Matt Robinson 3dfe1cf60e feat: document loader for epublications (#2202) ...

### Summary

Adds a new document loader for processing e-publications. Works with
`unstructured>=0.5.4`. You need to have
[`pandoc`](https://pandoc.org/installing.html) installed for this loader
to work.

### Testing

```python
from langchain.document_loaders import UnstructuredEPubLoader

loader = UnstructuredEPubLoader("winter-sports.epub", mode="elements")
data = loader.load()
data[0]
```

2023-03-30 20:45:31 -07:00

..

example_data

Harrison/whatsapp loader (#2085)

2023-03-27 23:43:45 -07:00

airbyte_json.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

azlyrics.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

azure_blob_storage_container.ipynb

Harrison/site map (#2061)

2023-03-27 16:28:08 -07:00

azure_blob_storage_file.ipynb

Harrison/site map (#2061)

2023-03-27 16:28:08 -07:00

bigquery.ipynb

Harrison/big query (#2100)

2023-03-28 08:17:22 -07:00

blackboard.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

college_confidential.ipynb

Harrison/site map (#2061)

2023-03-27 16:28:08 -07:00

CoNLL-U.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

copypaste.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

csv.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

dataframe.ipynb

Harrison/document cleanup (#2062)

2023-03-27 16:32:55 -07:00

directory_loader.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

duckdb.ipynb

Harrison/duckdb (#2064)

2023-03-27 19:51:34 -07:00

email.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

evernote.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

facebook_chat.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

figma.ipynb

[Documents] Updated Figma docs and added example (#2172)

2023-03-29 22:11:45 -07:00

gcs_directory.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

gcs_file.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

gitbook.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

googledrive.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

gutenberg.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

hn.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

html.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

ifixit.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

image.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

imsdb.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

markdown.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

notebook.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

notion.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

notiondb.ipynb

feat: Add Notion database document loader (#2056)

2023-03-28 08:07:09 -07:00

obsidian.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

pdf.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

powerpoint.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

readthedocs_documentation.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

roam.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

s3_directory.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

s3_file.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

sitemap.ipynb

docs: tiny fix on docs verbiage (#2124)

2023-03-28 22:56:29 -07:00

srt.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

telegram.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

unstructured_file.ipynb

feat: document loader for epublications (#2202)

2023-03-30 20:45:31 -07:00

url.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

web_base.ipynb

Harrison/site map (#2061)

2023-03-27 16:28:08 -07:00

whatsapp_chat.ipynb

Harrison/whatsapp loader (#2085)

2023-03-27 23:43:45 -07:00

word_document.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00

youtube.ipynb

big docs refactor (#1978)

2023-03-26 19:49:46 -07:00