Chat-AI-Service

A Service to write AI Agent Logic.

System Flow Diagram

Services

• Sync-Backend
• Chat-UI
• Chat-Backend

Getting Started

1. Clone the repository:

   git clone https://github.com/AI-at-Work/Chat-AI-Service
   cd Chat-AI-Service

2. Copy the .env.sample to .env and configure the environment variables:

   cp .env.sample .env

   Edit the .env file to set your specific configurations and add openai api key.

3. Start the service:

   make proto && docker compose up -d --build

To add Nvidia GPU to the Ollama You Need to install NVIDIA Container Toolkit

1. Configure the production repository:

   curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
   && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
   sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
   sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

2. Update the packages list from the repository:

   sudo apt-get update

3. Install the NVIDIA Container Toolkit packages:

      sudo apt-get install -y nvidia-container-toolkit

4. Configure the container runtime by using the nvidia-ctk command:

   sudo nvidia-ctk runtime configure --runtime=docker

5. Restart the Docker daemon:

   sudo systemctl restart docker

Configuration

Key configuration options in the .env file:

• AI_*: AI Server configurations

Refer to the .env.sample file for a complete list of configuration options.