Unlocking Text Generation Capabilities with OpenHermes-2.5-Mistral-7B Cognitive Actions

24 Apr 2025
Unlocking Text Generation Capabilities with OpenHermes-2.5-Mistral-7B Cognitive Actions

In the realm of AI-driven text generation, the OpenHermes-2.5-Mistral-7B model stands out with its robust capabilities. This model allows developers to generate intelligent text predictions, making it an invaluable tool for applications that require dynamic content generation. With customizable parameters, these pre-built Cognitive Actions can enhance the interactivity and responsiveness of applications, enabling a wide range of use cases from chatbots to content creation.

Prerequisites

To leverage the Cognitive Actions provided by OpenHermes-2.5-Mistral-7B, you will need the following:

  • API Key: An access key to authenticate requests to the Cognitive Actions platform.
  • Basic Setup: Familiarity with making HTTP requests and handling JSON data.

Authentication typically involves passing your API key in the headers of your request, ensuring that your application can securely access the Cognitive Actions.

Cognitive Actions Overview

Generate Text Prediction

The Generate Text Prediction action utilizes the OpenHermes-2.5-Mistral-7B model to produce text outputs based on a given prompt. It offers several customizable parameters that allow developers to fine-tune the output to meet specific needs.

  • Category: Text Generation
  • Purpose: Generate coherent and contextually relevant text based on a structured prompt.

Input

The input for this action requires a JSON object with the following fields:

  • prompt (required): A JSON string representing an array of message objects. Each object should include a 'role' (e.g., 'system' or 'user') and 'content'.
  • topK (optional): An integer that determines how many of the most likely tokens to consider during sampling. Default is 50.
  • topP (optional): A floating-point number that specifies the proportion of likely tokens to sample from. Default is 0.9.
  • temperature (optional): A floating-point number that controls the randomness of the generated text. Default is 0.75.
  • maxNewTokens (optional): An integer defining the maximum number of new tokens to generate. Default is 512.

Example Input:

{
  "topK": 50,
  "topP": 0.9,
  "prompt": "[{\"role\": \"system\", \"content\": \"You are a helpful assistant.\"}, {\"role\": \"user\", \"content\": \"What is Slite?\"}]",
  "temperature": 0.75,
  "maxNewTokens": 512
}

Output

The output is an array of strings, each representing a token generated based on the input prompt. The generated text can vary in length and content, depending on the prompt and parameters used.

Example Output:

[
  "",
  "",
  "Slite ",
  "is ",
  "a ",
  ...
  "and ",
  "integration ",
  "with ",
  "other ",
  "productivity ",
  "tools ",
  "like ",
  "Google ",
  "Drive ",
  "and ",
  "Trello."
]

Conceptual Usage Example (Python)

Below is a conceptual Python code snippet that demonstrates how to call the Generate Text Prediction action using the Cognitive Actions 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 = "4d65b955-9665-4d91-9af8-2671310f1364"  # Action ID for Generate Text Prediction

# Construct the input payload based on the action's requirements
payload = {
    "topK": 50,
    "topP": 0.9,
    "prompt": "[{\"role\": \"system\", \"content\": \"You are a helpful assistant.\"}, {\"role\": \"user\", \"content\": \"What is Slite?\"}]",
    "temperature": 0.75,
    "maxNewTokens": 512
}

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 corresponds to the Generate Text Prediction action. The payload is structured according to the required input fields. This example shows how to handle the HTTP request and manage potential errors effectively.

Conclusion

The Cognitive Actions provided by OpenHermes-2.5-Mistral-7B empower developers to integrate sophisticated text generation capabilities into their applications. By customizing parameters such as temperature and token sampling, you can achieve focused and diverse outputs tailored to your specific needs. Whether building chatbots, content generators, or intelligent assistants, these tools offer immense potential for enhancing user experiences. Explore the possibilities and start integrating these actions into your projects today!

← Back to All Articles