Unlock the power of similarity search with vectors in this episode of Memriq Inference Digest – Engineering Edition. We explore how dense and sparse vector techniques combine to enable scalable, accurate semantic retrieval for AI systems, inspired by Chapter 8 of Keith Bourne’s book. Join us and special guest Keith Bourne as we unpack the engineering trade-offs, indexing algorithms, hybrid search strategies, and real-world applications that make vector search foundational in modern AI workflows.

In this episode:

- The fundamentals of representing data as high-dimensional embeddings and retrieving nearest neighbors

- How hybrid search fuses dense semantic embeddings with sparse keyword vectors to boost relevance

- Deep dive into Approximate Nearest Neighbor algorithms like HNSW for billion-scale indexing

- Practical considerations between open-source models and managed vector stores

- Engineering tips on tuning ANN parameters, persistence, and combining retrieval results with Reciprocal Rank Fusion

- Real-world use cases in enterprise search, recommendation engines, and retrieval-augmented generation systems

Key tools and technologies mentioned:

- sentence_transformers (e.g., all-mpnet-base-v2)

- BM25Retriever

- LangChain and Chroma

- FAISS, HNSW, ANNOY

- Reciprocal Rank Fusion (RRF)

- Pinecone, Weaviate, Google Vertex AI Vector Search

Timestamps:

0:00 - Introduction and episode overview

2:00 - The power of hybrid search: dense + sparse vectors

5:30 - ANN algorithms and indexing techniques (HNSW, LSH)

9:00 - Trade-offs: open-source embeddings vs commercial APIs

11:30 - Reciprocal Rank Fusion and ranking strategies

14:00 - Engineering challenges: persistence, tuning, and latency

16:30 - Real-world applications and production system considerations

19:00 - Final thoughts and resources

Resources:

- "Unlocking Data with Generative AI and RAG" by Keith Bourne - Search for 'Keith Bourne' on Amazon and grab the 2nd edition

- Visit Memriq.ai for advanced AI engineering guides and resources

Thanks for tuning into Memriq Inference Digest – Engineering Edition. Stay sharp, and see you next time!