mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
9870bfb9cd
- Description: this PR adds `s3_object_key` and `s3_bucket` to the doc metadata when loading an S3 file. This is particularly useful when using `S3DirectoryLoader` to remove the files from the dir once they have been processed (getting the object keys from the metadata `source` field seems brittle) - Dependencies: N/A - Tag maintainer: ? - Twitter handle: _cbornet --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
100 lines
2.0 KiB
Plaintext
100 lines
2.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "66a7777e",
|
|
"metadata": {},
|
|
"source": [
|
|
"# AWS S3 File\n",
|
|
"\n",
|
|
">[Amazon Simple Storage Service (Amazon S3)](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-folders.html) is an object storage service.\n",
|
|
"\n",
|
|
">[AWS S3 Buckets](https://docs.aws.amazon.com/AmazonS3/latest/userguide/UsingBucket.html)\n",
|
|
"\n",
|
|
"This covers how to load document objects from an `AWS S3 File` object."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "9ec8a3b3",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.document_loaders import S3FileLoader"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "43128d8d",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#!pip install boto3"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "35d6809a",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"loader = S3FileLoader(\"testing-hwc\", \"fake.docx\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "efd6be84",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 's3://testing-hwc/fake.docx'}, lookup_index=0)]"
|
|
]
|
|
},
|
|
"execution_count": 9,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"loader.load()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "93689594",
|
|
"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": "3.10.6"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|
|
|