vector-db-rag

Name: vector-db-rag
Availability: InStock
Author: jota-batuta

Implement RAG pipelines with PostgreSQL vector stores and multi-tenant isolation.

Updated Feb 20, 2026

Search Tags:#multi-tenant #embeddings #rag #chunking #pgvector #vector-store #hybrid-search

Ready to run

npx skills add https://github.com/jota-batuta/batuta-dots --skill vector-db-rag

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vector-db-rag
Source: https://github.com/jota-batuta/batuta-dots/tree/main/BatutaClaude/skills/vector-db-rag
Command: npx skills add https://github.com/jota-batuta/batuta-dots --skill vector-db-rag

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Standardizes end-to-end Retrieval Augmented Generation pipelines by providing a consistent approach to embeddings, chunking, and vector storage with multi-tenant isolation.

Core Features & Use Cases

End-to-end RAG guidance for documents, code, and knowledge bases using pgvector.
Multi-tenant isolation via Row-Level Security on embedding storage, with tenant-aware chunking and indexing.
Hybrid semantic+keyword retrieval with configurable chunking strategies per document type and metrics tracking.

Quick Start

Instruct the system to configure and deploy a RAG pipeline with a PostgreSQL-backed vector store, including chunking, embedding, storage, retrieval, and evaluation.

Frequently Asked Questions about vector-db-rag

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

FAQPage Schema

How do I build a multi-tenant RAG pipeline with PostgreSQL?▼

To build a multi-tenant RAG pipeline with PostgreSQL, you use pgvector as the vector store and enforce Row-Level Security for tenant isolation. This Skill standardizes that process by applying per-document-type chunking policies and HNSW indexing.

What is the best way to isolate vector embeddings for different tenants in pgvector?▼

The best way to isolate vector embeddings in pgvector is by enforcing Row-Level Security policies on the embedding storage tables. This ensures multi-tenant isolation so queries only retrieve chunks belonging to the specific tenant.

How do I configure hybrid search for a RAG application using pgvector?▼

You configure hybrid search for a RAG application by combining semantic vector retrieval with keyword matching within the PostgreSQL database. This approach uses HNSW indexing to optimize vector similarity searches alongside traditional text queries.

Does this approach support different chunking strategies for various document types?▼

Yes, this approach supports configurable chunking strategies tailored per document type. Whether processing documents, code, or knowledge bases, the pipeline applies specific chunking policies to optimize embedding generation and retrieval accuracy.

Can I track evaluation metrics for my RAG pipeline at runtime?▼

Yes, you can track runtime evaluation metrics for your RAG pipeline. The pipeline includes metrics tracking to measure retrieval effectiveness and overall performance during the embedding, chunking, and retrieval phases.

When should I use HNSW indexing for vector similarity search in PostgreSQL?▼

You should use HNSW indexing for vector similarity search when you need high-performance approximate nearest neighbor queries in PostgreSQL. It is enforced in this pipeline to ensure fast hybrid semantic and keyword retrieval across large embedding datasets.