Build Multi-Agent Workflows in Minutes: A Beginner's Guide to Rowboat

Tired of complex coding when building multi-agent systems? Rowboat uses AI to create multi-agent workflows from scratch, revolutionizing how you approach complex tasks. Forget spending hours on setup – Rowboat lets you focus on the results, streamlining your development process and boosting productivity.

What is Rowboat and Why Should You Use It?

Rowboat leverages OpenAI's Agents SDK to provide the fastest way to build multi-agent systems. Imagine describing your ideal agent workflow – for example, "Build an assistant for a food delivery company to handle delivery status and missing items." Rowboat turns that idea into reality.

Here's why Rowboat should be your go-to tool:

• AI-Powered Workflow Generation: Describe your desired outcome, and Rowboat builds the underlying multi-agent workflow.
• Fast Development: Launch fully functional, multi-agent systems in minutes.
• Simplified Integration: Seamlessly integrate with your application using the HTTP API or Python SDK.

Getting Started with Rowboat: A Step-by-Step Guide

Ready to dive in and experience the power of AI-driven multi-agent systems? Here is a quick start guide:

1. Set Up Your OpenAI Key:

• First, you need an OpenAI API key. Set it up in your environment:

  export OPENAI_API_KEY=your-openai-api-key
  

  Copy

2. Clone and Start Rowboat:

• Clone the Rowboat repository and start the Docker container.

  git clone [email protected]:rowboatlabs/rowboat.git
  cd rowboat
  docker-compose up --build
  

  Copy

• Access the application in your browser at http://localhost:3000.

With Rowboat running, you're ready to build.

Integrating Rowboat Agents into Your Applications

Rowboat offers flexible integration options to suit your development needs. Choose between the HTTP API for direct access and the Python SDK for a more programmatic approach.

Option 1: Using the HTTP API

• Access the API documentation at http://localhost:3000/api/v1/ for detailed information.

• Use curl to send requests. Here's an example that gets the weather in London:

  curl --location 'http://localhost:3000/api/v1/<PROJECT_ID>/chat' \
  --header 'Content-Type: application/json' \
  --header 'Authorization: Bearer <API_KEY>' \
  --data '{
  "messages": [
  {
  "role": "user",
  "content": "tell me the weather in london in metric units"
  }
  ],
  "state": null
  }'
  

  Copy

Remember to replace <PROJECT_ID> and <API_KEY> with your specific credentials found in settings.

Option 2: Using the Python SDK

• The Python SDK provides a convenient way to interact with Rowboat agents. Here’s a quick example:

  from rowboat import Client, StatefulChat
  from rowboat.schema import UserMessage, SystemMessage
  
  # Initialize the client
  client = Client(
  host="http://localhost:3000",
  project_id="<PROJECT_ID>",
  api_key="<API_KEY>"
  )
  
  # Create a stateful chat session (recommended)
  chat = StatefulChat(client)
  response = chat.run("What's the weather in London?")
  print(response)
  
  # Or use the low-level client API
  messages = [
  SystemMessage(role='system', content="You are a helpful assistant"),
  UserMessage(role='user', content="Hello, how are you?")
  ]
  
  # Get response
  response = client.chat(messages=messages)
  print(response.messages[-1].content)
  

  Copy

• Make sure to install the rowboat package. Update the host, project ID, and API key with your credentials.

Simplify Multi-Agent System Development with Rowboat

Rowboat significantly accelerates the development process for multi-agent workflows. Whether you're building a customer service chatbot or automating complex business operations, Rowboat's intuitive interface and powerful AI engine empower you to get the job done faster. Build your first multi-agent workflow today! Consult the full documentation to explore all the features and options available.