DataStax announced a new integration with LangChain, the popular orchestration framework for developing applications with large language models (LLMs). The integration makes it easy to add Astra DB – the real-time database for developers building production Gen AI applications – or Apache Cassandra, as a new vector source in the LangChain framework. 

As companies implement retrieval augmented generation (RAG) – the process of providing context from outside data sources to deliver more accurate LLM query responses – into their generative AI applications, they require a vector store that provides real-time updates with zero latency on critical production workloads.

Generative AI applications built with RAG stacks require a vector-enabled database and an orchestration framework like LangChain to provide memory or context to LLMs for accurate and relevant answers. Developers use LangChain as an AI-first toolkit to connect their application to different data sources.

The integration lets developers leverage the Astra DB vector database for their LLM, AI assistant, and real-time generative AI projects through the LangChain plugin architecture for vector stores. Together, Astra DB and LangChain help developers to take advantage of framework features like vector similarity search, semantic caching, term-based search, LLM-response caching, and data injection from Astra DB (or Cassandra) into prompt templates.