DEVOPSdigest

DataStax announced a new integration with Airbyte that simplifies the process of building production-ready GenAI applications with structured and unstructured data.

With the new DataStax integration, developers are able to ingest data from those sources, vectorize the data with the embedding model of their choice, and ingest and index the data and vectors into Astra DB. This dramatically simplifies and speeds up the process of building RAG (retrieval augmented generation) applications, and freeing up developers to focus on building amazing AI experiences for their end users.

Developers can also use the AirByte integration with RAGStack, an out of the box solution that includes the best open-source for implementing RAG, giving enterprise developers a supported, one-stop GenAI Stack leveraging LangChain, LLamaIndex, and more.

“We enable developers to replicate data from the most comprehensive catalog of connectors in the industry,” said Michel Tricot, co-founder and CEO, Airbyte. “Our partnership with DataStax lets our users streamline their RAG application development cycles and provides access to one of the leading vector databases. We’re always looking for opportunities to innovate and provide our users with access to leading GenAI products in the market.”

“The process of data ingest and embedding creation can be long and complex for developers building GenAI applications,” said Ed Anuff, chief product officer, DataStax. “By enabling Airbyte users to easily index vectorized data into Astra DB we’re opening the door to the more than 40,000 engineers that use their platform to easily connect and integrate data from a wide array of sources into the best vector database for building production GenAI applications.”