Using OpenAI API for Natural Language Processing in JavaScript/

...

/

Generation

Generation

Learn how to use chat completions for generating new text and its practical use cases.

We'll cover the following...

Overview

The OpenAI models are also great at generating code and text as they have been trained on a large amount of data from different resources.

Press + to interact
Generation
Generation

We input the prompt text and request parameters into the OpenAI API's model to generate both text and code.

Press + to interact
Completions: text generation
Completions: text generation

Generate text

Now that we have learned about how OpenAI API’s model work, we can utilize the following prompt to generate new ideas about deep learning and images:

Brainstorm some ideas combining deep learning and images:

Example

Let’s try the above example in the code widget below:

Press + to interact
Please provide values for the following:
SECRET_KEY
Not Specified...
// Define endpoint URL here
const endpointUrl = "https://api.openai.com/v1/chat/completions";
// Define Header Parameters here
const headerParameters = {
  "Authorization": "Bearer {{SECRET_KEY}}",
  "Content-Type": "application/json"
};
// Body Parameters
const bodyParameters = JSON.stringify({
    model: "gpt-3.5-turbo",
    messages: [{ role: "system", content: "You are a helpful assistant." }],
    messages: [{ role: "user", content: "Brainstorm some ideas combining deep learning and images." }],
    temperature: 0.75,
    max_tokens: 200,
    top_p: 1.0,
    frequency_penalty: 1,
    presence_penalty: 1
});
// Set API call options
const options = {
  method: "POST",
  headers: headerParameters,
  body: bodyParameters
};
// Function to make API call
async function generateCompletion() {
  try {
    const response = await fetch(`${endpointUrl}`, options);
    // Print the  response
    printResponse(response);
  } catch (error) {
    // Print the  error message
    printError(error);
  }
}
// Call the function to make the API call.
generateCompletion();

In the code above, we use ...