IT Brief New Zealand - Technology news for CIOs & IT decision-makers
Story image
DataStax rolls out RAGStack, an all-new Gen AI data solution
Mon, 26th Feb 2024

DataStax, the Gen AI data firm, has announced that its retrieval augmented generation (RAG) solution, known as RAGStack, is now broadly available. This innovative solution is powered by LlamaIndex, an open-source framework, and also LangChain.

The new RAGStack specifically designed for LlamaIndex is a first in the industry to support integration with LlamaIndex's LlamaParse, currently in public preview. This integration provides Astra DB developers with a simplified API, enabling efficient parsing and transformation of intricate PDF documents into vectors in a matter of minutes.

LlamaIndex focuses on ingesting, indexing, and querying data for developing generative AI applications whilst tackling ingestion pipelines necessary for enterprise-ready RAG. Introduced as a new offering from LlamaIndex, LlamaParse caters to enterprise developers crafting RAG for complex PDF files by facilitating immaculate table extraction via recursive retrieval, promising highly accurate parsing of typically complex business documents.

RAGStack combined with LlamaIndex offers developers a comprehensive solution that addresses challenges prevalent in implementing RAG solutions in enterprise applications. Significant benefits of this solution include Python distribution curated for Astra DB, DataStax Enterprise (DSE), and Apache Cassandra, a live RAGStack test matrix, and tried-and-tested GenAI app templates. With enhanced indexing and parsing capabilities, users can effortlessly deploy LlamaIndex alone, or in combination with LangChain.

Jerry Liu, Co-founder and CEO of LlamaIndex, commented on the partnership, "We are excited to be working with DataStax to streamline the implementation process of RAG techniques. Together, we're reshaping the RAG landscape by offering a simplified journey for not only enterprises but also developers looking to put GenAI applications into production with ease. This collaboration embodies our commitment to simplicity, innovation, and limitless possibilities."

As part of this collaboration, Imprompt, a leading digital interaction platform, will integrate Astra DB from DataStax as their primary vector store. CEO at Imprompt, Jeff Schneider, commented on this integration, "With RAGStack powered by LlamaIndex, we enhance enterprise offerings while prioritising privacy. Our integration with RAGStack enables secure data exchange, powering innovation for global enterprises."

The CTO and Executive Vice President at DataStax, Davor Bonaci, further emphasized the importance of this integration, stating, "Out-of-the-box RAG solutions are in high demand, so this integration is a significant milestone for our enterprise developers seeking to implement generative AI applications. By incorporating LlamaIndex into RAGStack, we are providing developers with a comprehensive GenAI stack that simplifies the complexities of RAG implementation, while offering long-term support and compatibility assurance."

An informative event detailing further about the integration is scheduled for March 12, where LlamaIndex and Imprompt will guide audiences on the utilization of LlamaIndex and LlamaParse with Astra DB.