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>
This commit is contained in:
Jason Fan
2023-07-12 20:53:30 -07:00
committed by GitHub
parent f11d845dee
commit 8effd90be0
17 changed files with 985 additions and 6 deletions

View File

@@ -45,3 +45,13 @@ print(texts[1])
```
</CodeOutputBlock>
## Other transformations:
### Filter redundant docs, translate docs, extract metadata, and more
We can do perform a number of transformations on docs which are not simply splitting the text. With the
`EmbeddingsRedundantFilter` we can identify similar documents and filter out redundancies. With integrations like
[doctran](https://github.com/psychic-api/doctran/tree/main) we can do things like translate documents from one language
to another, extract desired properties and add them to metadata, and convert conversational dialogue into a Q/A format
set of documents.