Module de.seggebaeing.sqlanalyzer

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

Class ClaudePromptHandler

java.lang.Object

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

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

All Implemented Interfaces:

Promptable

public class ClaudePromptHandler
extends AbstractLLMHandler

Handles communication with the Anthropic Claude API. Builds the request payload, sends the HTTP request, processes the response, and returns the generated text. Supports error handling for rate limits and API-specific error messages.

Field Summary

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

client, gson

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method	Description
String	prompt(String input, String model, String apiKey, double temperature)	Sends a prompt request to the Claude API and returns the model's response text.

Methods inherited from class java.lang.Object

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

Constructor Details

ClaudePromptHandler

public ClaudePromptHandler()

Constructs a new ClaudePromptHandler instance, initializing the underlying HTTP client and JSON parser via the AbstractLLMHandler superclass.

Method Details

prompt

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

Sends a prompt request to the Claude API and returns the model's response text.

Builds and submits an HTTP request containing the user input, model name, API key, and temperature parameter. Handles HTTP errors and rate limits, parsing error messages or retry-after values where available.

Parameters:

input - the user input to be processed by the model

model - the Claude model identifier

apiKey - the API key used for authentication

temperature - the sampling temperature for response generation

Returns:

the text content of Claude's response

Throws:

LLMException - if the request fails, is rate limited, or the response is invalid