DataStax is making quite a few enhancements to its growth platform that can permit builders to extra simply implement retrieval augmented technology (RAG) of their generative AI purposes.
“The Generative AI stack is a giant and sophisticated ball of know-how that many are working to get their arms round. We’re targeted on serving to builders keep true to their roots to allow them to do what they do finest: construct and develop, fairly than worrying about software infrastructure. We’re delivering a cutting-edge, end-to-end stack to make this so much simpler,” stated Ed Anuff, chief product officer at DataStax.
The corporate is releasing Langflow 1.0, the latest model of the visible framework for constructing RAG purposes, which DataStax acquired again in April. This replace contains dozens of integrations with different generative AI instruments, together with LangChain, LangSmith, OpenAI, Hugging Face, and Mistral. It additionally features a cloud-hosted model of Langflow inside DataStax Cloud and entry to LangSmith’s observability capabilities.
DataStax additionally introduced RAGStack 1.0. RAGStack is an out-of-the-box resolution that features varied instruments wanted to implement RAG.
RAGStack 1.0 contains assist for Langflow, a data graph designed for generative AI, ColBERT powered by Astra DB, Text2SQL and Text2CQL, and Vectorize, which is a device that lets builders select their embedding service.
The corporate can be demoing these new updates at its RAG++ occasion in San Francisco tonight.
You may additionally like…
RAG is the following thrilling development for LLMs
Protected AI growth: Integrating explainability and monitoring from the beginning
