fullstack-rag-pro

What problem does it solve?

This Skill addresses the complex task of creating production-grade Retrieval-Augmented Generation (RAG) pipelines, providing a comprehensive solution for integrating Vector DBs and hybrid search capabilities.

Core Features & Use Cases

• End-to-End RAG Architecture: Covers document ingestion, chunking, embedding generation, vector database querying, and LLM synthesis.
• Document Ingestion: Handles various document formats for indexing into a Vector DB.
• Embedding Generation: Supports different embedding models for efficient vector storage.
• Retrieval: Implements cosine similarity search with metadata filtering.
• Synthesis: Formats retrieved context for LLM system prompts.
• Use Case: Ideal for building AI chat applications with custom knowledge bases or implementing semantic search in applications.

Quick Start

Use the fullstack-rag-pro skill to generate embeddings for a given text and retrieve relevant documents.