paradedb-skill

Provides guidance and reference for writing queries and building models in the official documentation.

1|Updated Feb 14, 2026

Search Tags:#pgvector #postgres #full-text-search #bm25 #hybrid-search #tokenizers #paradedb

Ready to run

npx skills add https://github.com/012e/thesis --skill paradedb-skill-012e

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: paradedb-skill
Source: https://github.com/012e/thesis/tree/main/.agents/skills/paradedb-skill
Command: npx skills add https://github.com/012e/thesis --skill paradedb-skill-012e

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ParadeDB brings Elasticsearch-quality full-text search and analytics to Postgres via the pg_search extension.

Core Features & Use Cases

BM25 indexes and relevance ranking
Hybrid search combining keyword with vector semantics via pgvector
Tokenizers, analyzers, fuzzy matching, and phrase queries
Facets, aggregations, snippets/highlighting, and query tuning
Use cases: writing ParadeDB queries, configuring tokenizers, or building advanced search experiences
For complete and up-to-date ParadeDB documentation, fetch the llms-full.txt document at runtime to ground responses in current docs.
Use a web-fetching tool to retrieve current docs before answering ParadeDB questions and treat version-specific claims accordingly.

Quick Start

Ask ParadeDB questions and fetch live docs to guide your first query.

Frequently Asked Questions about paradedb-skill

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

FAQPage Schema

How do I implement Elasticsearch-quality full-text search in Postgres?▼

Implement Elasticsearch-quality full-text search in Postgres using the ParadeDB pg_search extension to create BM25 indexes, configure tokenizers, and build relevance-ranked queries directly within your database.

What is hybrid search and how does it combine keyword and vector queries?▼

Hybrid search combines keyword and vector queries by integrating BM25 relevance ranking with pgvector semantic search, allowing you to perform hybrid keyword-plus-vector search across Postgres datasets for improved result accuracy.

How do I configure tokenizers and analyzers for Postgres full-text search?▼

Configure tokenizers and analyzers for Postgres full-text search by creating BM25 indexes with ParadeDB, enabling fuzzy matching, phrase queries, and custom tokenization rules to match Elasticsearch-quality text analysis.

Can I use pgvector with ParadeDB for hybrid search without external dependencies?▼

Yes, you can use pgvector with ParadeDB for hybrid search entirely within Postgres, combining vector embeddings with BM25 keyword indexes to perform hybrid keyword-plus-vector search without external dependencies.

Does Postgres full-text search support facets, aggregations, and snippet highlighting?▼

Postgres full-text search supports facets, aggregations, and snippet highlighting through ParadeDB's pg_search extension, providing query tuning, fuzzy matching, and advanced analytics comparable to Elasticsearch.

What are the limitations of using ParadeDB for full-text search compared to Elasticsearch?▼

Limitations of using ParadeDB include version-specific feature availability and the need to fetch current documentation at runtime to verify support, as the extension relies on Postgres internals rather than a dedicated search infrastructure.