mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-16 06:53:16 +00:00
83586661d6
This PR adds an additional method to `Chroma` to retrieve the embedding vectors, besides the most relevant Documents. This is sometimes of use when you need to run a postprocessing algorithm on the retrieved results based on the vectors, which has been the case for me lately. Example issue (discussion) requesting this change: https://github.com/langchain-ai/langchain/discussions/20383 --------- Co-authored-by: ccurme <chester.curme@gmail.com>
langchain-chroma
This package contains the LangChain integration with Chroma.
Installation
pip install -U langchain-chroma
Usage
The Chroma class exposes the connection to the Chroma vector store.
from langchain_chroma import Chroma
embeddings = ... # use a LangChain Embeddings class
vectorstore = Chroma(embeddings=embeddings)