You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/langchain/document_loaders
blob42 14d0e0ee41 fix: ReadTheDocs loader main content filter 1 year ago
..
__init__.py Removed duplicate BaseModel dependencies (#2471) 1 year ago
airbyte_json.py Harrison/airbyte (#989) 1 year ago
apify_dataset.py Harrison/apify (#2215) 1 year ago
azlyrics.py clean up loaders (#1178) 1 year ago
azure_blob_storage_container.py Added Azure Blob Storage File and Container Loader (#1890) 1 year ago
azure_blob_storage_file.py Added Azure Blob Storage File and Container Loader (#1890) 1 year ago
base.py Harrison/unstructured support (#903) 1 year ago
bigquery.py Harrison/big query (#2100) 1 year ago
blackboard.py hotfix (#1742) 1 year ago
college_confidential.py clean up loaders (#1178) 1 year ago
conllu.py add CoNLL-U document loader (#1297) 1 year ago
csv_loader.py Allow passing in encoding to csv_loader (#1836) 1 year ago
dataframe.py rm pandas dependency (#2102) 1 year ago
directory.py Add ability to pass kwargs to loader classes in `DirectoryLoader`, add ability to modify encoding and BeautifulSoup behaviour in `BSHTMLLoader` (#2275) 1 year ago
duckdb_loader.py Harrison/duckdb (#2064) 1 year ago
email.py fix: pass unstructured kwargs down in all unstructured loaders (#2506) 1 year ago
epub.py fix: pass unstructured kwargs down in all unstructured loaders (#2506) 1 year ago
evernote.py Update and rename everynote.py to evernote.py (#1060) 1 year ago
facebook_chat.py Harrison/fb loader (#1277) 1 year ago
figma.py Harrison/figma doc loader (#1908) 1 year ago
gcs_directory.py Harrison/add roam loader (#939) 1 year ago
gcs_file.py Harrison/add roam loader (#939) 1 year ago
gitbook.py Gitbook enhancements (#2279) 1 year ago
googledrive.py Add shared Google Drive folder support (#2562) 1 year ago
gutenberg.py gutenberg books (#946) 1 year ago
hn.py Refactor some loops into list comprehensions (#1185) 1 year ago
html.py feat: allow the unstructured kwargs to be passed in to Unstructured document loaders (#1667) 1 year ago
html_bs.py Add ability to pass kwargs to loader classes in `DirectoryLoader`, add ability to modify encoding and BeautifulSoup behaviour in `BSHTMLLoader` (#2275) 1 year ago
ifixit.py Harrison/ifixit (#1680) 1 year ago
image.py feat: allow the unstructured kwargs to be passed in to Unstructured document loaders (#1667) 1 year ago
imsdb.py clean up loaders (#1178) 1 year ago
markdown.py fix: pass unstructured kwargs down in all unstructured loaders (#2506) 1 year ago
notebook.py fix imports (#1288) 1 year ago
notion.py Harrison/unstructured support (#903) 1 year ago
notiondb.py feat: Add Notion database document loader (#2056) 1 year ago
obsidian.py add encoding parameter to ObsidianLoader (#1752) 1 year ago
pdf.py add missing `source` field to pymupdf output (#2110) 1 year ago
powerpoint.py feat: allow the unstructured kwargs to be passed in to Unstructured document loaders (#1667) 1 year ago
readthedocs.py fix: ReadTheDocs loader main content filter 1 year ago
roam.py Harrison/add roam loader (#939) 1 year ago
s3_directory.py Harrison/add roam loader (#939) 1 year ago
s3_file.py Support S3 Object keys with `/` in `S3FileLoader` (#1517) 1 year ago
sitemap.py sitemap more flexible (#2214) 1 year ago
srt.py add srt loader (#1140) 1 year ago
telegram.py fix telegram imports (#1110) 1 year ago
text.py Add encoding parameter to TextLoader (#2250) 1 year ago
unstructured.py feat: allow the unstructured kwargs to be passed in to Unstructured document loaders (#1667) 1 year ago
url.py fix: pass unstructured kwargs down in all unstructured loaders (#2506) 1 year ago
url_selenium.py Introduces SeleniumURLLoader for JavaScript-Dependent Web Page Data Retrieval (#2291) 1 year ago
web_base.py Harrison/gitbook (#2044) 1 year ago
whatsapp_chat.py Fix WhatsAppChatLoader regex pattern for 24 hour time format (#2458) 1 year ago
word_document.py feat: allow the unstructured kwargs to be passed in to Unstructured document loaders (#1667) 1 year ago
youtube.py Harrison/subtitles (#1842) 1 year ago