Skills
.Work. You
Rest

django-pgsearch-patterns

Official

Django BM25 + vector search patterns

Software Engineering#django#pgvector#postgres#full-text-search#vector-search#bm25#hybrid-search
AuthorMercurium-Analytics
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Django applications often need both strong full-text search and semantic similarity. This skill enables Django to leverage BM25 via pg_search and vector search via pgvector, plus a straightforward path to hybrid retrieval in Django workflows.

Core Features & Use Cases

  • BM25-based lexical search on Django models using RunSQL migrations to create BM25 indexes.
  • Vector search with pgvector using VectorField and HnswIndex for semantic matching.
  • Hybrid retrieval using pgsv.hybrid_search() from raw SQL to fuse lexical and vector results for RAG-like pipelines.
  • Django-friendly adapters like django-paradedb and pgvector.django to simplify integration and scoring.

Quick Start

Install django-paradedb and pgvector, define a model with a VectorField and HnswIndex, run migrations to create bm25 and vector indexes, and perform a hybrid search via pgsv.hybrid_search.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: django-pgsearch-patterns
Download link: https://github.com/Mercurium-Analytics/pg-search-vector/archive/main.zip#django-pgsearch-patterns

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.