Function call_openai

pub async fn call_openai(
    prompt: &str,
    model: &str,
    max_token: u32,
) -> Result<String, Box<dyn Error>>

Sends a prompt to the OpenAI chat API and returns the generated response as a string.

This function uses the async-openai crate to interact with a chat completion endpoint (e.g., GPT-4, GPT-4o, GPT-3.5-turbo). The base URL can be overridden via the OPENAI_BASE_URL environment variable.

Arguments

• prompt - The text prompt to send to the model.
• model - The model ID to use (e.g., "gpt-4o", "gpt-3.5-turbo").
• max_token - Maximum number of tokens allowed in the response.

Returns

A Result containing the generated string response on success, or an error on failure.

Errors

This function will return an error if the request fails, the environment variable is misconfigured, or if the response cannot be parsed correctly.

Example

use git_commit_helper::call_openai;

#[tokio::main]
async fn main() {
    let prompt = "Summarize the following diff...";
    let model = "gpt-4o";
    let max_token = 2048;

    match call_openai(prompt, model, max_token).await {
        Ok(response) => println!("LLM response: {}", response),
        Err(e) => eprintln!("Error calling OpenAI: {}", e),
    }
}