Skip to content

Collections

Best Chain of Thought Episodes on RAG & Retrieval

Getting the right context to the model: chunking, vectors, graphs, and what breaks at scale.

Sudhir Hasbe explains where similarity search reaches its limits and what a knowledge graph can add. Richmond Alake connects retrieval to memory, and Fergal Reid describes Intercom’s experience with RAG. Maxime Labonne and Bob van Luijt cover retrieval models and the shift from a fixed retrieval pipeline to agent-directed fetching.

  • 5 episodes
  • 5 guests
  • 4 hours of listening
  • 3 jump-to moments
  1. 1 EP 55 52 min Transcript Hallucinations Are a Data Architecture Problem | Sudhir Hasbe, Neo4j Sudhir Hasbe, Neo4j Neo4j’s Sudhir Hasbe walks the standard pipeline end to end, chunk to embed to similarity search, then argues where it hits a ceiling and what a knowledge graph adds on top. The clearest explanation of the mechanism on the show. Jump to the moment · 12:09 · Where vector search stops →
  2. 2 EP 53 59 min Transcript Agent Memory: The Last Battleground in the AI Stack | Richmond Alake, Oracle Richmond Alake, Oracle Richmond Alake’s finding from building agent memory at Oracle: “vector search was not all you need… It was a very key component of what you needed, but it wasn’t all you need.” Retrieval strategy is what the memory layer rests on.
  3. 3 EP 49 54 min Transcript How Intercom Cut $250K/Month by Ditching GPT for Open Models | Fergal Reid Fergal Reid, Intercom Fergal Reid on running what he believes was one of the first production RAG deployments, launched on GPT-4 launch day, and what three years of iterating the chunking and context pipeline behind Fin taught them.
  4. 4 EP 43 53 min Transcript Beyond Transformers: How Liquid AI Is Rethinking LLM Architecture | Maxime Labonne Maxime Labonne, Liquid AI Maxime Labonne on the retrieval half nobody demos: the embedding models themselves, and why Liquid AI built a late-interaction ColBERT retriever rather than reaching for classic single-vector embeddings. Jump to the moment · 18:54 · Late-interaction retrieval →
  5. 5 EP 8 35 min Transcript AI Infrastructure & the Evolution of RAG | Weaviate's Bob van Luijt Bob van Luijt, Weaviate Weaviate’s Bob van Luijt on RAG’s original one-directional shape of query, retrieve, generate, and the moment agents turned it into a feedback loop where the model decides what to fetch next. Jump to the moment · 6:03 · From RAG to a feedback loop →

More collections

All collections →

New here? Start with five → Browse by topic →