skills.rest
sit-institute
sit-instituteOFFICIAL
Explore all skills by this author →
WebsiteGitHub

local-rag-pipeline

Index documents into ChromaDB and perform semantic search locally.

Updated Aug 23, 2026
Search Tags:#document processing#embeddings#rag#search#local#chromadb
One-click install
npx skills add https://github.com/sit-institute/docbot --skill local-rag-pipeline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: local-rag-pipeline
Source: https://github.com/sit-institute/docbot/tree/main/.github/skills/local-rag-pipeline
Command: npx skills add https://github.com/sit-institute/docbot --skill local-rag-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires docling, sentence-transformers, chromadb, torch, PyPDF2, python-docx, Pillow, numpy, pandas, scikit-learn, tqdm, click, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a complete, self-contained system for indexing and searching documents locally, eliminating the need for external APIs and cloud services.

Core Features & Use Cases

  • Local RAG: Full RAG pipeline running on your machine.
  • Document Indexing: Parse, chunk, embed, and index documents into a local vector database (ChromaDB).
  • Semantic Search: Perform relevance-based searches on your indexed documents.
  • Use Case: Index your project's internal documentation and then ask natural language questions to retrieve relevant information without uploading sensitive data.

Quick Start

Use the local rag pipeline skill to index the documents in the 'documents' folder into a new ChromaDB collection named 'my-project-docs'.

Frequently Asked Questions about local-rag-pipeline

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

FAQPage Schema
How do I set up a local RAG pipeline for semantic search on my internal documents?▼

Set up a local RAG pipeline using this skill to parse, chunk, and embed documents into a local ChromaDB vector database for fully on-premise semantic search. It processes PDF and DOCX files without external API dependencies.

Does this local RAG system require external APIs or cloud services to index documents?▼

No, this local RAG system requires no external APIs or cloud services. It runs entirely on your machine to parse, embed, and index documents locally, ensuring sensitive data never leaves your environment.

How do I index PDF and DOCX files into ChromaDB for natural language queries?▼

Index PDF and DOCX files into ChromaDB by pointing the pipeline at your documents folder. It uses Docling for parsing, applies hierarchical chunking, and generates GPU-accelerated embeddings via sentence-transformers for semantic search.

Can I use GPU acceleration with sentence-transformers for document embeddings in a local RAG setup?▼

Yes, you can use GPU acceleration with sentence-transformers to generate document embeddings. This local RAG setup leverages torch and sentence-transformers to compute embeddings efficiently for your indexed documents.

What is the best way to search internal project documentation without uploading sensitive data?▼

The best way to search internal documentation securely is using a local RAG pipeline. It indexes your project files into a local ChromaDB collection, allowing you to perform relevance-based queries without uploading sensitive data.

Related Skills

Explore More Software Engineering Skills→
sahiixxsahiixx
2

gpu-document-processing

Extract text and tables from large PDFs using GPU acceleration.

Community
Advanced
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
patricio0312revpatricio0312rev
5

embedding-pipeline-builder

Automate document embedding pipelines for semantic search.

Community
Advanced
MarbleSodasMarbleSodas

chroma

Store and query embedding vectors with metadata for semantic retrieval.

Community
Intermediate