Series

RAG and Retrieval

Retrieval-augmented generation, embeddings, vector databases, re-ranking and knowledge graphs for AI memory.

26 episodes
  1. 1

    AI Memory vs. RAG: Building Long-Term Intelligence

    Explore why AI needs a "diary" and not just a "library" as we dive into the architectural differences between RAG and long-term agentic memory.

    23:03 · 4 Jan 2026
  2. 2

    Why Graph RAG Beats Flat Vectors for AI Memory

    Explore how the AI stack is evolving from simple vector search to complex Graph RAG and why the "boring" Postgres database is winning the race.

    24:42 · 8 Jan 2026
  3. 3

    The Vector DB Hangover: Scaling Without Going Broke

    Stop overpaying for your AI's memory. We break down the math of self-hosting vectors and the rise of serverless search.

    21:46 · 15 Mar 2026
  4. 4

    Giving AI a Brain: The Power of Knowledge Graphs

    Move beyond "stochastic parrots" with Knowledge Graphs. Discover how structured data is giving AI the logical backbone it needs to reason.

    24:34 · 20 Mar 2026
  5. 5

    The Hidden Cost of Choosing an Embedding Model

    From Matryoshka models to multimodal search, discover how the fundamental units of AI memory are being optimized for efficiency and scale.

    21:16 · 23 Mar 2026
  6. 6

    The Recall-Per-Dollar Era: Mastering Vector Database Tuning

    Stop burning money on unoptimized vector searches. We dive into HNSW tuning, distance metrics, and the vital "recall-per-dollar" metric.

    26:16 · 23 Mar 2026
  7. 7

    The Vector Debt Trap: Choosing Embeddings That Last

    Stop treating embedding models like plumbing. Learn how to navigate vector debt, multimodal retrieval, and database configuration for RAG.

    23:13 · 27 Mar 2026
  8. 8

    Context1: The Retrieval Coprocessor

    Chroma's new 20B model acts as a specialized "scout" for your LLM, replacing slow, static RAG with multi-step, agentic search.

    26:27 · 30 Mar 2026
  9. 9

    Google's Native Multimodal Embedding Kills the Fusion Layer

    Google’s new embedding model maps text, images, audio, and video into a single vector space—cutting latency by 70%.

    26:53 · 31 Mar 2026
  10. 10

    RAG Is Cheaper Than You Think (Until It’s Not)

    From a $1 embedding bill to a $10k/month vector database bill, here’s the real math behind RAG in 2026.

    21:53 · 31 Mar 2026
  11. 11

    Google Invented RAG's Secret Sauce

    Before LLMs, Google solved the "hallucination" problem with a two-stage trick that's making a huge comeback.

    28:07 · 2 Apr 2026
  12. 12

    When RAG Becomes an Agent

    RAG in chatbots is simple retrieval. RAG in agents is a multi-step decision loop. Here's what actually changes.

    29:04 · 12 Apr 2026
  13. 13

    Memory Without RAG: The Real Architecture

    mem0, Letta, Zep, and LangMem solve agent memory differently than RAG. Here's what's actually happening under the hood.

    28:08 · 13 Apr 2026
  14. 14

    Tuning RAG: When Retrieval Helps vs. Hurts

    How do you prevent retrieval from suppressing a model's reasoning? We diagnose our own pipeline's four control levers and multi-source fusion strat...

    24:15 · 15 Apr 2026
  15. 15

    Vector Search in a Single File

    What if you could do vector search with just SQLite? We explore sqlite-vec, the extension that adds embeddings to the world's simplest database, an...

    21:34 · 17 Apr 2026
  16. 16

    Embedding Model Deprecation: RAG's Silent Killer

    When OpenAI retires an embedding model, your RAG pipeline breaks silently. Here’s how to fix it.

    26:06 · 26 Apr 2026
  17. 17

    The Hidden Trap of Embedding Model Lock-In

    What happens when your vector database works great — until your embedding model gets deprecated and your vectors become useless.

    27:25 · 26 Apr 2026
  18. 18

    The Embedding Coupling Problem: Editing Vector Stores

    Can you edit or delete individual chunks in Pinecone? And can you actually back up a vector index? Yes—but with critical caveats.

    23:34 · 6 May 2026
  19. 19

    Vector Database Schema Design for AI Memory Layers

    Stop dumping vectors blindly. Design metadata schemas and namespaces for retrieval that actually works at scale.

    29:32 · 6 May 2026
  20. 20

    Live Retrieval vs. RAG: What an Agent Actually Does

    Does every AI conversation create a tiny vector store? We unpack the real tradeoffs between live document fetching and pre-indexed RAG.

    39:03 · 7 May 2026
  21. 21

    Knowledge Graphs vs SQL: How Custom Relationships Change Retrieval

    Why naming relationships (not just connecting data) transforms how you retrieve information.

    28:10 · 18 Jun 2026
  22. 22

    Source-Restricted vs. Open Retrieval: How to Lock Down Your LLM

    When should an LLM be locked to specific documents, and when should it search the web? A practical framework for grounding decisions.

    29:59 · 20 Jun 2026
  23. 23

    Embedding Models vs LLMs: What Actually Connects?

    Can you mix any embedding model with any LLM? And why are new embedding models still dropping if they're "solved"?

    27:02 · 4 Jul 2026
  24. 24

    Graph Engineering: AI Memory Beyond Retrieval

    How linked notes and knowledge graphs are turning AI agents from memory tools into discovery engines.

    21:28 · 7 Aug 2026
  25. 25

    Weighting Memory in a RAG Pipeline

    Daniel's memory leg won't fire. Turns out system prompts have no inherent vector-space privilege — but retrieval does have a real knob.

    35:02 · 10 Sept 2026
  26. 26

    Lorebooks: The Hobbyist RAG That Beat the Labs

    How a chat frontend fork built a full retrieval system — keywords, vectors, recursion — so fictional characters would stop forgetting who they are.

    30:52 · 8 Oct 2026