mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
74 lines
1.3 KiB
Plaintext
74 lines
1.3 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f70e6118",
|
|
"metadata": {},
|
|
"source": [
|
|
"# PDF\n",
|
|
"\n",
|
|
"This covers how to load pdfs into a document format that we can use downstream."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "0cc0cd42",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import UnstructuredPDFLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "082d557c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"loader = UnstructuredPDFLoader(\"example_data/layout-parser-paper.pdf\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "5c41106f",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"data = loader.load()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "54fb6b62",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|