langchain/docs/modules/indexes/document_loaders/examples
leo-gan 36c59e0c25
Arxiv document loader (#3627)
It makes sense to use `arxiv` as another source of the documents for
downloading.
- Added the `arxiv` document_loader, based on the
`utilities/arxiv.py:ArxivAPIWrapper`
- added tests
- added an example notebook
- sorted `__all__` in `__init__.py` (otherwise it is hard to find a
class in the very long list)
2023-04-26 21:04:56 -07:00
..
example_data
airbyte_json.ipynb
apify_dataset.ipynb
arxiv.ipynb Arxiv document loader (#3627) 2023-04-26 21:04:56 -07:00
azlyrics.ipynb
azure_blob_storage_container.ipynb
azure_blob_storage_file.ipynb
bigquery.ipynb
bilibili.ipynb
blackboard.ipynb
blockchain.ipynb
chatgpt_loader.ipynb
college_confidential.ipynb
confluence.ipynb
CoNLL-U.ipynb
copypaste.ipynb
csv.ipynb
dataframe.ipynb
diffbot.ipynb
directory_loader.ipynb
discord_loader.ipynb
duckdb.ipynb
email.ipynb
epub.ipynb
evernote.ipynb
facebook_chat.ipynb
figma.ipynb
gcs_directory.ipynb
gcs_file.ipynb
git.ipynb
gitbook.ipynb
googledrive.ipynb
gutenberg.ipynb
hn.ipynb
html.ipynb
hugging_face_dataset.ipynb
ifixit.ipynb
image_captions.ipynb
image.ipynb
imsdb.ipynb
markdown.ipynb
notebook.ipynb
notion.ipynb
notiondb.ipynb
obsidian.ipynb
pdf.ipynb
powerpoint.ipynb
readthedocs_documentation.ipynb
roam.ipynb
s3_directory.ipynb
s3_file.ipynb
sitemap.ipynb
slack_directory.ipynb
srt.ipynb
telegram.ipynb
twitter.ipynb
unstructured_file.ipynb
url.ipynb
web_base.ipynb
whatsapp_chat.ipynb
word_document.ipynb
youtube.ipynb