You're viewing version 2.19 of the OpenSearch documentation. For the latest version, see the current documentation. For information about OpenSearch version maintenance, see Release Schedule and Maintenance Policy.

LLM framework integration

Several popular large language model (LLM) frameworks integrate with OpenSearch as a vector store, enabling you to build production-ready generative AI applications. These frameworks provide high-level abstractions and tools for working with LLMs, and their OpenSearch integrations allow you to use OpenSearch for efficient vector storage, retrieval, and similarity search:

• LangChain
  • Semantic cache
  • Vector store support
• LlamaIndex
  • Vector store support
• FlowiseAI:
  • Vector store support
• Langflow:
  • Vector store support
• Haystack:
  • Vector store support