forked from Archives/langchain
In https://github.com/hwchase17/langchain/issues/1716 , it was identified that there were two .py files performing similar tasks. As a resolution, one of the files has been removed, as its purpose had already been fulfilled by the other file. Additionally, the init has been updated accordingly. Furthermore, the how_to_guides.rst file has been updated to include links to documentation that was previously missing. This was deemed necessary as the existing list on https://langchain.readthedocs.io/en/latest/modules/document_loaders/how_to_guides.html was incomplete, causing confusion for users who rely on the full list of documentation on the left sidebar of the website.tool-patch
Klein Tahiraj
1 year ago
committed by
GitHub
parent
1f93c5cf69
commit
d3d4503ce2
@ -1,145 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "34c90eed",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Microsoft Word\n",
|
||||
"\n",
|
||||
"This notebook shows how to load text from Microsoft word documents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "28ded768",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import UnstructuredDocxLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "f1f26035",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredDocxLoader('example_data/fake.docx')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2c87dde9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "0e4a884c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5d1472e9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Retain Elements\n",
|
||||
"\n",
|
||||
"Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "93abf60b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "c35cdbcc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"data = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "fae2d730",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"data"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "961a7b1d",
|
||||
"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
|
||||
}
|
||||
@ -1,13 +0,0 @@
|
||||
"""Loader that loads Microsoft Word files."""
|
||||
from typing import List
|
||||
|
||||
from langchain.document_loaders.unstructured import UnstructuredFileLoader
|
||||
|
||||
|
||||
class UnstructuredDocxLoader(UnstructuredFileLoader):
|
||||
"""Loader that uses unstructured to load Microsoft Word files."""
|
||||
|
||||
def _get_elements(self) -> List:
|
||||
from unstructured.partition.docx import partition_docx
|
||||
|
||||
return partition_docx(filename=self.file_path)
|
||||
Loading…
Reference in New Issue