Does it provide specific settings for different data types?

Yes, it includes tailored chunk size and overlap recommendations for legal documents, technical docs, source code, markdown, and large PDFs.

How does this help with RAG performance?

It provides Top-K retrieval guidelines and diagnostic strategies to ensure your LLM receives the most relevant context while minimizing noise and latency.

What is the LlamaFarm RAG Pipeline skill?

It is a specialized capability for Claude Code that provides deep technical guidance on building, configuring, and optimizing Retrieval-Augmented Generation workflows.

When should I activate this skill?

Activate this skill when you are setting up vector databases, choosing embedding models, determining chunking strategies, or troubleshooting AI response quality.

Can it help with document parsing?

Yes, the skill covers the entire pipeline from file parsing and metadata extraction to final retrieval and LLM integration.

LlamaFarm RAG Pipeline

Name: LlamaFarm RAG Pipeline
Author: llama-farm

byllama-farm

数据科学与机器学习

Provides expert guidance for building, configuring, and optimizing Retrieval-Augmented Generation (RAG) pipelines.

关于

The LlamaFarm RAG Pipeline skill equips Claude with deep technical expertise to architect and refine RAG workflows. It offers prescriptive advice on document parsing, chunking strategies, embedding model selection, and vector store configuration. Whether you are troubleshooting retrieval quality or optimizing performance for specific document types like legal texts or source code, this skill provides the structured guidelines and progressive disclosure needed to build high-performance AI search systems.

主要功能

Troubleshooting workflows for fixing RAG quality issues
Domain-specific chunking strategies for various document types
Expert embedding model selection and configuration advice
0 GitHub stars
Detailed guidance for vector store integration and metadata extraction
Optimized Top-K retrieval guidelines for diverse use cases

使用场景

Improving the accuracy and relevance of an existing AI retrieval pipeline
Configuring a RAG system for specialized legal or technical documentation
Optimizing chunk sizes and overlaps to improve LLM context quality

关于

主要功能

Troubleshooting workflows for fixing RAG quality issues
Domain-specific chunking strategies for various document types
Expert embedding model selection and configuration advice
0 GitHub stars
Detailed guidance for vector store integration and metadata extraction
Optimized Top-K retrieval guidelines for diverse use cases

使用场景

Improving the accuracy and relevance of an existing AI retrieval pipeline
Configuring a RAG system for specialized legal or technical documentation
Optimizing chunk sizes and overlaps to improve LLM context quality