Vector Databases
Not Started0 / 10 complete
Open a video or resource link, watch it, then check its box to track your progress and unlock what comes next.
10 lessons3 levels1 capstone project
Design vector retrieval systems: dense and sparse vectors, metadata filters, approximate-nearest-neighbor indexes, HNSW, recall/latency tradeoffs, hybrid search, persistence, scaling, and vector-store selection.
BASIC
- Vector Databases Explained: Complete Guide — Aishwarya Srinivasan (10 min)
Modern overview of vector stores, embeddings, indexing, retrieval, and use cases. - What Is a Vector Database? — IBM Technology (9 min)
Clear mental model for similarity search and why vector stores differ from relational databases. - Vector Databases Explained Hands-On Video — Data Science Dojo (30 min selected Time)
Adds ANN, indexing, architecture, and practical vector-search considerations. Build / Practice
INTERMEDIATE
- Production RAG Agent — Google Cloud
A deeper treatment of the same skill; use it to move from concept to working patterns. - What Is Retrieval-Augmented Generation (RAG)? — IBM Technology
Apply Vector Databases through the adjacent capability: Retrieval-Augmented Generation (RAG). - RAG From Scratch: Part 1 (Overview) — LangChain
Apply Vector Databases through the adjacent capability: Retrieval-Augmented Generation (RAG).
ADVANCED
- Learn RAG From Scratch — freeCodeCamp / LangChain
Extend Vector Databases into senior/production practice through Retrieval-Augmented Generation (RAG). - Build an MCP Server in 20 Minutes — pixegami
Extend Vector Databases into senior/production practice through Tool Use & Function Calling. - MCP Workshop — Anthropic
Extend Vector Databases into senior/production practice through AI Agents.