Sponsored Session: Building a Production Open Source RAG Application using LlamaIndex and Cassandra
summary
Datastax shows a working knowledge-retrieval chatbot built with LlamaIndex and Astra as the vector store, integrated with Intercom and Slack, and released as an open source repo with a Gitpod demo. The repo has ~5–6k GitHub stars, runs embeddings via OpenAI (beware exposed keys), and uses production tactics: chunking, small to big retrieval, reranking, and chain-of-thought examples. Scalability to millions of docs is still work in progress, but the app is live and used.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 3:30What RAG is and why it matters
- 7:44RAG in practice
- 10:11Live demo: production RAG app
- 14:43Production RAG challenges
- 17:09Advanced RAG strategies
- 23:29Q&A
related talks
48mUnlocking LLM Potential: From Exploration to Integration
20mProduction RAG apps made easier with Astra
14mBuilding RAG at scale with Semantic Kernel and DataStax Astra DB
01h 12mBuild RAG using Llama 3.1
42mTake Your RAG To The Max!
44mThe RAG Really Ties the App Together
40mRolling out Enterprise AI: Tools, Insights, & Team Empowerment
42mUsing LlamaIndex for building Generative AI apps