Building RAG at scale with Semantic Kernel and DataStax Astra DB
summary
Live demo builds a real-time RAG chatbot called WikiCh.at demo that ingests the top 1,000 Wikipedia pages, listens to the change log, generates embeddings for edits, stores vectors in Astra DB, runs approximate nearest neighbor retrieval and feeds results to Azure OpenAI via Microsoft Semantic Kernel. Code shows a Colab notebook, a JSON API token and database ID, an Astra DB memory connector, three lines to wire memory, and a successful query returning a factual answer.
AI-written summary · about
chapters (6)
- 0:00Introduction to RAG
- 0:42RAG concepts and architecture
- 3:13Real-world RAG examples
- 6:19Semantic Kernel setup
- 9:11Building the RAG application
- 12:32Conclusion and resources
related talks
20mProduction RAG apps made easier with Astra
31mSponsored Session: Building a Production Open Source RAG Application using LlamaIndex and Cassandra
01h 36mTutorial: From Planni...
53mBuild RAG from Scratch
44mThe RAG Really Ties the App Together
25mLets Build A Node.js ChatGPT-Like Bot With AI APIs
44mBuild RAG from Scratch
45mManaging Data & Analytics Projects Effectively