Course Wiki

Module 2: Vector Search — LLM Zoomcamp

Lessons, materials, and key concepts for module 2 of LLM Zoomcamp.

LLM Zoomcamp > Module 2: Vector Search

Module 2: Vector Search

In this module, we extend the RAG pipeline from module 1 with vector search. Vector search matches documents by semantic meaning instead of exact keyword overlap. We start from embeddings and end with persistent vector indexes (sqlitesearch, PGVector) and ONNX-based embedders for lightweight deployments.

• Code: code/
• Embeddings runtime: embed/

Lessons

The lessons cover vector search end to end, from embeddings to persistent indexes.

1. What is Vector Search - Keyword search vs vector search, why it matters
2. Embeddings - Turning text into vectors with sent

Lessons

Key concepts

• OpenAI API
• RAG
• Hybrid Search
• Docker
• PostgreSQL
• PyTorch
• Keyword Search
• Vector Search
• Pandas
• Neural Networks
• Embeddings
• Jupyter Notebooks
• LLM Evaluation
• Prompt Engineering
• Reranking
• Partitioning and Clustering
• Classification Metrics
• Kafka
• Elasticsearch
• Model Deployment

Homework and deadlines live in the course repository: llm-zoomcamp.

Other modules in this course

• Module 1: Agentic RAG
• Module 3: Orchestration
• Module 4: Evaluation
• Module 5: Monitoring
• Module 6: Best Practices
• Module 7: End-to-End Project