mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-21 00:35:23 -04:00
8effd90be0
- 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>
20 lines
637 B
Python
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",
|
|
]
|