langchain/docs/modules/document_loaders/examples/copypaste.ipynb
2023-02-26 17:26:37 -08:00

103 lines
2.1 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "d9826810",
"metadata": {},
"source": [
"# Copy Paste\n",
"\n",
"This notebook covers how to load a document object from something you just want to copy and paste. In this case, you don't even need to use a DocumentLoader, but rather can just construct the Document directly."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "fd9e71a2",
"metadata": {},
"outputs": [],
"source": [
"from langchain.docstore.document import Document"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f40d3f30",
"metadata": {},
"outputs": [],
"source": [
"text = \"..... put the text you copy pasted here......\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "d409bdba",
"metadata": {},
"outputs": [],
"source": [
"doc = Document(page_content=text)"
]
},
{
"cell_type": "markdown",
"id": "cc0eff72",
"metadata": {},
"source": [
"## Metadata\n",
"If you want to add metadata about the where you got this piece of text, you easily can with the metadata key."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "fe3aa5aa",
"metadata": {},
"outputs": [],
"source": [
"metadata = {\"source\": \"internet\", \"date\": \"Friday\"}"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "827d4e91",
"metadata": {},
"outputs": [],
"source": [
"doc = Document(page_content=text, metadata=metadata)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c986a43d",
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}