Elevate Your Applications with the Llama 2 Chat Completion Cognitive Action

24 Apr 2025
Elevate Your Applications with the Llama 2 Chat Completion Cognitive Action

Integrating AI into your applications has never been easier, thanks to the meta/llama-2-7b-chat API. This API provides a powerful set of Cognitive Actions, specifically designed for generating coherent chat completions using the Llama 2 model—a state-of-the-art, 7 billion parameter language model from Meta. By leveraging these pre-built actions, developers can enhance user interaction, manage dialogue exchanges, and tailor responses to suit various contexts.

Prerequisites

Before you start integrating Llama 2 Cognitive Actions into your applications, ensure you have the following:

  • An API key to access the Cognitive Actions platform.
  • Basic understanding of JSON format for structuring requests and responses.
  • Familiarity with making HTTP requests in your programming environment, such as Python.

Authentication is typically handled via an API key that you will pass in the headers of your requests, ensuring that your application can securely interact with the Cognitive Actions API.

Cognitive Actions Overview

Generate Chat Completion with Llama 2

This action utilizes the Llama 2 model to generate chat completions based on provided prompts. It is particularly adept at managing dialogue and can be customized through system prompts to ensure safe and helpful responses.

  • Category: Text Generation

Input

The input for this action requires the following fields:

  • prompt (required): The text prompt to generate a response.
  • topP (optional): Sets the sampling threshold for the most likely tokens (default: 0.95).
  • temperature (optional): Controls the randomness of the output (default: 0.7).
  • maxNewTokens (optional): Maximum tokens to generate (default: 128).
  • minNewTokens (optional): Minimum tokens to generate (default: -1).
  • systemPrompt (optional): A guiding prompt that shapes the model's responses (default: "You are a helpful, respectful and honest assistant.").
  • repetitionPenalty (optional): Adjusts the repetition of tokens (default: 1.15).
  • stopSequences (optional): Specifies sequences where token generation should stop.
  • seed (optional): Random seed for reproducibility.
  • topK (optional): Samples from the top K most likely tokens (default: -1).
  • debug (optional): Enable debugging output (default: false).

Example Input:

{
  "topP": 1,
  "prompt": "Tell me how to tailor a men's suit so I look fashionable.",
  "temperature": 0.75,
  "maxNewTokens": 800,
  "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.\n\nIf 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
}

Output

The action will return a coherent response generated by the Llama 2 model based on the input prompt. Below is an example of what the output might look like:

Example Output:

Great question! Tailoring a men's suit can make a big difference in how fashionable and put-together you look. Here are some tips on how to tailor a men's suit to achieve a stylish and flattering look: 1. Take your measurements: Before you can tailor your suit, you need to take your measurements to ensure a proper fit. Measure your chest, waist, inseam, and arm length to give your tailor an accurate idea of your body shape. 2. Choose the right fabric: The fabric you choose for your suit will play a big role in how it looks and feels. Consider the season, your lifestyle, and your personal preferences when selecting the fabric. For example, a lightweight cotton or linen suit is perfect for summer, while a wool or cashmere suit is ideal for winter. 3. Adjust the jacket length: The jacket of your suit should hit you at the natural waistline, about an inch or two below the belly button. If you have a longer torso, you may want to have the jacket length adjusted to avoid looking too boxy. 4. Tailor the sleeves: Make sure the sleeves of your suit are the right length for your body. If they're too long, have them taken in to create a more tailored look. If they're too short, have them lengthened to avoid looking like a kid's suit. 5. Get the pants right: The pants of your suit should be tailored to fit your body perfectly. Make sure they're not too tight or too loose, and that the hem is level with the bottom of your shoe. 6. Add a personal touch: Consider adding some personal touches to your suit, such as a monogram or a subtle pattern. This will make your suit stand out and reflect your personal style. Remember, tailoring a men's suit is all about creating a flattering and stylish fit. Take your time, and work with your tailor to ensure that your suit is perfect. Happy tailoring!

Conceptual Usage Example (Python)

Here’s a conceptual Python code snippet demonstrating how to call the Cognitive Actions execution endpoint for generating chat completions:

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 = "1f755371-75c9-4a84-9b8f-599d057caba0" # Action ID for Generate Chat Completion with Llama 2

# Construct the input payload based on the action's requirements
payload = {
    "topP": 1,
    "prompt": "Tell me how to tailor a men's suit so I look fashionable.",
    "temperature": 0.75,
    "maxNewTokens": 800,
    "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.\n\nIf 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
}

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 YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload is structured to match the required input for generating a chat completion. The endpoint URL and request structure shown are illustrative and should be adjusted based on the actual API documentation you are working with.

Conclusion

The meta/llama-2-7b-chat Cognitive Action for generating chat completions is a powerful tool for developers looking to enhance user interaction through intelligent dialogue management. With customizable parameters, it allows for tailored responses that can fit a wide range of applications. As you explore these capabilities, consider the various use cases where chat completions could add value to your projects, from customer support bots to interactive storytelling apps. Happy coding!

← Back to All Articles