langchain/docs/modules/document_loaders/examples/powerpoint.ipynb
2023-02-06 18:13:46 -08:00

95 lines
2.0 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "39af9ecd",
"metadata": {},
"source": [
"# PowerPoint\n",
"\n",
"This covers how to load PowerPoint documents into a document format that we can use downstream."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "721c48aa",
"metadata": {},
"outputs": [],
"source": [
"from langchain.document_loaders import UnstructuredPowerPointLoader"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9d3d0e35",
"metadata": {},
"outputs": [],
"source": [
"loader = UnstructuredPowerPointLoader(\"example_data/fake-power-point.pptx\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "06073f91",
"metadata": {},
"outputs": [],
"source": [
"data = loader.load()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "c9adc5cb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[Document(page_content='Adding a Bullet Slide\\n\\nFind the bullet slide layout\\n\\nUse _TextFrame.text for first bullet\\n\\nUse _TextFrame.add_paragraph() for subsequent bullets\\n\\nHere is a lot of text!\\n\\nHere is some text in a text box!', lookup_str='', metadata={'source': 'example_data/fake-power-point.pptx'}, lookup_index=0)]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0c55f1cf",
"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
}