Follow Datanami:
June 12, 2024

Elastic Adds Vector Database and Broad Retrieval Capabilities to LangChain

SAN FRANCISCO, Calif., June 12, 2024 — Elastic (NYSE: ESTC), the Search AI Company, today announced a partner integration package with LangChain that will simplify the import of vector database and retrieval capabilities of Elasticsearch into LangChain applications. This deeper collaboration and native support will empower developers to leverage common retrieval strategies to bring greater context, relevancy, and accuracy to their application builds.

“Our collaboration with Elastic in the last 12 months has been exceptional, particularly as we establish better ways for developers and end users to build RAG applications from prototype to production,” said Harrison Chase, co-founder and CEO at LangChain. “The LangChain-Elasticsearch vector database integrations will help do just that, and we’re excited to see this partnership grow with future feature and integration releases.”

“Elasticsearch is being used as a vector database, for hybrid search, and as a powerful engine for retrieval augmented generation (RAG), and LangChain is the de facto orchestration library for these use cases,” said Shay Banon, co-founder and chief technology officer at Elastic. “As GenAI continues to evolve at a breakneck speed, we’ll continue to work closely with the LangChain team to ensure the latest Elasticsearch enhancements are available to all users in the global LangChain ecosystem.”

Elastic has also taken ownership of the code and release process through a dedicated repository. For more information on the partnership and integration package, read the Elastic blog.

Source: Elastic