flutter_ai_provider_openai 0.1.0

OpenAI-compatible LlmProvider for flutter_ai: streams Chat Completions (text, tool calls, finish reasons) as flutter_ai_core AiStreamEvents over an injectable HTTP client.

flutter_ai_provider_openai

_{Streamed responses render through flutter_ai_elements (AiResponse).}

An OpenAI-compatible LlmProvider for the flutter_ai family.

Streams the OpenAI Chat Completions API and maps each chunk to flutter_ai_core AiStreamEvents — text deltas, streamed tool calls, and finish reasons. Works with the public OpenAI endpoint or any compatible server (Azure OpenAI, proxies, local servers) via a custom base URL.

Usage

import 'package:flutter_ai_provider_openai/flutter_ai_provider_openai.dart';

final provider = OpenAiProvider(
  apiKey: const String.fromEnvironment('OPENAI_API_KEY'),
  defaultModel: 'gpt-4o-mini',
);

// Drive it with flutter_ai_client's UseChatController:
final controller = UseChatController(provider: provider);
controller.sendText('Hello!');

Point it elsewhere with baseUrl:

OpenAiProvider(
  apiKey: key,
  baseUrl: Uri.parse('https://my-proxy.example.com/v1'),
);

The HTTP client is injectable (client:) for testing or custom transport.

Status

0.1.0. The request/response mapping is unit-tested against recorded SSE chunks; it has not been exercised against the live OpenAI API in this release. Depends on flutter_ai_core via a local path (publish_to: none) until that package is published.