charieswei
/
TradingAgents
mirror of https://github.com/TauricResearch/TradingAgents.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
TradingAgents/docs/QUICKSTART.md

5.5 KiB
Raw Blame History

Quick Start Guide

Get started with TradingAgents in under 10 minutes.

Installation

Prerequisites

  • Python >= 3.10 (Python 3.13 recommended)
  • pip package manager
  • Conda or virtualenv (recommended)

Step 1: Clone the Repository

git clone https://github.com/TauricResearch/TradingAgents.git
cd TradingAgents

Step 2: Create Virtual Environment

Using conda (recommended):

conda create -n tradingagents python=3.13
conda activate tradingagents

Or using venv:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

Step 3: Install Dependencies

pip install -r requirements.txt

Required APIs

TradingAgents requires API keys for LLM providers and data sources.

LLM Provider (choose one)

Option 1: OpenAI (default)

export OPENAI_API_KEY=your_api_key_here

Get your key at: https://platform.openai.com/api-keys

Option 2: Anthropic

export ANTHROPIC_API_KEY=your_api_key_here

Get your key at: https://console.anthropic.com/

Option 3: OpenRouter (unified access)

export OPENROUTER_API_KEY=your_api_key_here
export OPENAI_API_KEY=your_api_key_here  # Still needed for embeddings

Get your key at: https://openrouter.ai/keys

Option 4: Google Generative AI

export GOOGLE_API_KEY=your_api_key_here

Get your key at: https://makersuite.google.com/app/apikey

Data Vendor

Alpha Vantage (required for fundamental and news data)

export ALPHA_VANTAGE_API_KEY=your_api_key_here

Get a free key at: https://www.alphavantage.co/support/#api-key

TradingAgents users get increased rate limits (60 requests/minute, no daily limits) thanks to Alpha Vantage's open-source support program.

Using .env File

Alternatively, create a .env file in the project root:

cp .env.example .env
# Edit .env with your actual API keys

Example .env:

OPENAI_API_KEY=your_openai_key_here
ALPHA_VANTAGE_API_KEY=your_alpha_vantage_key_here
TRADINGAGENTS_RESULTS_DIR=./results

Your First Analysis

CLI Mode

Run the interactive CLI:

python -m cli.main

You'll see a menu where you can:

  • Select ticker symbols (e.g., NVDA, AAPL, TSLA)
  • Choose analysis date
  • Configure LLM models
  • Set research depth (debate rounds)

The CLI will display real-time progress as agents analyze the market and generate trading signals.

Programmatic Mode

Create a Python script:

from tradingagents.graph.trading_graph import TradingAgentsGraph
from tradingagents.default_config import DEFAULT_CONFIG

# Initialize the trading graph
ta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())

# Run analysis for NVDA on a specific date
_, decision = ta.propagate("NVDA", "2024-05-10")

# Print the trading decision
print(f"Decision: {decision['action']}")
print(f"Confidence: {decision['confidence_score']}")
print(f"Reasoning: {decision['reasoning']}")

Run your script:

python your_script.py

Configuration

Using Different LLM Providers

OpenAI (default):

config = DEFAULT_CONFIG.copy()
config["llm_provider"] = "openai"
config["deep_think_llm"] = "o4-mini"
config["quick_think_llm"] = "gpt-4o-mini"
config["backend_url"] = "https://api.openai.com/v1"

Anthropic:

config["llm_provider"] = "anthropic"
config["deep_think_llm"] = "claude-sonnet-4-20250514"
config["quick_think_llm"] = "claude-sonnet-4-20250514"
config["backend_url"] = "https://api.anthropic.com"

OpenRouter:

config["llm_provider"] = "openrouter"
config["deep_think_llm"] = "anthropic/claude-sonnet-4.5"
config["quick_think_llm"] = "openai/gpt-4o-mini"
config["backend_url"] = "https://openrouter.ai/api/v1"

Customizing Data Vendors

config["data_vendors"] = {
    "core_stock_apis": "yfinance",        # Stock prices
    "technical_indicators": "yfinance",   # Technical analysis
    "fundamental_data": "alpha_vantage",  # Company fundamentals
    "news_data": "alpha_vantage",         # News and sentiment
}

See Configuration Guide for all available options.

Next Steps

Troubleshooting

Common Issues

API Rate Limits

If you hit rate limits, the framework will automatically save partial analysis state. Wait for the suggested retry time and re-run.

Missing API Keys

Ensure environment variables are set:

echo $OPENAI_API_KEY
echo $ALPHA_VANTAGE_API_KEY

Import Errors

Ensure you're in the correct virtual environment:

conda activate tradingagents  # or source venv/bin/activate

Data Vendor Errors

Check your Alpha Vantage API key is valid and has remaining quota. Free tier allows 25 requests/day; TradingAgents users get 60 requests/minute.

Getting Help

Happy trading!