In today’s world of AI, agents are becoming powerful tools to automate and simplify complex tasks, ranging from chatbots to interactive storytelling. Flowise is a no-code AI workflow builder that makes designing, deploying, and managing AI agents for various applications easy. This is currently deployed to my local but can be deployed on the cloud.
In this blog, we’ll walk you through creating an AI storytelling agent using Flowise. Our example features a delightful story about a robot named IBM and his hilarious marshmallow party adventure. Let’s dive in!
What Are AI Agents in Flowise?
AI agents in Flowise are intelligent modules that can handle tasks autonomously by combining logic, AI models, and external tools. These agents can process inputs, make decisions, and generate tailored outputs. We are using the supervisor and worker nodes with OpenAPI chat
In this case, our AI agent will act as a storyteller for kids, generating imaginative stories based on specific themes or prompts.
How to Build an AI Storytelling Agent
Here’s a step-by-step guide to creating a storytelling AI agent like the one shown in the Flowise workflow screenshot.
Step 1: Setting Up Flowise
- Install Flowise:
- Download and install Flowise by following the npm install flowise , npx flowise run.
- Once installed, log in to access the interactive canvas.
- Create a New Workflow:
- Click “New Workflow” to begin creating your AI agent.
Step 2: Designing the AI Storytelling Agent
To make your AI storytelling agent functional, you’ll need the following nodes and configurations:
1. Chat Model Node
- Drag and drop a ChatOpenAI Node to the canvas.
- Configure it with your preferred AI model, such as GPT-4.
- Adjust parameters for creativity:
- Temperature: Set to a higher value (e.g., 0.9) to encourage more imaginative outputs.
- Max Tokens: Limit the response length as needed for short stories (e.g., 400–500 words).
2. Storytelling Agent (Worker Node)
- Add a Worker Node and connect it to the Chat Model.
- Set this node’s role as the Storyteller.
- In the Worker Prompt, include instructions for generating stories:”You are a storyteller. Write a fun and engaging story for kids aged 5–8. The main character is a robot named IBM. Make it funny, magical, and include a twist. Limit the story to 400 words.”
3. Title Assigner Agent (Worker Node)
- Add another Worker Node to create a title for the story.
- Connect it to the Storyteller Node.
- Set its prompt to extract a creative title from the generated story:”Extract the title of the story you just created. Keep it short and engaging.”
4. Output Formatter
- Use the Format Prompt Values Node to combine the story and title into a final output.
- Example format:cssCopyEdit
Title: {Title Extracted} Story: {Generated Story}
5. Chat Output
- Connect the formatted output to the Chat Output Node to display the story and title to users.
Step 3: Running the AI Agent
Once your nodes are configured and connected:
- Save your workflow and name it something like “AI Storytelling Agent.”
- Enter a prompt (or use the default storytelling instructions) to see the AI agent in action.
- Sit back as your agent generates an entertaining story for kids.
Example Output: IBM’s Marshmallow Party
Here’s an example of what your AI agent might generate:
Title: IBM the Robot and the Marshmallow Party
Once upon a time, in a land of giggles and sparkles, there lived a silly little robot named IBM. Now, IBM wasn’t your everyday robot who danced or painted; oh no! He was known as a “computer,” which is a magic box that helps people do all sorts of amazing things!
One sunny day, IBM decided to throw a party for all his robot friends. He said, “Let’s make it the best party ever! I’ll invite my buddy, Printer Pete, and my bestie, Codey the Coder!” But IBM accidentally ordered 1,000 bags of rainbow-colored marshmallows instead of snacks, and chaos ensued!
The party turned into a marshmallow-filled adventure with pillow fights, marshmallow towers, and lots of laughs. In the end, IBM and his friends agreed: whether it’s chips or marshmallows, any party is fun when friends are around!
Conclusion
Flowise enables you to design intelligent AI agents that can perform a wide range of tasks. In this example, we explored how to create an AI storytelling agent that generates engaging stories for kids. By combining the power of Flowise’s workflow nodes and the creativity of AI models, you can build interactive, dynamic tools that entertain and educate.
Leave a Reply