||||
"- Responsible Material Sourcing\n",
|
||||
"- Cobalt Sourcing\n",
|
||||
"\n",
|
||||
"# People and Culture 37\n",
|
||||
"- Our Environmental, Health, and Safety Strategy\n",
|
||||
"- Safety Improvements\n",
|
||||
"- Case Study: Ergonomics and Model Y Design\n",
|
||||
"- Rewarding the Individual\n",
|
||||
"- Culture of Diversity and Inclusion\n",
|
||||
"- Workforce Development\n",
|
||||
"- Community Engagement\n",
|
||||
"- Employee Mobility and Transportation Programs\n",
|
||||
"- Corporate Governance\n",
|
||||
"\n",
|
||||
"# Appendix 52\n",
|
||||
"---\n",
|
||||
"# Introduction\n",
|
||||
"\n",
|
||||
"The very purpose of Tesla’s existence is to accelerate the world’s transition to sustainable energy. In furtherance of this mission, we are excited to publish our second annual Impact Report. Transparency and disclosure are important for our customers, employees, and shareholders, which is why we have expanded the Impact Report’s content this year.\n",
|
||||
"\n",
|
||||
"While many environmental reports focus on emissions generated by the manufacturing phase of products and future goals for energy consumption, we highlight the totality of the environmental impact of our products today. After all, the vast majority of emissions generated by vehicles today occur in the product-use phase—that is, when consumers are driving their vehicles. We believe that providing information on both sides of the manufacturing and consumer-use equation provides a clearer picture of the environmental impact of Tesla products, and we have done so this year largely through a lifecycle analysis detailed in this report.\n",
|
||||
"\n",
|
||||
"Tesla aims to continue to increase the proportion of renewable energy usage at our factories in an effort to minimize the carbon footprint for every mile traveled by our products and their components in our supply chain. All of the factories that we built from the ground-up, such as Gigafactory Nevada and Gigafactory Shanghai, and our forthcoming Gigafactories in Berlin and North America, are designed from the beginning to use energy from renewable sources.\n",
|
||||
"\n",
|
||||
"Making a significant and lasting impact on environmental sustainability is difficult to achieve without securing financial sustainability for the long term. We generated positive Free Cash Flow (operating cash flow less capex) of more than $1 billion for the first time in 2019. We believe the notion that a sustainable future is not economically feasible is no longer valid.\n",
|
||||
"---\n",
|
||||
"# 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",
|
||||
"| 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[0].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": "f624e243-1878-4d87-841d-69e57360a7d9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from llama_index.core import VectorStoreIndex\n",
|
||||
"from llama_index.core.node_parser import SentenceSplitter\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"splitter = SentenceSplitter()\n",
|
||||
"nodes = splitter.get_nodes_from_documents(documents_gpt4o)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d8b7c3ad-2147-448c-bcbe-3e6fcd8d5361",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"vector_index = VectorStoreIndex(nodes)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8013351a-180d-4947-9f81-513042175c19",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_engine = vector_index.as_query_engine()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"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% to 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(\"What does Tesla aim to do?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e739eabf-732b-4f59-9628-972c4bf6c857",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Tesla aims to accelerate the world's transition to sustainable energy by creating a complete energy and transportation ecosystem that includes solar generation, energy storage, and all-electric vehicles with zero tailpipe emissions.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(str(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
|
||||
}
|
||||
@@ -57,6 +57,14 @@ class LlamaParse(BasePydanticReader):
|
||||
parsing_instruction: Optional[str] = Field(
|
||||
default="", description="The parsing instruction for the parser."
|
||||
)
|
||||
gpt4o_mode: bool = Field(
|
||||
default=False,
|
||||
description="Whether to use gpt-4o extract text from documents.",
|
||||
)
|
||||
gpt4o_api_key: Optional[str] = Field(
|
||||
default=None,
|
||||
description="The API key for the GPT-4o API. Lowers the cost of parsing.",
|
||||
)
|
||||
ignore_errors: bool = Field(
|
||||
default=True,
|
||||
description="Whether or not to ignore and skip errors raised during parsing.",
|
||||
@@ -113,6 +121,8 @@ class LlamaParse(BasePydanticReader):
|
||||
data={
|
||||
"language": self.language.value,
|
||||
"parsing_instruction": self.parsing_instruction,
|
||||
"gpt4o_mode": self.gpt4o_mode,
|
||||
"gpt4o_api_key": self.gpt4o_api_key,
|
||||
},
|
||||
)
|
||||
if not response.is_success:
|
||||
@@ -309,6 +319,11 @@ class LlamaParse(BasePydanticReader):
|
||||
def get_images(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:
|
||||
images = []
|
||||
for result in json_result:
|
||||
@@ -318,9 +333,16 @@ class LlamaParse(BasePydanticReader):
|
||||
print(f"> Image for page {page['page']}: {page['images']}")
|
||||
for image in page["images"]:
|
||||
image_name = image["name"]
|
||||
|
||||
# get the full path
|
||||
image_path = os.path.join(
|
||||
download_path, f"{job_id}-{image_name}"
|
||||
)
|
||||
|
||||
# get a valid image path
|
||||
if not image_path.endswith(".png"):
|
||||
image_path += ".png"
|
||||
|
||||
image["path"] = image_path
|
||||
image["job_id"] = job_id
|
||||
image["original_pdf_path"] = result["file_path"]
|
||||
|
||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
|
||||
|
||||
[tool.poetry]
|
||||
name = "llama-parse"
|
||||
version = "0.4.1"
|
||||
version = "0.4.3"
|
||||
description = "Parse files into RAG-Optimized formats."
|
||||
authors = ["Logan Markewich <logan@llamaindex.ai>"]
|
||||
license = "MIT"
|
||||
|
||||
Reference in New Issue
Block a user