AI
Dance between dense and sparse embeddings: Enabling Hybrid Search in LangChain-Milvus
How to create and search multi-vector-store in langchain-milvus Ohad Eytan · Follow Published in Towards Data Science · 6 min read · 18 hours ago — This blog post was co-authored by Omri Levy and Ohad Eytan, as part of the work we have done in IBM Research Israel. Intro Recently, we — at IBM Research — needed to use hybrid search in the Milvus vector store. Since we were already using the LangChain framework,
Ohad Eytan
November 19, 2024