Generate Captivating Text with the Neuromancer-13b Cognitive Actions

22 Apr 2025
Generate Captivating Text with the Neuromancer-13b Cognitive Actions

In the world of artificial intelligence and natural language processing, the ability to generate text that mimics a particular style or tone is a powerful tool. The fofr/neuromancer-13b API offers developers a unique set of capabilities through its Cognitive Actions, specifically designed to leverage a fine-tuned model for generating text in the style of Neuromancer. This blog post will guide you through the process of integrating this exciting feature into your applications, enhancing your content creation with a touch of literary flair.

Prerequisites

Before diving into the integration, here are the general requirements for using the Neuromancer-13b Cognitive Actions:

  • API Key: You’ll need an API key from the Cognitive Actions platform to authenticate your requests.
  • Set Up: Ensure you have the necessary development environment set up, including Python and the requests library for making HTTP calls.

Authentication typically involves passing your API key in the request headers, allowing you to interact securely with the Cognitive Actions service.

Cognitive Actions Overview

Generate Neuromancer Style Text

The Generate Neuromancer Style Text action uses the fine-tuned llama-13b-base model to produce text that emulates the distinctive style of Neuromancer. This action is particularly useful for developers looking to enrich their applications with creative text generation capabilities.

Input

The input for this action requires the following fields:

  • prompt (string, required): The text or command prompt provided to guide the model in generating responses.
  • topK (integer, optional): Limits sampling to the top K most probable tokens (default: 50).
  • topP (number, optional): Limits sampling to the top P percentage of most probable tokens (default: 0.9).
  • temperature (number, optional): Controls randomness in text generation (default: 0.75).
  • maxNewTokens (integer, optional): Specifies the maximum number of tokens to generate (default: 128).
  • minNewTokens (integer, optional): Specifies the minimum number of tokens to generate (default: -1).
  • stopSequences (string, optional): Defines sequences at which text generation will terminate.
  • seed (integer, optional): Random seed for generating outputs.
  • debug (boolean, optional): Enables detailed logging output for debugging purposes.
  • tuningWeights (string, optional): Path to the fine-tuned model weights.

Here’s an example input JSON payload for invoking this action:

{
  "topK": 55,
  "topP": 0.9,
  "debug": false,
  "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
  "temperature": 0.75,
  "maxNewTokens": 1000,
  "minNewTokens": 100,
  "stopSequences": "[/NEUROMANCED]"
}

Output

The output of this action typically returns a text response generated in the Neuromancer style. Here’s an example of the expected output:

The caffeine was running low. He checked his credit. No more money until tomorrow. His eyes ached from too much time on the screen. He could do with a cup right now. But he'd have to wait till payday.

Conceptual Usage Example (Python)

Here's a conceptual Python code snippet demonstrating how to call the Generate Neuromancer Style Text action using the Cognitive Actions API:

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 = "aeb923db-0b42-42cb-afbf-aedf9e8584f8" # Action ID for Generate Neuromancer Style Text

# Construct the input payload based on the action's requirements
payload = {
    "topK": 55,
    "topP": 0.9,
    "debug": False,
    "prompt": "Given the following input, rewrite it in the style of neuromancer:\n[TO_NEURO_REWRITE] John needed coffee. [/TO_NEURO_REWRITE]\n[NEUROMANCED] ",
    "temperature": 0.75,
    "maxNewTokens": 1000,
    "minNewTokens": 100,
    "stopSequences": "[/NEUROMANCED]"
}

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 code snippet:

  • Replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key.
  • The action_id is set to the ID of the Generate Neuromancer Style Text action.
  • The payload is structured according to the action's input schema.

Conclusion

The Neuromancer-13b Cognitive Actions provide a remarkable opportunity for developers to harness advanced text generation capabilities. By implementing these actions, you can elevate your applications with rich, stylistic content that captures the essence of classic literature. Whether you're creating chatbots, content generators, or interactive storytelling platforms, integrating these features can significantly enhance user experience. Start experimenting today, and let your creativity flow!

← Back to All Articles