PGVector Semantic Search

PGVector Semantic Search is an AI Engineering skill for Claude Code, published by timescale in pg-aiguide.

1.8K stars104 forkson timescale/pg-aiguideAdded 2026/08/18Repository updated 2026/06/26

aiai-agentsai-codingclaude-code-pluginclaude-code-pluginsclaude-code-plugins-marketplaceclaude-marketplaceclaude-pluginclaude-skillsdocsdocumentationmcpmcp-serverpostgrespostgresqlskills

Install in seconds

Install PGVector Semantic Search

Copy PGVector Semantic Search into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/timescale/pg-aiguide/tree/main/skills/pgvector-semantic-search ~/.claude/skills/pgvector-semantic-search

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/timescale/pg-aiguide.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/pgvector-semantic-search/SKILL.md in timescale/pg-aiguide
Installs to: ~/.claude/skills/pgvector-semantic-search
Collection: One of 10 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What PGVector Semantic Search does

PGVector Semantic Search stores and searches vector embeddings in PostgreSQL using HNSW or IVFFlat indexes for semantic search, RAG, and nearest-neighbor queries. Use it to set up pgvector, tune recall and performance, or implement binary quantization for large datasets.

PGVector Semantic Search is cataloged under AI Engineering on DirSkills. PGVector Semantic Search comes from a repository tagged ai, ai-agents, ai-coding, claude-code-plugin and claude-code-plugins.

Documentation

README

Excerpt

pgvector for Semantic Search

Semantic search finds content by meaning rather than exact keywords. An embedding model converts text into high-dimensional vectors, where similar meanings map to nearby points. pgvector stores these vectors in PostgreSQL and uses approximate nearest neighbor (ANN) indexes to find the closest matches quickly—scaling to millions of rows without leaving the database. Store your text alongside its embedding, then query by converting your search text to a vector and returning the rows with the smallest distance.

This guide covers pgvector setup and tuning—not embedding model selection or text chunking, which significantly affect search quality. Requires pgvector 0.8.0+ for all features (halfvec, binary_quantize, iterative scan).

This is the opening of the README. Read the full README on GitHub.

Frequently asked about PGVector Semantic Search

What else does timescale publish alongside PGVector Semantic Search?
PGVector Semantic Search is one of 10 skills that DirSkills catalogs from timescale/pg-aiguide, the repository it ships in. Its siblings there include Find Hypertable Candidates, Ghost Database and PostGIS Spatial Table Design. Each one is a separate skill with its own page in this directory, installs the same way PGVector Semantic Search does, and is maintained by timescale in that same repository. The rest of the collection is listed on the timescale/pg-aiguide page.
How does PGVector Semantic Search compare to other AI Engineering skills?
PGVector Semantic Search ranks #920 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of PGVector Semantic Search against them. Open each page to compare what they document and how they install.