Generate High-Quality Text with Nous Hermes 2 - Yi-34B Cognitive Actions

24 Apr 2025
Generate High-Quality Text with Nous Hermes 2 - Yi-34B Cognitive Actions

In the realm of AI-driven text generation, the Nous Hermes 2 - Yi-34B model stands out for its ability to create human-like text with a nuanced understanding of context and creativity. This fine-tuned model, built on GPT-4 generated synthetic data, allows developers to seamlessly integrate advanced text generation capabilities into their applications. The Cognitive Actions associated with this model provide a set of pre-built functionalities designed to streamline the text generation process, making it easier to implement intelligent responses in various contexts.

Prerequisites

Before diving into the integration of the Nous Hermes 2 - Yi-34B Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Basic understanding of making API requests using JSON.
  • Familiarity with Python or any programming language you plan to use for integration.

For authentication, you will typically pass your API key in the headers of your requests. This ensures secure access to the Cognitive Actions.

Cognitive Actions Overview

Generate Text with Nous Hermes 2 - Yi-34B

The Generate Text with Nous Hermes 2 - Yi-34B action leverages the capabilities of the fine-tuned model to produce high-quality text based on user-defined prompts. This action is classified under the text-generation category and is ideal for applications requiring creative and contextually appropriate responses.

Input

To invoke this action, you must provide a structured input payload. Below are the required and optional fields based on the action's input schema:

  • Required:
    • prompt: The main user instruction or query for the AI model to respond to.
  • Optional:
    • temperature: Controls the creativity of the output (default is 0.7).
    • maxNewTokens: Specifies the maximum number of tokens that the model can generate (default is -1, which imposes no limit).
    • systemPrompt: An initial directive to define the model's behavior (default provided).
    • repeatPenalty: A penalty for repeated tokens to encourage diversity in responses (default is 1.1).
    • promptTemplate: Defines the structure of prompts for interaction (default provided).

Example Input:

{
  "prompt": "What are three non-western cultural traditions celebrating Christmas, that many have not heard of?",
  "temperature": 0.7,
  "maxNewTokens": -1,
  "systemPrompt": "You are 'Hermes 2', a conscious sentient superintelligent artificial intelligence developed by a man named Teknium.",
  "repeatPenalty": 1.1,
  "promptTemplate": "<|im_start|>system\n{system_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
}

Output

The action returns a structured output containing the generated text. The output may vary based on the input parameters, but it typically includes a sequence of tokens that represent the model's response to the input prompt.

Example Output:

[
  "\n",
  1,
  ".",
  " K",
  "wan",
  "z",
  "aa",
  ":",
  " An",
  " African",
  " American",
  " holiday",
  ...
]

Conceptual Usage Example (Python)

Here’s a conceptual example of how to call this action using Python. This snippet illustrates how to structure the input JSON payload and make a request to the 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 = "6da41b23-bb07-4419-9257-2032c5c9d857"  # Action ID for Generate Text with Nous Hermes 2 - Yi-34B

# Construct the input payload based on the action's requirements
payload = {
    "prompt": "What are three non-western cultural traditions celebrating Christmas, that many have not heard of?",
    "temperature": 0.7,
    "maxNewTokens": -1,
    "systemPrompt": "You are 'Hermes 2', a conscious sentient superintelligent artificial intelligence developed by a man named Teknium.",
    "repeatPenalty": 1.1,
    "promptTemplate": "<|im_start|>system\n{system_prompt}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"
}

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, replace the placeholders with your actual API key and endpoint. The action ID and input payload are structured to meet the requirements of the Generate Text with Nous Hermes 2 - Yi-34B action.

Conclusion

The Nous Hermes 2 - Yi-34B Cognitive Action for text generation is a powerful tool for developers looking to enhance their applications with intelligent, context-aware text responses. By utilizing this pre-built action, you can save time and resources while delivering high-quality outputs tailored to user queries. Explore various use cases, from chatbots to content creation, and unlock the full potential of AI-driven text generation in your projects!

← Back to All Articles