paradedb-skill

What problem does it solve?

This Skill helps developers and data engineers implement and tune high-quality full-text and hybrid search (BM25 + semantic vectors) inside Postgres using ParadeDB, removing guesswork about index design, tokenizers, and relevance tuning.

Core Features & Use Cases

• Query Authoring: Provide runnable ParadeDB SQL for BM25 indexes, hybrid searches with pgvector, phrase and fuzzy queries, and relevance scoring.
• Configuration Guidance: Recommend tokenizers, analyzers, BM25 field weights, and hybrid fusion strategies for production search.
• Operational Advice: Explain migration patterns from Elasticsearch, faceted aggregations, and performance/monitoring tips for large datasets.
• Use Case: Implement a product search that combines BM25 title/description ranking with vector semantics for personalized relevance.

Quick Start

Fetch the official ParadeDB llms-full.txt docs, then produce a runnable ParadeDB SQL statement that creates a BM25 index and a hybrid BM25+vector query for a products table.