ollama_dart 1.3.0

Dart client for the Ollama API to run LLMs locally (OpenAI gpt-oss, DeepSeek-R1, Gemma 3, Llama 4, and more).

Ollama Dart Client

Dart client for the Ollama API to run LLMs locally (OpenAI gpt-oss, DeepSeek-R1, Gemma 3, Llama 4, and more).

Table of Contents

• Features
• Why choose this client?
• Quickstart
• Installation
• Configuration
• Usage
• Examples
• API Coverage
• Development
• License

Features

Generation & Streaming

• ✅ Text generation (generate)
• ✅ Chat completions (chat)
• ✅ Streaming support with NDJSON
• ✅ Tool/function calling
• ✅ Thinking mode (reasoning)
• ✅ Structured output (JSON mode and JSON schema)
• ✅ Multimodal support (images)
• ✅ Context memory for conversation continuity

Embeddings

• ✅ Generate embeddings (embed)

Model Management

• ✅ List local models (list)
• ✅ Show model details (show)
• ✅ Pull models from library (pull)
• ✅ Push models to library (push)
• ✅ Create models from Modelfile (create)
• ✅ Copy models (copy)
• ✅ Delete models (delete)
• ✅ List running models (ps)
• ✅ Get server version (version)

Why choose this client?

• ✅ Type-safe with sealed classes
• ✅ Minimal dependencies (http, logging only)
• ✅ Works on all compilation targets (native, web, WASM)
• ✅ Interceptor-driven architecture
• ✅ Comprehensive error handling
• ✅ Automatic retry with exponential backoff
• ✅ NDJSON streaming support

Quickstart

import 'package:ollama_dart/ollama_dart.dart';

void main() async {
  final client = OllamaClient();

  // Chat completion
  final response = await client.chat.create(
    request: ChatRequest(
      model: 'gpt-oss',
      messages: [
        ChatMessage.user('Hello, how are you?'),
      ],
    ),
  );

  print(response.message?.content);

  client.close();
}

Installation

dependencies:
  ollama_dart: ^x.y.z

Configuration

Configuration Options

import 'package:ollama_dart/ollama_dart.dart';

// From environment variables (reads OLLAMA_HOST, defaults to localhost:11434)
final client = OllamaClient.fromEnvironment();

// Or with explicit configuration
final clientWithConfig = OllamaClient(
  config: OllamaConfig(
    baseUrl: 'http://localhost:11434',  // Default Ollama server
    timeout: Duration(minutes: 5),
    retryPolicy: RetryPolicy(
      maxRetries: 3,
      initialDelay: Duration(seconds: 1),
    ),
  ),
);

Authentication (for remote Ollama servers):

final client = OllamaClient(
  config: OllamaConfig(
    baseUrl: 'https://my-ollama-server.example.com',
    authProvider: BearerTokenProvider('YOUR_TOKEN'),
  ),
);

Usage

Chat Completions

Chat Completions Example

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

final response = await client.chat.create(
  request: ChatRequest(
    model: 'gpt-oss',
    messages: [
      ChatMessage.system('You are a helpful assistant.'),
      ChatMessage.user('What is the capital of France?'),
    ],
  ),
);

print(response.message?.content);
client.close();

Streaming

Streaming Example

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

final stream = client.chat.createStream(
  request: ChatRequest(
    model: 'gpt-oss',
    messages: [
      ChatMessage.user('Tell me a story.'),
    ],
  ),
);

await for (final chunk in stream) {
  stdout.write(chunk.message?.content ?? '');
}

client.close();

Tool Calling

Tool Calling Example

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

final response = await client.chat.create(
  request: ChatRequest(
    model: 'gpt-oss',
    messages: [
      ChatMessage.user('What is the weather in Paris?'),
    ],
    tools: [
      ToolDefinition(
        type: ToolType.function,
        function: ToolFunction(
          name: 'get_weather',
          description: 'Get the current weather for a location',
          parameters: {
            'type': 'object',
            'properties': {
              'location': {'type': 'string', 'description': 'City name'},
            },
            'required': ['location'],
          },
        ),
      ),
    ],
  ),
);

if (response.message?.toolCalls != null) {
  for (final toolCall in response.message!.toolCalls!) {
    print('Tool: ${toolCall.function?.name}');
    print('Args: ${toolCall.function?.arguments}');
  }
}

client.close();

Text Generation

Text Generation Example

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

final response = await client.completions.generate(
  request: GenerateRequest(
    model: 'gpt-oss',
    prompt: 'Complete this: The capital of France is',
  ),
);

print(response.response);
client.close();

Embeddings

Embeddings Example

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

final response = await client.embeddings.create(
  request: EmbedRequest(
    model: 'nomic-embed-text',
    input: 'The quick brown fox jumps over the lazy dog.',
  ),
);

print(response.embeddings);
client.close();

Model Management

Model Management Examples

import 'package:ollama_dart/ollama_dart.dart';

final client = OllamaClient();

// List models
final models = await client.models.list();
for (final model in models.models ?? []) {
  print('${model.name}: ${model.size}');
}

// Pull a model
await for (final progress in client.models.pullStream(
  request: PullRequest(model: 'gpt-oss'),
)) {
  print('${progress.status}: ${progress.completed}/${progress.total}');
}

// Show model details
final info = await client.models.show(
  request: ShowRequest(model: 'gpt-oss'),
);
print(info.license);

// List running models
final running = await client.models.ps();
for (final model in running.models ?? []) {
  print('Running: ${model.model}');
}

// Get server version
final version = await client.version.get();
print('Ollama version: ${version.version}');

client.close();

Examples

See the example/ directory for comprehensive examples:

1. ollama_dart_example.dart - Basic usage
2. chat_example.dart - Chat completions
3. streaming_example.dart - Streaming responses
4. tool_calling_example.dart - Function calling
5. embeddings_example.dart - Generate embeddings
6. models_example.dart - Model management

API Coverage

This client implements 100% of the Ollama REST API:

Chat Resource (client.chat)

• create - Generate a chat completion
• createStream - Generate a streaming chat completion

Completions Resource (client.completions)

• generate - Generate a text completion
• generateStream - Generate a streaming text completion

Embeddings Resource (client.embeddings)

• create - Generate embeddings for text

Models Resource (client.models)

• list - List local models (GET /api/tags)
• show - Show model details (POST /api/show)
• create / createStream - Create a model from Modelfile (POST /api/create)
• copy - Copy a model (POST /api/copy)
• delete - Delete a model (DELETE /api/delete)
• pull / pullStream - Pull a model from library (POST /api/pull)
• push / pushStream - Push a model to library (POST /api/push)
• ps - List running models (GET /api/ps)

Version Resource (client.version)

• get - Get server version (GET /api/version)

License

ollama_dart is licensed under the MIT License.