RAGStack Documentation

What is RAGStack?

RAGStack is a curated stack of the best open-source software for easing implementation of the RAG pattern in production-ready applications using Astra DB Serverless or Apache Cassandra as a vector store.

A single command (pip install ragstack-ai) unlocks all the open-source packages required to build production-ready RAG applications with LangChain and the vector-enabled Astra DB Serverless database.

For each open-source project included in RAGStack, we select a version lineup and then test the combination for compatibility, performance, and security. Our extensive test suite ensures that RAGStack components work well together so you can confidently deploy them in production. We also run security scans on all components using industry-standard tools to ensure that you are not exposed to known vulnerabilities.

If you are already using an open-source library that is part of RAGStack in your project, such as LangChain, it should be easy to switch it to RAGStack by simply updating the requirements.


DataStax has been busy helping our customers through the pains of RAG implementation, so the RAGStack components we’ve selected have withstood production workloads and stringent testing by our engineering teams for performance, compatibility, and security.

  • RAGStack leverages the LangChain ecosystem and is fully compatible with LangSmith for monitoring your AI deployments.

  • The Astra DB Serverless database provides the best performance and scalability for RAG applications, in addition to being particularly well-suited to RAG workloads like question answering, semantic search, and semantic caching.

Why RAGStack?

RAGStack offers solutions for challenges facing developers building RAG applications.

  • Productivity — abstract over the RAG pattern’s complexities to keep developers focused on business logic.

  • Advanced RAG techniques — use advanced patterns like RAG fusion and FLARE.

  • Future-proof — as new techniques are discovered, RAGStack offers enterprise users a predictable upgrade path to always be on the cutting edge of AI.

  • Performance, scalability, cost — cache a large percentage of AI calls and leverage the inherent parallelism built into Astra DB.

  • Enterprise governance and compliance - backed with enterprise support and SLAs, and offering support for HIPAA, TRUSTe, and SOC2 when running in Astra DB.

Get started

Was this helpful?

Give Feedback

How can we improve the documentation?

© 2024 DataStax | Privacy policy | Terms of use

Apache, Apache Cassandra, Cassandra, Apache Tomcat, Tomcat, Apache Lucene, Apache Solr, Apache Hadoop, Hadoop, Apache Pulsar, Pulsar, Apache Spark, Spark, Apache TinkerPop, TinkerPop, Apache Kafka and Kafka are either registered trademarks or trademarks of the Apache Software Foundation or its subsidiaries in Canada, the United States and/or other countries. Kubernetes is the registered trademark of the Linux Foundation.

General Inquiries: +1 (650) 389-6000, info@datastax.com