rag-pipeline

Build and query RAG pipelines over document collections with Codex.

Updated Jun 23, 2026

Search Tags:#semantic search #RAG #document analysis #document indexing #AI-driven generation

Ready to run

npx skills add https://github.com/guideops/agentic-shared --skill rag-pipeline-guideops

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: rag-pipeline
Source: https://github.com/guideops/agentic-shared/tree/main/skills/rag-pipeline
Command: npx skills add https://github.com/guideops/agentic-shared --skill rag-pipeline-guideops

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, openai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently building and querying RAG (Retrieval-Augmented Generation) pipelines, enabling users to create and manage indexes over document collections for semantic search and retrieval-augmented generation.

Core Features & Use Cases

Index Creation: Build and manage indexes for Obsidian vaults or arbitrary document collections.
Semantic Search: Perform semantic searches on indexed documents.
Retrieval-Augmented Generation: Generate responses using Codex based on retrieved document context.
Use Case: For a researcher looking to analyze a large corpus of documents, this Skill can automate the process of indexing, searching, and generating summaries, saving significant time and effort.

Quick Start

Build an index for your documents with /rag-pipeline index --path wiki/.

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 RAG pipeline for semantic search over my documents?▼

To build a RAG pipeline for semantic search, you create and manage indexes over your document collections, enabling efficient retrieval. This Skill automates indexing and querying to generate responses using Codex based on retrieved context.

Do I need an OpenAI API key to use retrieval-augmented generation with Codex?▼

Yes, you need an OpenAI API key to use retrieval-augmented generation with Codex. The Python environment requires this key for Codex integration to generate responses based on retrieved document context.

What's the best way to index an Obsidian vault for AI-driven document analysis?▼

The best way to index an Obsidian vault for AI-driven document analysis is using a RAG pipeline. You can build and manage indexes for arbitrary document collections by running a command like `/rag-pipeline index --path wiki/`.

How does retrieval-augmented generation work with indexed document collections?▼

Retrieval-augmented generation works by performing semantic searches on indexed document collections to find relevant context. It then uses Codex to generate responses based on the retrieved document information.

Can I use Python to automate document indexing and summarization for large corpora?▼

Yes, you can use Python to automate document indexing and summarization for large corpora. This Skill supports building RAG pipelines that index, search, and generate summaries, saving researchers significant time and effort.

What are the limitations of using Codex for retrieval-augmented generation?▼

Limitations of using Codex for retrieval-augmented generation include dependencies on Python and an OpenAI API key. The effectiveness of generated responses is constrained by the quality of indexed documents and semantic search results.