mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-04 19:35:08 +00:00
b5d670498f
# Description Milvus (and `pymilvus`) recently added the option to use [sparse vectors](https://milvus.io/docs/sparse_vector.md#Sparse-Vector) with appropriate search methods (e.g., `SPARSE_INVERTED_INDEX`) and embeddings (e.g., `BM25`, `SPLADE`). This PR allow creating a vector store using langchain's `Milvus` class, setting the matching vector field type to `DataType.SPARSE_FLOAT_VECTOR` and the default index type to `SPARSE_INVERTED_INDEX`. It is only extending functionality, and backward compatible. ## Note I also interested in extending the Milvus class further to support multi vector search (aka hybrid search). Will be happy to discuss that. See [here](https://github.com/langchain-ai/langchain/discussions/19955), [here](https://github.com/langchain-ai/langchain/pull/20375), and [here](https://github.com/langchain-ai/langchain/discussions/22886) similar needs. --------- Co-authored-by: Erick Friis <erick@langchain.dev>
langchain-milvus
This is a library integration with Milvus and Zilliz Cloud.
Installation
pip install -U langchain-milvus
Milvus vector database
See a usage example
from langchain_milvus import Milvus
Milvus hybrid search
See a usage example.
from langchain_milvus import MilvusCollectionHybridSearchRetriever
Zilliz Cloud vector database
See a usage example.
from langchain_milvus import Zilliz
Zilliz Cloud Pipeline Retriever
See a usage example.
from langchain_milvus import ZillizCloudPipelineRetriever