skills.rest
ThaiG2Pro
ThaiG2ProCOMMUNITY
Explore all skills by this author →
GitHub

pgvector-semantic-search

Store embeddings in PostgreSQL with pgvector and run cosine-distance queries.

Updated Feb 3, 2026
Search Tags:#postgresql#pgvector#HNSW#semantic-search#vector-search#halfvec#cosine-distance
One-click install
npx skills add https://github.com/ThaiG2Pro/ai-agent-sale-v1 --skill pgvector-semantic-search-thaig2pro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pgvector-semantic-search
Source: https://github.com/ThaiG2Pro/ai-agent-sale-v1/tree/main/.gemini/skills/pgvector-semantic-search
Command: npx skills add https://github.com/ThaiG2Pro/ai-agent-sale-v1 --skill pgvector-semantic-search-thaig2pro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stores embeddings in PostgreSQL with pgvector and uses HNSW indexes to enable fast semantic search within the database, avoiding external inference bottlenecks.

Core Features & Use Cases

  • In-database vector storage using halfvec(N) to minimize storage overhead.
  • High-speed cosine-distance queries with HNSW indexing for scalable similarity search.
  • Use cases include content retrieval, product recommendations, and semantic search over text corpora.

Quick Start

Configure your database to enable the pgvector extension, create a vector column, index with HNSW, and run a sample cosine-distance nearest-neighbor query.

Frequently Asked Questions about pgvector-semantic-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic search in PostgreSQL using pgvector?▼

Semantic search in PostgreSQL uses pgvector to store embeddings and perform cosine-distance queries. You enable the extension, add a vector column, and query using nearest-neighbor operators to find similar content.

What is the best way to scale vector search queries in a PostgreSQL database?▼

Scaling vector search in PostgreSQL relies on creating HNSW indexes on your vector columns. HNSW indexing accelerates cosine-distance queries, enabling fast similarity matching across large text corpora or product catalogs.

Can I use half precision vectors with pgvector to reduce storage overhead?▼

Yes, pgvector supports in-database vector storage using halfvec(N) to minimize storage overhead. This allows you to store half-precision embeddings directly in PostgreSQL while maintaining semantic search capabilities.

How do I set up HNSW indexing for cosine distance queries?▼

To set up HNSW indexing for cosine distance queries, enable the pgvector extension, create a vector column, and apply the HNSW index. This configuration supports high-speed nearest-neighbor queries for similarity search.

Does pgvector work for product recommendations and content retrieval?▼

Yes, pgvector is designed for database-centric applications needing scalable in-database vector search. It handles content retrieval, product discovery, and similarity-based recommendations directly within PostgreSQL.

Related Skills

Explore More Software Engineering Skills→
1lastphoenix1lastphoenix
7

pgvector-semantic-search

Store embeddings in PostgreSQL and query them via nearest-neighbor distance.

Community
Advanced
wshobsonwshobson
38.6k

similarity-search-patterns

Implement similarity search patterns with Pinecone, Qdrant, pgvector, and Weaviate.

Community
Advanced
FalkorDBFalkorDB
22

Create and query vector indexes

Create and query HNSW vector indexes in FalkorDB graph databases.

Official
Intermediate
DrLuggelsDrLuggels
3

similarity-search-patterns

Provide patterns for similarity search with vector databases like Pinecone and Qdrant.

Community
Advanced