rag-pipeline-python

Scaffold end-to-end RAG pipelines for local or cloud LLMs.

2|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/michaelalber/ai-toolkit --skill rag-pipeline-python
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rag-pipeline-python
Source: https://github.com/michaelalber/ai-toolkit/tree/main/skills/rag-pipeline-python
Command: npx skills add https://github.com/michaelalber/ai-toolkit --skill rag-pipeline-python

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires langchain, langchain-community, langchain-chroma, langchain-ollama, sentence-transformers, chromadb, pypdf, pdfplumber, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation of Retrieval-Augmented Generation (RAG) pipelines, enabling you to build intelligent systems that can answer questions based on your own documents.

Core Features & Use Cases

  • End-to-End Scaffolding: Guides you through document ingestion, chunking, embedding, indexing, retrieval, and generation.
  • Flexible Configuration: Supports local models (Ollama, sentence-transformers) and cloud embeddings/LLMs.
  • Evaluation Focused: Emphasizes measuring retrieval quality before generation tuning.
  • Use Case: You have a large collection of internal company documentation and want to build a chatbot that can answer employee questions accurately by referencing these documents.

Quick Start

Use the rag-pipeline-python skill to scaffold a RAG pipeline using Ollama and local documents.

Frequently Asked Questions about rag-pipeline-python

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

FAQPage Schema
How do I build a RAG pipeline with Ollama and local documents?

This skill scaffolds a RAG pipeline by automating document ingestion, chunking, embedding, and indexing with LangChain, then retrieves and generates answers using Ollama and local documents.

What is retrieval quality evaluation in a RAG pipeline?

Retrieval quality evaluation measures how accurately relevant chunks are fetched before generation tuning. This skill enforces retrieval quality metrics to ensure the generation step receives accurate context from your documents.

Can I use sentence-transformers for embedding generation in a ChromaDB RAG pipeline?

Yes, you can use sentence-transformers for embedding generation in a ChromaDB RAG pipeline. This skill supports local models like sentence-transformers alongside cloud embedding providers for indexing and retrieval.

What's the best way to process PDFs for retrieval-augmented generation?

The best way to process PDFs for retrieval-augmented generation is to enforce document preprocessing and chunking before embedding. This skill integrates pypdf and pdfplumber to ingest and chunk PDF content for vector indexing.

Does this RAG scaffolding approach work with cloud LLMs or only local models?

This RAG scaffolding approach works with both cloud LLMs and local models. It supports flexible configuration for Ollama, sentence-transformers, and cloud embedding providers to adapt to your infrastructure.

Why does my RAG pipeline return inaccurate answers from my documents?

Your RAG pipeline may return inaccurate answers due to poor retrieval quality or improper document chunking. This skill emphasizes measuring retrieval quality metrics and enforces document preprocessing before generation tuning.