Quick Start

Getting Started

This guide will walk you through setting up the AI-driven trading system, from environment configuration to running your first backtest and visualizing results on the dashboard.

1. Prerequisites

Before you begin, ensure you have the following installed:

• Python 3.10+
• Node.js & npm (for the dashboard)
• LLM Provider: An API key for Groq (recommended for speed) or a local Ollama instance.
• NewsAPI Key: (Optional) For enhanced news sentiment data.

2. Installation

Clone the repository and set up the backend and frontend environments.

Backend Setup

# Create and activate a virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

Frontend Setup

cd dashboard/frontend
npm install
cd ../..

3. Environment Configuration

Create a .env file in the root directory to store your credentials:

# LLM Configuration
GROQ_API_KEY=your_groq_api_key_here
# OR if using Ollama
OLLAMA_BASE_URL=http://localhost:11434

# Data Connectors
NEWSAPI_KEY=your_newsapi_key_here

4. Initialize Knowledge Base (RAG)

The system uses Retrieval-Augmented Generation (RAG) to provide agents with domain-specific knowledge. You must index the provided markdown files before running the agents.

from agents.rag.indexer import KnowledgeIndexer

indexer = KnowledgeIndexer()
indexer.index_all()

Alternatively, if a CLI script is provided, run: python manage_knowledge.py --index

5. Running Your First Backtest

Execute a backtest to simulate the multi-agent system's performance over a specific period. The system will orchestrate Technical, Sentiment, Fundamental, and Risk agents to make trading decisions.

# Run a 30-day backtest on Bitcoin
python run_backtest.py --days 30 --asset BTC

Once the backtest completes, a JSON report is generated in the logs/ directory. You can view a quick summary in the terminal:

python view_trades.py

6. Launching the Dashboard

To visualize the equity curve, agent reasoning, and specific trade logs, start the dashboard.

Start the Backend API

# From the root directory
uvicorn dashboard.backend.main:app --reload

The API will be available at http://localhost:8000.

Start the Frontend

# In a new terminal
cd dashboard/frontend
npm run dev

Open http://localhost:5173 in your browser. You can now select your backtest from the dropdown to see a detailed breakdown of the AI's performance and the logic behind every trade.

7. Basic Usage Example

If you wish to interact with the orchestration layer directly in your own scripts:

from orchestrator import TradingOrchestrator

# Initialize the system
orchestrator = TradingOrchestrator(backend="groq")

# Request a comprehensive analysis
query = "Bitcoin is at $62,000. RSI is 70. News sentiment is bullish but network growth is flat. Recommendation?"
result = orchestrator.analyze(query, enable_debate=True)

# Print the final consensus decision
orchestrator.print_final_decision(result)