DSPy: Chain-of-Thought vs ReAct

This example demonstrates how to implement the same "math tutor" task with two different prompting strategies in DSPy:

1. A Chain-of-Thought (CoT) module that reasons step by step.
2. A ReAct agent that can call a calculator tool while reasoning.

Requirements

• Python 3.6+
• An OpenAI API key

Steps for running this example in the shell

1. Install dependencies:

python -m venv .venv

# macOS/Linux:
source .venv/bin/activate

# Windows Command Prompt:
.venv\Scripts\activate.bat

# Windows PowerShell:
.venv\Scripts\Activate.ps1

pip install -r requirements.txt

2. Export your OpenAI API key as an environment variable:

export OPENAI_API_KEY="sk-..." # Windows cmd: set OPENAI_API_KEY="sk-..." # Windows PowerShell: $env:OPENAI_API_KEY="sk-..."

3. Run the script:

python dspy_cot_vs_react.py

Output

When you run the script, it will execute both the Chain-of-Thought and ReAct strategies and print their results and reasoning/trajectory.