ballerinax/ai.openai Ballerina library

Overview

OpenAI provides powerful AI models for natural language processing, image generation, and other advanced tasks.

The OpenAI connector offers APIs for connecting with OpenAI Large Language Models (LLMs), enabling the integration of advanced conversational AI, text generation, and language processing capabilities into applications.

Key Features

• Connect and interact with OpenAI Large Language Models (LLMs)
• Support for GPT-6, GPT-5, GPT-4.1, GPT-4o, and other advanced models
• Efficient handling of conversational prompts and completions
• Secure communication with API key authentication

Prerequisites

Before using this module in your Ballerina application, first you must obtain the nessary configuration to engage the LLM.

• Create an OpenAI account.
• Obtain an API key by following these instructions.

Quickstart

To use the ai.openai module in your Ballerina application, update the .bal file as follows:

Step 1: Import the module

Import the ai.openai; module.

import ballerinax/ai.openai;

Step 2: Intialize the Model Provider

Here's how to initialize the Model Provider:

import ballerina/ai;
import ballerinax/ai.openai;

final ai:ModelProvider openAiModel = check new openai:ModelProvider("openAiApiKey", modelType = openai:GPT_4O);

Note: Some models are restricted on the default Chat Completions API:

• O3_PRO, GPT_5_PRO, GPT_5_2_PRO, GPT_5_3_CODEX, GPT_5_4_PRO and GPT_5_5_PRO are available only with apiType = openai:RESPONSES.
• Tool calling and generate() with GPT_6_ASTRA, GPT_6_1_SOL and GPT_6_1_TERRA require apiType = openai:RESPONSES.
• Tool calling and generate() with the GPT_5_6 family, GPT_6_SOL and GPT_6_LUNA require reasoningEffort = openai:NONE, or apiType = openai:RESPONSES.

Step 4: Invoke chat completion

ai:ChatMessage[] chatMessages = [{role: "user", content: "hi"}];
ai:ChatAssistantMessage response = check openAiModel->chat(chatMessages, tools = []);

chatMessages.push(response);