Course Wiki

Vector Search

Nearest-neighbor retrieval over embedding vectors — semantic search that matches meaning, not just words.

Vector search retrieves documents by the closeness of their embedding vectors to the query’s vector. Because the vectors encode meaning, a question about ‘how do I reset my password’ can retrieve a document that says ‘change your credentials’ without either sharing keywords. Module 2 implements it three ways in the course: minsearch (an in-memory approach), sqlitesearch, and PGVector for Postgres.

The module also teaches the operational layer: indexing the whole knowledge base, querying efficiently, and combining scores. It is the retrieval engine for the RAG pipeline — and, via the hybrid-search module, half of an even stronger combined retriever.

Taught in

• LLM Zoomcamp

  • Module 1: Agentic RAG
    • Environment
    • RAG
    • Search
    • The LLM
    • RAG Helper
    • Data Ingestion
    • Wrap-up of Part 1
    • Agents
    • Quick RAG Revision (Optional)
  • Module 2: Vector Search
    • Vector Search
    • Embeddings
    • Vector Search
    • Vector Search with minsearch
    • RAG with Vector Search
    • Vector Search with sqlitesearch
    • Vector Search with PGVector
    • Using ONNX Runtime instead of PyTorch
    • Next Steps
  • Module 3: Orchestration
    • Retrieval Augmented Generation
  • Module 4: Evaluation
    • Evaluation
    • Search Evaluation
  • Module 5: Monitoring
    • Next Steps
  • Module 6: Best Practices
    • Best Practices for RAG
    • Hybrid Search
    • Hybrid Search with LangChain
    • Next Steps
  • Module 7: End-to-End Project
    • End-to-End Project Example
    • Interface and Ingestion Pipeline
    • Summary and Closing Remarks ## Related concepts

• Embeddings

• RAG

• Hybrid Search

• Keyword Search

• Agentic RAG