Enhance Your Applications with the InternLM2.5 Chat Model Cognitive Actions

22 Apr 2025
Enhance Your Applications with the InternLM2.5 Chat Model Cognitive Actions

The InternLM2.5 Chat Model is a powerful tool designed to facilitate text generation and interaction across various domains. With its advanced reasoning capabilities and a substantial 1 million context window, this model provides excellent performance for practical applications in chatbots, content generation, and more. By leveraging the pre-built Cognitive Actions, developers can easily integrate sophisticated text generation features into their applications without needing to build complex models from scratch.

Prerequisites

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

  • An API key for the Cognitive Actions platform to authenticate your requests.
  • Familiarity with JSON structures, as you will be working with JSON payloads to interact with the API.

Authentication typically involves passing your API key in the request headers to validate access to the Cognitive Actions service.

Cognitive Actions Overview

Utilize InternLM2.5 Chat Model

The Utilize InternLM2.5 Chat Model action enables interaction with the InternLM2.5 chat model. This action excels in text generation and reasoning tasks, making it ideal for applications that require nuanced and contextually relevant responses.

Input

The input for this action is structured as follows:

  • topK: (integer) The number of highest probability tokens to consider for output generation. Default is 50.
  • topP: (number) A probability threshold for output generation. Default is 0.9.
  • prompt: (string) The input text or question guiding the model's output.
  • maxTokens: (integer) The maximum number of tokens to generate. Default is 512.
  • minTokens: (integer) The minimum number of tokens to generate. Default is 0.
  • temperature: (number) Controls randomness in token selection. Default is 0.6.
  • systemPrompt: (string) A directive to guide the model's behavior. Default is "You are a helpful assistant."
  • stopSequences: (string) A comma-separated list of sequences that will stop the generation process.
  • presencePenalty: (number) Reduces the likelihood of generating tokens based on their presence in the text. Default is 0.
  • frequencyPenalty: (number) Reduces the likelihood of generating tokens based on their cumulative frequency. Default is 0.

Example Input:

{
  "topK": 50,
  "topP": 0.9,
  "prompt": "please provide three suggestions about time management",
  "maxTokens": 512,
  "minTokens": 0,
  "temperature": 0.6,
  "systemPrompt": "You are a helpful assistant.",
  "presencePenalty": 0,
  "frequencyPenalty": 0
}

Output

The output from this action typically returns a list of tokens that form the generated text. For example, when prompted for suggestions about time management, the model might return:

[
  "Certainly!",
  " Here are three suggestions for effective time management:\n\n",
  "1. **Prioritize Tasks**: Start by identifying the most important tasks...",
  "2. **Set Specific Goals**: Define clear, achievable goals...",
  "3. **Use Time-Blocking Techniques**: Allocate specific blocks of time..."
]

Conceptual Usage Example (Python)

Here's how you might interact with the InternLM2.5 Chat Model using a hypothetical Cognitive Actions execution endpoint in Python:

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 = "d8823dc2-f97a-457c-8e92-acc65e483375"  # Action ID for Utilize InternLM2.5 Chat Model

# Construct the input payload based on the action's requirements
payload = {
    "topK": 50,
    "topP": 0.9,
    "prompt": "please provide three suggestions about time management",
    "maxTokens": 512,
    "minTokens": 0,
    "temperature": 0.6,
    "systemPrompt": "You are a helpful assistant.",
    "presencePenalty": 0,
    "frequencyPenalty": 0
}

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, you can see how to structure your request, including the action ID and input payload. The endpoint URL and request structure are illustrative and should be adapted to your specific API.

Conclusion

Integrating the InternLM2.5 Chat Model into your applications can significantly enhance your text generation capabilities. With features like nuanced reasoning and context-aware responses, you can create engaging and intelligent applications. Consider exploring various use cases, from chatbots to content creation, leveraging this powerful Cognitive Action to provide value to your users.

← Back to All Articles