langchain/docs/snippets/modules/data_connection
Jason Fan 8effd90be0
Add new types of document transformers (#7379)
- Description: Add two new document transformers that translates
documents into different languages and converts documents into q&a
format to improve vector search results. Uses OpenAI function calling
via the [doctran](https://github.com/psychic-api/doctran/tree/main)
library.
  - Issue: N/A
  - Dependencies: `doctran = "^0.0.5"`
  - Tag maintainer: @rlancemartin @eyurtsev @hwchase17 
  - Twitter handle: @psychicapi or @jfan001

Notes
- Adheres to the `DocumentTransformer` abstraction set by @dev2049 in
#3182
- refactored `EmbeddingsRedundantFilter` to put it in a file under a new
`document_transformers` module
- Added basic docs for `DocumentInterrogator`, `DocumentTransformer` as
well as the existing `EmbeddingsRedundantFilter`

---------

Co-authored-by: Lance Martin <lance@langchain.dev>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2023-07-12 23:53:30 -04:00
..
document_loaders codespell: workflow, config + some (quite a few) typos fixed (#6785) 2023-07-12 16:20:08 -04:00
document_transformers Add new types of document transformers (#7379) 2023-07-12 23:53:30 -04:00
retrievers codespell: workflow, config + some (quite a few) typos fixed (#6785) 2023-07-12 16:20:08 -04:00
text_embedding Polish reference docs (#7045) 2023-07-02 08:08:51 -06:00
vectorstores Polish reference docs (#7045) 2023-07-02 08:08:51 -06:00