ꇙ꓄0ꋊꀘ: Personal AI Agent

A Personal AI agent that answers questions about your PDF documents using Google Gemini.

🚀 Quick Start (Docker - Recommended)

Prerequisites

• Docker installed on your system (Recommended)
• Google Gemini API key (free from Google AI Studio)

Installation & Setup

Step 1: Get Your API Key

1. Visit Google AI Studio
2. Sign in with your Google account
3. Click "Get API Key" → "Create API Key"
4. Copy your key (starts with AIzaSy...)

Step 2: Choose Your Installation Method

🐳 Method A: Docker (Recommended - No Python Required)

# Clone the repository
git clone https://github.com/souravsuvarna/st0nk.git
cd st0nk

# Build Docker image
docker build -t st0nk .

# Run the container
docker run -p 8501:8501 -e GOOGLE_API_KEY="your_actual_key_here" --name st0nk st0nk

💻 Method B: Local Python Development

# Clone the repository
git clone https://github.com/souravsuvarna/st0nk.git
cd st0nk


#Create Virtual Environment (Recommended)
# Windows
python -m venv ai_agent_env
ai_agent_env\Scripts\activate

# Linux/Mac
python -m venv ai_agent_env
source ai_agent_env/bin/activate

#Install Dependencies
pip install -r requirements.txt


#Set Up Environment File
# Copy the environment template
cp .env.example .env


# Edit the .env file and add your API key
# On Windows, you can use Notepad:
notepad .env

# On Linux/Mac, you can use nano:
nano .env

#Add this line to .env file:
GOOGLE_API_KEY=AIzaSyYourActualKeyHere

## Create Data Directory (Created by default when you clone)

# This directory is usually created by default during cloning,
# but you can manually create it if it doesn’t exist.
mkdir -p data


#Run the Application
streamlit run app.py

Step 3: Verify Installation

For Docker:

Open your browser and go to: http://localhost:8501

You should see the AI Agent interface

For Local Python:

Open your browser and go to: http://localhost:8501

Streamlit should automatically open the application

Step 4: First-Time Setup in Web Interface

Upload PDF Documents

Click "Upload PDF Files" in the sidebar

Select your PDF files

Click "Upload"

Process Documents

Click "Process Documents" button

Wait for processing to complete (2-5 minutes for typical documents)

Start Chatting

Type your question in the chat input

Press Enter to get AI-powered answers

System Requirements

For Docker:
Docker Desktop installed
4GB RAM available
2GB free disk space
Windows 10+, macOS 10.15+, or Linux

For Local Python:
Python 3.11.8
4GB RAM available
1GB free disk space
pip package manager