Run a complete AI agent locally

With this small project you can run Ollama with llama-3-8b model locally. Also, it uses Whisper Timestamped to receive the audio from a microphone of your choose. When the completion (streamed in the console) is ready, the output is then read using the library pyttsx3 (in the future planning to change it for a local AI voice generator also open-source and locally :)

Video tutorial: How to Run LLAMA 3 locally

Retrieval Augmented Generation local with Llama and Chroma video

1. You must have Python to run this project. If you don't have it, you can download it here.

2. Install Ollama from its website: Ollama

3. Execute the installer for your operating system
   Just click the installer and press "install" or something

Create a new environment with the following command:

py -m venv venv

Activate the environment with the following command:

source venv/Scripts/activate

Install the required packages with the following command:

pip install -r requirements.txt

Run the application with the following command:

python main.py