Perform semantic similarity search with pgvector. Use when asked to "search similar documents", "find related content", "semantic search", "vector search", or when implementing the retrieval phase of RAG pipelines.
Quickly install pgvector-similarity-search AI skill to your development environment via command line
Source: constructive-io/constructive-skills.
Query vector embeddings using pgvector's similarity operators. This skill covers the retrieval phase of RAG pipelines.
| | Cosine distance | Most common, normalized vectors | | | Euclidean (L2) | When magnitude matters | | | Inner product | Dot product similarity |
Cosine distance is recommended for text embeddings as it measures angle between vectors, ignoring magnitude.
Perform semantic similarity search with pgvector. Use when asked to "search similar documents", "find related content", "semantic search", "vector search", or when implementing the retrieval phase of RAG pipelines. Source: constructive-io/constructive-skills.
Stable fields and commands for AI/search citations.
npx skills add https://github.com/constructive-io/constructive-skills --skill pgvector-similarity-searchPerform semantic similarity search with pgvector. Use when asked to "search similar documents", "find related content", "semantic search", "vector search", or when implementing the retrieval phase of RAG pipelines. Source: constructive-io/constructive-skills.
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/constructive-io/constructive-skills --skill pgvector-similarity-search Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code, Cursor, or OpenClaw
https://github.com/constructive-io/constructive-skills