globe_ai 1.0.3 copy "globe_ai: ^1.0.3" to clipboard
globe_ai: ^1.0.3 copied to clipboard

A Dart-first package for interacting with large language models (LLMs).

🧠 globe_ai #

globe_ai is a Dart-first package for interacting with large language models (LLMs) like OpenAI’s GPT series.

✨ Features #

  • πŸ“ generateText β€” basic prompt or messages based text generation

  • πŸ“‘ streamText β€” stream text responses as they’re generated

  • 🧱 generateObject β€” validate structured JSON output against a schema

  • 🌊 streamObject β€” stream and validate structured data

πŸš€ Installation #

Install Globe Runtime #

You can install globe runtime using either of these approaches.

  • Using Globe CLI.

    If you have Globe CLI installed locally, you can run globe runtime install.

  • Adding Manually to your Environment

    Download the libglobe_runtime dynamic library for your Platform from Github Release Pages and place it in ~/.globe/runtime/ directory.

Setup #

  • Add dependency
dependencies:
  globe_ai: ^<latest-version>
  • Configure your model provider (e.g. OpenAI, Google Generative AI):
final model = openai('gpt-4o');

or

final model = google('gemini-2.0-flash');

Usage #

πŸ”Ή Text Generation #

final result = await generateText(
  model: openai.chat('gpt-4o'),
  prompt: 'What is the capital of Ghana?',
);
print(result);

or

final textWithPdf = await generateText(
  model: openai.chat('gpt-4o', user: 'Chima'),
  messages: [
    OpenAIMessage(
      role: 'user',
      content: [
        OpenAIContent.text('What is the title of this book?'),
        OpenAIContent.file(
          File('bin/test_doc.pdf'),
          mimeType: 'application/pdf',
        ),
      ],
    ),
  ],
);
print(textWithPdf);

πŸ”Ή Streaming Text #

final stream = streamText(
  model: openai('o4-mini'),
  prompt: 'Describe the Mission burrito vs SF burrito debate.',
);

await for (final chunk in stream) {
  stdout.write(chunk);
}

πŸ”Ή Structured Object Generation #

final schema = l.schema({
  'recipe': l.schema({
    'name': l.string(),
    'ingredients': l.list(validators: [
      l.schema({'name': l.string(), 'amount': l.string()}),
    ]),
    'steps': l.list(validators: [l.string()]),
  })
});

final result = await generateObject<Map<String, dynamic>>(
  model: openai('gpt-4.1'),
  prompt: 'Generate a lasagna recipe.',
  schema: schema,
);

print(result['recipe']['name']);

πŸ”Ή Streaming Structured Objects #

final resultStream = streamObject<Map<String, dynamic>>(
  model: openai('gpt-4.1'),
  prompt: 'Generate a lasagna recipe.',
  schema: schema,
);

await for (final chunk in resultStream) {
  print(chunk); // Validated partial output
}

πŸ“š Roadmap #

  • 🌐 Outside-Globe support β€” Coming soon

  • πŸ€– Additional model providers β€” In progress

  • πŸ§ͺ Unit tests & CI examples

  • πŸ“– Function-level API docs

πŸ› οΈ Development #

  • Building the JS package

    dart pub run rps build
    
  • Generate types from protos

    dart pub run rps gen_dart
    

    and

    dart pub run rps gen_typescript
    
5
likes
140
points
202
downloads

Publisher

unverified uploader

Weekly Downloads

A Dart-first package for interacting with large language models (LLMs).

Repository (GitHub)
Contributing

Documentation

API reference

License

Apache-2.0 (license)

Dependencies

globe_runtime, luthor, path, protobuf, version

More

Packages that depend on globe_ai