Harnessing Creativity: Integrating Text Generation with lucataco/freewilly2 Cognitive Actions

25 Apr 2025
Harnessing Creativity: Integrating Text Generation with lucataco/freewilly2 Cognitive Actions

In today’s digital landscape, leveraging AI for text generation can significantly enhance the user experience across applications. The lucataco/freewilly2 API provides a powerful action that allows developers to generate high-quality text using Stability AI's FreeWilly2 model. This action comes with customizable parameters that ensure outputs are both creative and accurate, making it an essential tool for developers looking to integrate intelligent text generation into their applications.

Prerequisites

Before diving into the integration of Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic familiarity with making HTTP requests and handling JSON data.

Authentication typically involves passing your API key in the headers of your requests to authenticate against the Cognitive Actions service.

Cognitive Actions Overview

Generate Text Using FreeWilly2

The Generate Text Using FreeWilly2 action allows you to leverage the capabilities of Stability AI’s FreeWilly2 model to generate text based on a given prompt and customizable parameters. This action is categorized under text-generation and is designed to produce creative and coherent text responses.

Input

The input for this action requires a JSON object that includes several parameters:

  • topP (number): Cumulative probability threshold for sampling tokens (default: 0.95). Range: 0.01 to 1.
  • prompt (string): The initial input to guide the AI's response (default: "Tell me about AI").
  • temperature (number): Controls randomness in token selection (default: 0.75). Range: 0 to 5.
  • maxNewTokens (integer): Maximum tokens to be generated (default: 512). Range: 1 to 4096.
  • systemPrompt (string): Guidelines for the AI’s behavior (default: a comprehensive assistant profile).
  • repetitionPenalty (number): Adjusts penalties for repeated words (default: 1.1). Range: 0 to 5.

Here is an example input JSON:

{
  "topP": 0.95,
  "prompt": "Tell me about AI",
  "temperature": 0.75,
  "maxNewTokens": 512,
  "systemPrompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
  "repetitionPenalty": 1.1
}

Output

The output of this action is a string containing the generated text based on the provided prompt and parameters. Here is an example of the expected output:

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines programmed to think like humans and mimic their actions. These machines can be designed to recognize patterns, understand language, learn from experience, and make decisions based on the data they process. AI has various applications, including image and speech recognition, natural language processing, robotics, and decision-making systems. The goal of AI research is to create intelligent agents that can perform tasks that typically require human intelligence, ultimately leading to more efficient and effective solutions for complex problems.</s>

Conceptual Usage Example (Python)

Here’s how you might call the Generate Text Using FreeWilly2 action using a hypothetical Cognitive Actions execution endpoint:

import requests
import json

# Replace with your Cognitive Actions API key and endpoint
COGNITIVE_ACTIONS_API_KEY = "YOUR_COGNITIVE_ACTIONS_API_KEY"
COGNITIVE_ACTIONS_EXECUTE_URL = "https://api.cognitiveactions.com/actions/execute" # Hypothetical endpoint

action_id = "3eb3f8ad-7778-453c-837e-02b7d67a8b2f" # Action ID for Generate Text Using FreeWilly2

# Construct the input payload based on the action's requirements
payload = {
    "topP": 0.95,
    "prompt": "Tell me about AI",
    "temperature": 0.75,
    "maxNewTokens": 512,
    "systemPrompt": "You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.",
    "repetitionPenalty": 1.1
}

headers = {
    "Authorization": f"Bearer {COGNITIVE_ACTIONS_API_KEY}",
    "Content-Type": "application/json"
}

try:
    response = requests.post(
        COGNITIVE_ACTIONS_EXECUTE_URL,
        headers=headers,
        json={"action_id": action_id, "inputs": payload} # Hypothetical structure
    )
    response.raise_for_status() # Raise an exception for bad status codes (4xx or 5xx)

    result = response.json()
    print("Action executed successfully:")
    print(json.dumps(result, indent=2))

except requests.exceptions.RequestException as e:
    print(f"Error executing action {action_id}: {e}")
    if e.response is not None:
        print(f"Response status: {e.response.status_code}")
        try:
            print(f"Response body: {e.response.json()}")
        except json.JSONDecodeError:
            print(f"Response body: {e.response.text}")

In this Python code snippet, you will replace the placeholders with your actual API key and the endpoint. The action_id corresponds to the specific action being called. The payload variable is constructed according to the action's input schema, ensuring that the parameters are set to optimize the text generation process.

Conclusion

Integrating the Generate Text Using FreeWilly2 action into your application can significantly enhance the interaction quality by providing intelligent and contextually relevant text generation. By customizing parameters like temperature and top P, you can tailor the AI's responses to meet specific needs. Explore the possibilities of this action to create engaging content, informative responses, and interactive experiences in your applications. Happy coding!

← Back to All Articles