S1:E5

Build a RAG-based Agent with MindsDB

Data PlatformAI
21 min

Host

Jonny DaenenJonny Daenen

Guest

Tarik JamoulleTarik Jamoulle

In this Technical Exploration, Jonny and Tarik show how to build a fully functioning RAG-based AI agent using MindsDB, turning internal data from Postgres, Slack, or Google Drive into a queryable knowledge base powered by semantic search.

Read transcript →

What you'll see

  • ▸Convert internal documents into a semantic knowledge base
  • ▸Make Google Drive & Slack data queryable in minutes
  • ▸Build a custom AI Agent on top of your knowledge bases
  • ▸Run MindsDB locally with Docker
  • ▸Use SQL to configure agents, connectors, and knowledge bases
  • ▸Expose your agent through a simple API for app integration
  • ▸Chunking & embedding strategies
  • ▸Local vs. cloud LLMs
  • ▸How MindsDB compares to full ETL approaches

Chapters

  1. 00:00Intro: What is MindsDB?
  2. 02:03Scope and dataset
  3. 03:08Quick tour: connectors & UI
  4. 06:34Components: Source, Knowledge Base & Agent
  5. 06:55Agent demo + how MindsDB queries data
  6. 08:36The code: getting MindsDB running
  7. 11:27Q&A: embedding times & creating your agent
  8. 14:03A Slack agent in 5 minutes
  9. 17:19Multi-knowledge-base agents
  10. 18:23Q: Integrating with SDK & MCP
  11. 19:31Takeaways

Tags

MindsDBNatural Language ProcessingAI AgentsKnowledge BaseSemantic SearchData QueryingOpen SourceSQLRAGData IntegrationChatbot

Listen on

Technologies

MindsDBSQL

Additional material