mirror of https://github.com/hwchase17/langchain
feat: Add `UnstructuredOrgModeLoader` (#6842)
### Summary Adds `UnstructuredOrgModeLoader` for processing [Org-mode](https://en.wikipedia.org/wiki/Org-mode) documents. ### Testing ```python from langchain.document_loaders import UnstructuredOrgModeLoader loader = UnstructuredOrgModeLoader( file_path="example_data/README.org", mode="elements" ) docs = loader.load() print(docs[0]) ``` ### Reviewers - @rlancemartin - @eyurtsev - @hwchase17pull/6853/head
parent
e53995836a
commit
b24472eae3
@ -0,0 +1,27 @@
|
||||
* Example Docs
|
||||
|
||||
The sample docs directory contains the following files:
|
||||
|
||||
- ~example-10k.html~ - A 10-K SEC filing in HTML format
|
||||
- ~layout-parser-paper.pdf~ - A PDF copy of the layout parser paper
|
||||
- ~factbook.xml~ / ~factbook.xsl~ - Example XML/XLS files that you
|
||||
can use to test stylesheets
|
||||
|
||||
These documents can be used to test out the parsers in the library. In
|
||||
addition, here are instructions for pulling in some sample docs that are
|
||||
too big to store in the repo.
|
||||
|
||||
** XBRL 10-K
|
||||
|
||||
You can get an example 10-K in inline XBRL format using the following
|
||||
~curl~. Note, you need to have the user agent set in the header or the
|
||||
SEC site will reject your request.
|
||||
|
||||
#+BEGIN_SRC bash
|
||||
|
||||
curl -O \
|
||||
-A '${organization} ${email}'
|
||||
https://www.sec.gov/Archives/edgar/data/311094/000117184321001344/0001171843-21-001344.txt
|
||||
#+END_SRC
|
||||
|
||||
You can parse this document using the HTML parser.
|
@ -0,0 +1,88 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Org-mode\n",
|
||||
"\n",
|
||||
">A [Org Mode document](https://en.wikipedia.org/wiki/Org-mode) is a document editing, formatting, and organizing mode, designed for notes, planning, and authoring within the free software text editor Emacs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## `UnstructuredOrgModeLoader`\n",
|
||||
"\n",
|
||||
"You can load data from Org-mode files with `UnstructuredOrgModeLoader` using the following workflow."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import UnstructuredOrgModeLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = UnstructuredOrgModeLoader(\n",
|
||||
" file_path=\"example_data/README.org\", mode=\"elements\"\n",
|
||||
")\n",
|
||||
"docs = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"page_content='Example Docs' metadata={'source': 'example_data/README.org', 'filename': 'README.org', 'file_directory': 'example_data', 'filetype': 'text/org', 'page_number': 1, 'category': 'Title'}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(docs[0])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"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": "3.8.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
@ -0,0 +1,22 @@
|
||||
"""Loader that loads Org-Mode files."""
|
||||
from typing import Any, List
|
||||
|
||||
from langchain.document_loaders.unstructured import (
|
||||
UnstructuredFileLoader,
|
||||
validate_unstructured_version,
|
||||
)
|
||||
|
||||
|
||||
class UnstructuredOrgModeLoader(UnstructuredFileLoader):
|
||||
"""Loader that uses unstructured to load Org-Mode files."""
|
||||
|
||||
def __init__(
|
||||
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
||||
):
|
||||
validate_unstructured_version(min_unstructured_version="0.7.9")
|
||||
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
||||
|
||||
def _get_elements(self) -> List:
|
||||
from unstructured.partition.org import partition_org
|
||||
|
||||
return partition_org(filename=self.file_path, **self.unstructured_kwargs)
|
@ -0,0 +1,15 @@
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
from langchain.document_loaders import UnstructuredOrgModeLoader
|
||||
|
||||
EXAMPLE_DIRECTORY = file_path = Path(__file__).parent.parent / "examples"
|
||||
|
||||
|
||||
def test_unstructured_org_mode_loader() -> None:
|
||||
"""Test unstructured loader."""
|
||||
file_path = os.path.join(EXAMPLE_DIRECTORY, "README.org")
|
||||
loader = UnstructuredOrgModeLoader(str(file_path))
|
||||
docs = loader.load()
|
||||
|
||||
assert len(docs) == 1
|
@ -0,0 +1,27 @@
|
||||
* Example Docs
|
||||
|
||||
The sample docs directory contains the following files:
|
||||
|
||||
- ~example-10k.html~ - A 10-K SEC filing in HTML format
|
||||
- ~layout-parser-paper.pdf~ - A PDF copy of the layout parser paper
|
||||
- ~factbook.xml~ / ~factbook.xsl~ - Example XML/XLS files that you
|
||||
can use to test stylesheets
|
||||
|
||||
These documents can be used to test out the parsers in the library. In
|
||||
addition, here are instructions for pulling in some sample docs that are
|
||||
too big to store in the repo.
|
||||
|
||||
** XBRL 10-K
|
||||
|
||||
You can get an example 10-K in inline XBRL format using the following
|
||||
~curl~. Note, you need to have the user agent set in the header or the
|
||||
SEC site will reject your request.
|
||||
|
||||
#+BEGIN_SRC bash
|
||||
|
||||
curl -O \
|
||||
-A '${organization} ${email}'
|
||||
https://www.sec.gov/Archives/edgar/data/311094/000117184321001344/0001171843-21-001344.txt
|
||||
#+END_SRC
|
||||
|
||||
You can parse this document using the HTML parser.
|
Loading…
Reference in New Issue