Module de.seggebaeing.sqlanalyzer

Package de.seggebaeing.sqlanalyzer.logic.promptable.impl.llm

Class OpenAIPromptHandler

java.lang.Object

de.seggebaeing.sqlanalyzer.logic.promptable.impl.llm.AbstractLLMHandler

de.seggebaeing.sqlanalyzer.logic.promptable.impl.llm.OpenAIPromptHandler

All Implemented Interfaces:

Promptable

public class OpenAIPromptHandler
extends AbstractLLMHandler

Handler for interacting with the OpenAI Chat Completions API.

This class builds and sends requests to the OpenAI endpoint using the provided API key, model, and prompt data. It parses responses to extract the generated message text and handles rate-limiting or error responses.

Field Summary

Fields inherited from class de.seggebaeing.sqlanalyzer.logic.promptable.impl.llm.AbstractLLMHandler

client, gson

Constructor Summary

Constructors

Constructor	Description
OpenAIPromptHandler()	Constructs a new OpenAIPromptHandler, initializing the underlying HTTP client and JSON parser via the superclass.

Method Summary

Modifier and Type	Method	Description
String	prompt(String input, String model, String apiKey, double temperature)	Sends the given input prompt to the OpenAI Chat Completions API and returns the generated response content.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

OpenAIPromptHandler

public OpenAIPromptHandler()

Constructs a new OpenAIPromptHandler, initializing the underlying HTTP client and JSON parser via the superclass.

Method Details

prompt

public String prompt(String input,
 String model,
 String apiKey,
 double temperature)
              throws LLMException

Sends the given input prompt to the OpenAI Chat Completions API and returns the generated response content.

Parameters:

input - the user input text to be sent to the model

model - the OpenAI model identifier (e.g., "gpt-4o-mini")

apiKey - the API key used for authentication

temperature - the sampling temperature controlling randomness

Returns:

the generated response text from the model

Throws:

LLMException - if the API call fails, returns an error, or the response cannot be parsed