oc-rag-forge
CommunityDesign and build RAG systems with vector DB choice, embeddings, chunking, hybrid search, and retrieval eval.
Software Engineering#vector database#RAG#hybrid search#chunking#embedding model#retrieval evaluation
Authorasfbay-bit
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a comprehensive solution for designing and building Retrieval-Augmented Generation (RAG) systems, addressing the complexities of vector database selection, embedding models, chunking strategies, hybrid search, and retrieval evaluation.
Core Features & Use Cases
- Vector Database Selection: Offers a choice of vector databases like pgvector, Turbopuffer, Pinecone, and Supabase Vectors.
- Embedding Model Choice: Allows selection from various embedding models tailored to specific domains and languages.
- Chunking Strategy: Provides options for chunking strategies to optimize retrieval performance.
- Hybrid Search: Integrates both dense and BM25 search modes for enhanced retrieval.
- Retrieval Evaluation: Includes an evaluation process to measure and improve retrieval quality.
- Use Case: Ideal for developers and data scientists looking to implement a knowledge base or semantic search system with a focus on retrieval quality.
Quick Start
To start using the oc-rag-forge skill, initiate the /oc-rag command to design, build, and evaluate a RAG system.
Dependency Matrix
Required Modules
pgvectorturbopufferpineconesupabase-vectorscoherevoyageopenai
Components
scriptsreferencesassets
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: oc-rag-forge Download link: https://github.com/asfbay-bit/opchain-skills/archive/main.zip#oc-rag-forge Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.