pipecat/examples/aws-strands/README.md

AWS Strands Examples

This folder contains two Python examples demonstrating how to use Pipecat with the AWS Strands agent.

Overview

These examples show how to delegate complex, multi-step tasks to a Strands agent, which can reason step-by-step and call tools to accomplish user requests.

These examples are intentionally simplified for demonstration, using mock API calls. They work best if you ask it:

What's the weather where the Golden Gate Bridge is?

Example Scripts

black-box.py

A minimal example that demonstrates how to use the Strands agent with Pipecat. The agent can handle multi-step queries by calling tools, but does not explain its reasoning out loud.

explain-thinking.py

An enhanced example where the Strands agent explains each step of its reasoning in clear, simple language as it works through a multi-step task.

Quick Start

1. Clone the repository and navigate to this example:

   git clone https://github.com/pipecat-ai/pipecat.git
   cd pipecat/examples/aws-strands
   

2. Set up a virtual environment:

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

3. Install dependencies:

   pip install -r requirements.txt
   

4. Configure environment variables:

   Copy the provided env.example file to .env and fill in the necessary credentials:

   cp env.example .env
   # Then edit .env with your preferred editor
   

5. Run an example:

   python black-box.py
   # or
   python explain-thinking.py