DataStax announced the launch of RAGStack, an out-of-the-box RAG solution designed to simplify implementation of retrieval augmented generation (RAG) applications built with LangChain. RAGStack reduces the complexity and overwhelming choices that developers face when implementing RAG for their generative AI applications with a streamlined, tested, and efficient set of tools and techniques for building with LLMs. 

With RAGStack, companies benefit from a preselected set of open-source software for implementing generative AI applications, providing developers with a ready-made solution for RAG that leverages the LangChain ecosystem including LangServe, LangChain Templates and LangSmith, along with Apache Cassandra and the DataStax Astra DB vector database. This removes the hassle of having to assemble a bespoke solution and provides developers with a simplified, comprehensive generative AI stack. 

RAG combines the strengths of both retrieval-based and generative AI methods for natural language understanding and generation, enabling real-time, contextually relevant responses that underpin much of the innovation happening with this technology.

With specifically curated software components, abstractions to improve developer productivity and system performance, enhancements that improve existing vector search techniques, and compatibility with most generative AI data components, RAGStack provides overall improvements to the performance, scalability, and cost of implementing RAG in generative AI applications.

https://www.datastax.com/products/ragstack

Cloudera, Inc., a data company for enterprise artificial intelligence (AI), and Pinecone, a vector database company providing long-term memory for AI, announced a strategic partnership that integrates Pinecone’s AI vector database expertise into Cloudera’s open data platform, aimed to help organizations use AI to streamline operations and improve customer experiences.

Pinecone is optimized to store AI representations of data (vector embeddings) and search through them by semantic similarity. This capability is necessary for adding context to queries against applications that use Large Language Models (LLMs) to reduce erroneous outputs and helps search and Generative AI applications deliver more accurate and relevant responses.

Pinecone’s vector database will also be integrated into Cloudera Data Platform (CDP), and includes the release of a new Applied ML Prototype (AMP) that will allow developers to more quickly create and augment new knowledge bases from data on their own website, as well as pre-built connectors that will enable customers to quickly set up ingest pipelines in AI applications.

Customers can use this same architecture to set up or improve support chatbots or internal support search systems to reduce operational costs and improve customer experience by decreasing human case-handling efforts and faster resolution times.

https://www.cloudera.com ■ https://www.pinecone.io