rag-pipeline

Name: rag-pipeline
Availability: InStock
Author: eco2-team

Implement and evaluate retrieval-augmented generation workflows with citation tracking.

3|Updated Oct 27, 2025

Search Tags:#rag #citation #retrieval-augmented generation #retriever #evidence-tracking #contextual-search #phase-1-4 evaluation

Ready to run

npx skills add https://github.com/eco2-team/backend --skill rag-pipeline

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-pipeline
Source: https://github.com/eco2-team/backend/tree/main/.claude/skills/rag-pipeline
Command: npx skills add https://github.com/eco2-team/backend --skill rag-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

RAG pipelines are complex to implement and evaluate; this guide provides a self-contained blueprint to build and test a Retrieval-Augmented Generation workflow, including context retrieval, evidence tracking, and phased evaluation.

Core Features & Use Cases

Retrieval-driven QA with evidence citation
Phase 1-4 evaluation (citation, nugget completeness, groundedness, and next steps)
Modular integration with LocalAssetRetriever and TagBasedRetriever
Reference materials and prompts to guide prompt strategies

Quick Start

Prepare your knowledge base data and a user query.
Run the RagPipeline driver to perform retrieval, assemble evidence, and generate an answer.
Review the Phase 1-4 evaluation results to confirm citation relevance, completeness, and grounding.

Frequently Asked Questions about rag-pipeline

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

FAQPage Schema

How do I build a retrieval-augmented generation pipeline with evidence tracking?▼

To build a retrieval-augmented generation pipeline with evidence tracking, you need a guided framework that integrates contextual retrieval, citation generation, and phased evaluation to ensure grounded responses.

What is Phase 1-4 evaluation in retrieval-augmented generation?▼

Phase 1-4 evaluation in retrieval-augmented generation is a structured testing framework that measures citation relevance, nugget completeness, groundedness, and next steps to validate answer accuracy.

How do I add citation and evidence tracking to a RAG chatbot?▼

Adding citation and evidence tracking to a RAG chatbot requires assembling retrieved context into grounded evidence references before generation, ensuring the output links back to source materials.

Can I use local retrievers with a retrieval-augmented generation workflow?▼

Yes, you can use local retrievers with a retrieval-augmented generation workflow by implementing modular integration with components like LocalAssetRetriever and TagBasedRetriever for contextual search.

What is the best way to evaluate groundedness in a RAG pipeline?▼

The best way to evaluate groundedness in a RAG pipeline is applying a phased evaluation framework that specifically tests citation relevance and nugget completeness against the retrieved context.

Why does my retrieval-augmented generation chatbot return ungrounded answers?▼

Retrieval-augmented generation chatbots return ungrounded answers when lacking strict evidence tracking and phased evaluation, which are required to align generated responses with retrieved context.