https://github.com/eduardolagoeiro/dumbledore

https://github.com/eduardolagoeiro/dumbledore

Last synced: 19 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/eduardolagoeiro/dumbledore
• Owner: eduardolagoeiro
• Created: 2024-09-14T15:34:05.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-09-15T03:57:35.000Z (5 months ago)
• Last Synced: 2024-11-24T10:26:09.160Z (3 months ago)
• Language: Python
• Size: 13.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Python CLI with Ollama Integration (GPU-enabled)

This project is a Python CLI that interacts with a local Ollama instance to run LLaMA, using a Retrieval-Augmented Generation (RAG) setup. The database stores relevant documents that are used to augment the LLaMA model’s responses.

## Requirements

- Python 3.10

- Docker

- Docker Compose

- Ollama

## Setup Instructions

### Step 1: Clone the Repository

```bash

git clone [email protected]:eduardolagoeiro/dumbledore.git

cd dumbledore

```

### Step 2: Set up a Python Virtual Environment

Create and activate the virtual environment using Python 3.8:

```bash

python -m venv venv

source venv/bin/activate  # On macOS/Linux

# or

venv\Scripts\activate  # On Windows

```

### Step 3: Install Python Dependencies

```bash

pip install -r requirements.txt

```

### Step 3: Run the CLI

Once the environment is set up and the Ollama instance is running with LLaMA installed, you can start the CLI by running:

```bash

python cli.py

```

This will open the main menu of the CLI, where you can interact with GitHub repositories or start chatting with the AI model.