Generate High-Quality Text Effortlessly with the Yi-6B Cognitive Actions

24 Apr 2025
Generate High-Quality Text Effortlessly with the Yi-6B Cognitive Actions

In the rapidly evolving landscape of artificial intelligence, the ability to generate human-like text has become a cornerstone of many applications. The Yi-6B Cognitive Actions, part of the 01-ai/yi-6b spec, are designed to leverage the advanced capabilities of the Yi-6B large language model developed by 01.AI. These pre-built actions allow developers to integrate robust text generation functionalities into their applications without needing to build complex models from scratch.

With these actions, you can create diverse, contextually relevant text outputs based on your input prompts, enabling innovative use cases in chatbots, content creation, and more.

Prerequisites

Before you can start using the Yi-6B Cognitive Actions, ensure you have the following:

  • An API key for accessing the Cognitive Actions platform.
  • Familiarity with making HTTP requests, particularly POST requests, to interact with the API.

Authentication typically involves including your API key in the request headers. This key will grant you access to the action functionalities provided by the Yi-6B model.

Cognitive Actions Overview

Generate Text with Yi-6B Model

The Generate Text with Yi-6B Model action allows you to harness the power of the Yi-6B model to produce high-quality text based on your input prompts. The action supports various customization options, such as token filtering and output dynamics, to ensure that the generated text meets your specific needs.

Input

The input for this action is structured as follows:

  • prompt (required): The initial input prompt that provides context or a question for the model to respond to.
  • topK (optional): The number of highest probability tokens to consider for generating the output. Default is 50.
  • topP (optional): A probability threshold for output generation, defaulting to 0.95.
  • temperature (optional): Controls randomness in the output. Default is 0.8.
  • maxNewTokens (optional): The maximum number of tokens the model can generate, with a default of 512.
  • promptTemplate (optional): Allows for formatting the input prompt, using the placeholder {prompt}.
  • presencePenalty (optional): A penalty for using tokens that have already appeared in the text, default is 0.
  • frequencyPenalty (optional): A penalty for repeating tokens frequently, also defaulting to 0.

Here's an example input JSON payload for this action:

{
  "topK": 50,
  "topP": 0.95,
  "prompt": "Question: I had 3 apples and I ate 1. How many apples do I have left?\nAnswer:",
  "temperature": 0.9,
  "maxNewTokens": 64,
  "promptTemplate": "{prompt}",
  "presencePenalty": 1,
  "frequencyPenalty": 1
}

Output

The output of this action typically returns an array of tokens that make up the generated text. For instance, given the example input, the output might look like this:

[
  " I",
  " have",
  " ",
  3,
  " –",
  " ",
  1,
  " =",
  " ",
  2,
  " apples",
  ".",
  ""
]

This output can be processed further to form coherent sentences or paragraphs.

Conceptual Usage Example (Python)

To invoke the Generate Text with Yi-6B Model, a developer might use the following conceptual Python code snippet:

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 = "68e13c49-24bb-4c8d-8058-8e1350f14160" # Action ID for Generate Text with Yi-6B Model

# Construct the input payload based on the action's requirements
payload = {
    "topK": 50,
    "topP": 0.95,
    "prompt": "Question: I had 3 apples and I ate 1. How many apples do I have left?\nAnswer:",
    "temperature": 0.9,
    "maxNewTokens": 64,
    "promptTemplate": "{prompt}",
    "presencePenalty": 1,
    "frequencyPenalty": 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 example, replace YOUR_COGNITIVE_ACTIONS_API_KEY with your actual API key. The payload variable holds the structured input for the action, and the response is handled to display the generated text.

Conclusion

The Yi-6B Cognitive Actions provide a powerful and flexible way to integrate text generation capabilities into your applications. By leveraging the advanced features of the Yi-6B model, developers can create engaging and contextually relevant outputs that enhance user interactions.

Consider experimenting with different parameters, such as temperature and maxNewTokens, to tailor the text generation to your specific use cases. With these tools at your disposal, the possibilities for innovation are endless!

← Back to All Articles