langchain/tests/integration_tests/document_loaders
Matt Robinson 3637d6da6e
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()
```
2023-05-10 01:37:17 -07:00
..
parsers Add PDF parser implementations (#4356) 2023-05-09 10:24:17 -04:00
__init__.py
test_arxiv.py Arxiv document loader (#3627) 2023-04-26 21:04:56 -07:00
test_bigquery.py
test_bilibili.py Added bilibili loader (#2673) (#2724) 2023-04-11 10:40:32 -07:00
test_blockchain.py Enhancement: option to Get All Tokens with a single Blockchain Document Loader call (#3797) 2023-05-03 15:46:44 -07:00
test_bshtml.py Add get_text_separator parameter to BSHTMLLoader (#3551) 2023-04-26 16:10:16 -07:00
test_confluence.py Several confluence loader improvements (#3300) 2023-04-23 15:06:10 -07:00
test_dataframe.py
test_duckdb.py
test_email.py
test_facebook_chat.py Refactor TelegramChatLoader and FacebookChatLoader classes and add tests (#3863) 2023-05-03 15:59:19 -07:00
test_figma.py
test_gitbook.py
test_ifixit.py
test_json_loader.py JSON loader (#4067) 2023-05-05 14:48:13 -07:00
test_modern_treasury.py Dev2049/add modern treasury (#3924) 2023-05-01 20:28:02 -07:00
test_odt.py feat: add loader for open office odt files (#4405) 2023-05-10 01:37:17 -07:00
test_pdf.py Dev2049/pypdfium2 (#4209) 2023-05-05 17:55:31 -07:00
test_python.py Add PythonLoader which auto-detects encoding of Python files (#3311) 2023-04-21 10:47:57 -07:00
test_sitemap.py Add an option to extract more metadata from crawled websites (#4347) 2023-05-09 10:18:33 -07:00
test_slack.py Add Slack Directory Loader (#2841) 2023-04-13 21:31:59 -07:00
test_spreedly.py Harrison/spreedly (#3937) 2023-05-01 20:56:56 -07:00
test_stripe.py Dev2049/add modern treasury (#3924) 2023-05-01 20:28:02 -07:00
test_telegram.py Refactor TelegramChatLoader and FacebookChatLoader classes and add tests (#3863) 2023-05-03 15:59:19 -07:00
test_url_playwright.py Harrison/playwright selector (#3185) 2023-04-19 16:54:15 -07:00
test_url.py add continue to fix 'continue_on_failure' parameter for URL doc loader (#2735) 2023-04-11 21:12:39 -07:00
test_whatsapp_chat.py Update WhatsAppChatLoader to include the character ~ in the sender name (#4420) 2023-05-09 15:00:04 -07:00