skills.rest
CleanExpo
CleanExpoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

vector-search

Generate pgvector embeddings and run similarity or hybrid search in Supabase/PostgreSQL.

1|Updated Sep 14, 2025
Search Tags:#semantic search#embeddings#rag#vector search#similarity search#pgvector
One-click install
npx skills add https://github.com/CleanExpo/DR-NRPG --skill vector-search-cleanexpo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-search
Source: https://github.com/CleanExpo/DR-NRPG/tree/main/.skills/custom/vector-search
Command: npx skills add https://github.com/CleanExpo/DR-NRPG --skill vector-search-cleanexpo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables powerful semantic search capabilities by leveraging pgvector for embedding queries, similarity search, and hybrid search, streamlining data retrieval and agent knowledge management.

Core Features & Use Cases

  • Multi-Provider Embeddings: Generates embeddings using various providers (OpenAI, Ollama) for flexibility.
  • Hybrid Search: Combines vector similarity with keyword matching for more relevant results.
  • RAG Pipeline Integration: Codifies the infrastructure for document retrieval and agent memory.
  • Use Case: Implement a Q&A system over your company's documentation where users can ask natural language questions and receive precise answers derived from the most relevant document chunks.

Quick Start

Use the vector-search skill to find documents semantically similar to the query "what are the latest disaster recovery protocols?".

Frequently Asked Questions about vector-search

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

FAQPage Schema
How do I implement semantic search in Supabase using pgvector?▼

Semantic search in Supabase uses pgvector to store embeddings and perform similarity queries. This Skill codifies pgvector embedding queries, indexing strategies, and chunking patterns to streamline vector infrastructure setup and data retrieval.

Can I generate embeddings from multiple providers like OpenAI and Ollama for RAG?▼

Yes, multi-provider embedding generation supports OpenAI and Ollama. This flexibility allows you to create embeddings within your RAG pipeline, combining vector similarity with keyword matching for hybrid search results.

What is the best way to combine keyword matching with vector similarity search?▼

Hybrid search combines vector similarity with keyword matching to deliver more relevant results. This approach is codified within the pgvector infrastructure, optimizing document retrieval and agent knowledge management for natural language queries.

Does pgvector work for managing agent memory and document retrieval pipelines?▼

Yes, pgvector manages the project's Memory Store and RAG Pipeline vector infrastructure. It codifies document retrieval and agent memory by handling embedding queries, similarity search, and chunking patterns for knowledge management.

How do I set up indexing strategies and chunking patterns for PostgreSQL vector search?▼

PostgreSQL vector search relies on proper indexing strategies and chunking patterns. This Skill codifies these infrastructure components within pgvector, managing embedding generation and similarity queries to optimize document chunk retrieval.

Related Skills

Explore More Software Engineering Skills→
yoanbernabeuyoanbernabeu
18

grepai-storage-postgres

Configure PostgreSQL with pgvector for GrepAI storage backends.

Community
Advanced
AxelooooAxeloooo

rag-implementation

Implement RAG pipelines with vector retrieval and context-grounded generation.

Community
Intermediate
Axel-DaMageAxel-DaMage
2

rag-architect

Design and implement RAG systems with document chunking, embeddings, and hybrid search.

Community
Advanced
DrLuggelsDrLuggels
3

similarity-search-patterns

Provide patterns for similarity search with vector databases like Pinecone and Qdrant.

Community
Advanced