Skip to main content

Setup and Installation

Follow these instructions to get the application running on your local machine.

1. Clone the Repository​

First, clone this repository to your local machine:

git clone https://github.com/Rishabh-Bajpai/Personal-Guru.git
cd Personal-Guru

2. Create a Conda Environment​

We recommend using Conda to manage your Python environment. Create and activate a new environment with Python 3.9:

conda create -n Personal-Guru python=3.9
conda activate Personal-Guru

3. Install Dependencies​

Install the required Python packages using pip:

pip install -r requirements.txt

4. Setup Environment Variables​

The application is configured using a .env file. Copy the example file and edit it with the URLs and models for your local AI services.

cp .env.example .env

Now, open the .env file and customize the settings.

Key Variables:

  • DATABASE_URL: Connection string for the PostgreSQL database (e.g., postgresql://postgres:postgres@localhost:5433/personal_guru).
  • PORT: The port the application will run on (default 5011).
  • LLM_ENDPOINT: The base URL of your LLM provider.
    • For Ollama: http://localhost:11434/v1
    • For LMStudio: http://localhost:1234/v1
    • For OpenAI: https://api.openai.com/v1
    • For Gemini: https://generativelanguage.googleapis.com/v1beta/openai/
  • LLM_MODEL_NAME: The name of the model to use (e.g., llama3, gpt-4o).
  • LLM_API_KEY: API Key (optional for local providers like Ollama).
  • LLM_NUM_CTX: Context window size (recommended: 18000 or higher if your hardware supports it).

Database Setup​

Before running the application, ensure your database is properly configured. For detailed instructions, please refer to the Database Setup Guide.