🤖 LocalMind CLI

A secure, offline RAG (Retrieval-Augmented Generation) system for chatting with your private documents.

🌟 Why It Impresses Recruiters

• Private AI: Demonstrates implementation of local LLM inference (Ollama) without data leaving the machine.
• RAG Architecture: Showcases mastery of vector embeddings, document chunking, and similarity search.
• Production CLI: Built with Typer and Rich for a professional, interactive terminal experience.

🛠️ Tech Stack

• AI Core: Ollama (Llama 3 / Mistral)
• Vector DB: ChromaDB
• Embeddings: Sentence-Transformers (all-MiniLM-L6-v2)
• CLI Framework: Typer, Rich (for beautiful UI)

🚀 Quick Start

1. Prerequisites: Ollama must be installed and running.
2. Install Dependencies:

   pip install -r requirements.txt

3. Ingest Documents:

   python main.py ingest docs/my_data.pdf

4. Chat:

   python main.py chat

📈 Key Features

• Semantic Search: Uses cosine similarity to find relevant context in seconds.
• Memory: Context-aware chat history for follow-up questions.
• Multi-format Support: Ingests PDF, DOCX, and TXT files.

---

Part of the 10-Project OSS Portfolio.