·postgres-semantic-search
</>

postgres-semantic-search

laguagu/claude-code-nextjs-skills

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank

18Installs·1Trend·@laguagu

Installation

$npx skills add https://github.com/laguagu/claude-code-nextjs-skills --skill postgres-semantic-search

SKILL.md

| | Cosine | Text embeddings (default) | | | L2/Euclidean | Image embeddings | | | Inner product | Normalized vectors |

| Cohere Rerank v4.0-fast | 150ms | Excellent | $0.001/query | | Cohere Rerank v4.0-pro | 300ms | Best | $0.002/query | | Zerank 2 | 100ms | Best | API cost | | Voyage Rerank 2.5 | 100ms | Excellent | API cost | | Cross-encoder (local) | 500ms | Very Good | Compute |

| Index not used | < 10k rows or planner choice | Normal for small tables, check with EXPLAIN | | Slow first query (30-60s) | HNSW cold-start | SELECT pgprewarm('idxname') or preload query | | Poor recall | Low efsearch | SET hnsw.efsearch = 100 or higher | | FTS returns nothing | Wrong language config | Use 'simple' for mixed/unknown languages |

View raw

Facts (cite-ready)

Stable fields and commands for AI/search citations.

Install command
npx skills add https://github.com/laguagu/claude-code-nextjs-skills --skill postgres-semantic-search
Category
</>Dev Tools
Verified
First Seen
2026-02-01
Updated
2026-02-18

Quick answers

What is postgres-semantic-search?

PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank Source: laguagu/claude-code-nextjs-skills.

How do I install postgres-semantic-search?

Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/laguagu/claude-code-nextjs-skills --skill postgres-semantic-search Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor

Where is the source repository?

https://github.com/laguagu/claude-code-nextjs-skills