Files
langchain-python/langchain/document_transformers/__init__.py
T
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

20 lines
637 B
Python

from langchain.document_transformers.doctran_text_extract import (
DoctranPropertyExtractor,
)
from langchain.document_transformers.doctran_text_qa import DoctranQATransformer
from langchain.document_transformers.doctran_text_translate import DoctranTextTranslator
from langchain.document_transformers.embeddings_redundant_filter import (
EmbeddingsClusteringFilter,
EmbeddingsRedundantFilter,
get_stateful_documents,
)
__all__ = [
"DoctranQATransformer",
"DoctranTextTranslator",
"DoctranPropertyExtractor",
"EmbeddingsClusteringFilter",
"EmbeddingsRedundantFilter",
"get_stateful_documents",
]