Build vector search: choose embedding models, set up vector databases (Pinecone, Weaviate, Qdrant, pgvector), implement hybrid search, and optimize recall vs latency.
When to use this skill
- Setting up a vector database
- Implementing semantic search
- Choosing an embedding model
Core concepts
This skill provides guidance on vector search best practices, patterns, and common pitfalls. It is designed to be loaded on demand when a relevant task is detected.
Installation
curl -LO https://opencode-skills.example/downloads/data/vector-search.zip
unzip vector-search.zip -d ~/.config/opencode/skills/Restart OpenCode — the skill loads automatically.
When it triggers
- setting up a vector database
- implementing semantic search
- choosing an embedding model