Skip to content

axellarsstenson/rag-directory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RAG Directory

A command-line tool for Retrieval-Augmented Generation (RAG) using local files and Ollama models.

Installation

pip install rag-directory

Requirements

Usage

# Using the command-line tool
rag-directory llama2:latest [directory]

# Or if you want to run on the directory that you are in
rag-directory llama2:latest

# Or using Python
from rag_directory.cli import RAGTool
rag = RAGTool("llama2:latest")
rag.load_directory("path/to/directory")
rag.chat_loop()

Features

  • Process multiple file types (PDF, Markdown, text files)
  • Semantic search using sentence transformers
  • Interactive chat interface
  • Source attribution for answers
  • Integrates with Ollama models

Example

$ rag-directory llama2:latest ./docs
Loading files from ./docs...
Processed: ./docs/architecture.pdf
Processed: ./docs/api.md
Starting chat session. Type 'exit' to quit.

What would you like to know: What is the system architecture?

License

MIT License. See LICENSE file for details.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages