mirror of https://github.com/hwchase17/langchain
feat: add loader for open office odt files (#4405)
# ODF File Loader Adds a data loader for handling Open Office ODT files. Requires `unstructured>=0.6.3`. ### Testing The following should work using the `fake.odt` example doc from the [`unstructured` repo](https://github.com/Unstructured-IO/unstructured). ```python from langchain.document_loaders import UnstructuredODTLoader loader = UnstructuredODTLoader(file_path="fake.odt", mode="elements") loader.load() loader = UnstructuredODTLoader(file_path="fake.odt", mode="single") loader.load() ```pull/4144/head^2
parent
65f85af242
commit
3637d6da6e
Binary file not shown.
@ -0,0 +1,76 @@
|
|||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "markdown",
|
||||||
|
"id": "22a849cc",
|
||||||
|
"metadata": {},
|
||||||
|
"source": [
|
||||||
|
"## Unstructured ODT Loader\n",
|
||||||
|
"\n",
|
||||||
|
"The `UnstructuredODTLoader` can be used to load Open Office ODT files."
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "e6616e3a",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"from langchain.document_loaders import UnstructuredODTLoader"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 2,
|
||||||
|
"id": "a654e4d9",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"Document(page_content='Lorem ipsum dolor sit amet.', metadata={'source': 'example_data/fake.odt', 'filename': 'example_data/fake.odt', 'category': 'Title'})"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 2,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"loader = UnstructuredODTLoader(\"example_data/fake.odt\", mode=\"elements\")\n",
|
||||||
|
"docs = loader.load()\n",
|
||||||
|
"docs[0]"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "9ab94bde",
|
||||||
|
"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": 5
|
||||||
|
}
|
@ -0,0 +1,22 @@
|
|||||||
|
"""Loader that loads Open Office ODT files."""
|
||||||
|
from typing import Any, List
|
||||||
|
|
||||||
|
from langchain.document_loaders.unstructured import (
|
||||||
|
UnstructuredFileLoader,
|
||||||
|
validate_unstructured_version,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class UnstructuredODTLoader(UnstructuredFileLoader):
|
||||||
|
"""Loader that uses unstructured to load open office ODT files."""
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
||||||
|
):
|
||||||
|
validate_unstructured_version(min_unstructured_version="0.6.3")
|
||||||
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
||||||
|
|
||||||
|
def _get_elements(self) -> List:
|
||||||
|
from unstructured.partition.odt import partition_odt
|
||||||
|
|
||||||
|
return partition_odt(filename=self.file_path, **self.unstructured_kwargs)
|
@ -0,0 +1,12 @@
|
|||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
from langchain.document_loaders import UnstructuredODTLoader
|
||||||
|
|
||||||
|
|
||||||
|
def test_unstructured_odt_loader() -> None:
|
||||||
|
"""Test unstructured loader."""
|
||||||
|
file_path = Path(__file__).parent.parent / "examples/fake.odt"
|
||||||
|
loader = UnstructuredODTLoader(str(file_path))
|
||||||
|
docs = loader.load()
|
||||||
|
|
||||||
|
assert len(docs) == 1
|
Binary file not shown.
Loading…
Reference in New Issue