Ollama Provider

nordwestt/ollama-ai-provider-v2 is a community provider that uses Ollama to provide language model support for the AI SDK.

Setup

The Ollama provider is available in the ollama-ai-provider-v2 module. You can install it with

pnpm add ollama-ai-provider-v2

Provider Instance

You can import the default provider instance ollama from ollama-ai-provider-v2:

import { ollama } from 'ollama-ai-provider-v2';

If you need a customized setup, you can import createOllama from ollama-ai-provider-v2 and create a provider instance with your settings:

import { createOllama } from 'ollama-ai-provider-v2';

const ollama = createOllama({
  // optional settings, e.g.
  baseURL: 'https://api.ollama.com',
});

You can use the following optional settings to customize the Ollama provider instance:

• baseURL string

  Use a different URL prefix for API calls, e.g. to use proxy servers. The default prefix is http://localhost:11434/api.

• headers Record<string,string>

  Custom headers to include in the requests.

Language Models

You can create models that call the Ollama Chat Completion API using the provider instance. The first argument is the model id, e.g. phi3. Some models have multi-modal capabilities.

const model = ollama('phi3');

You can find more models on the Ollama Library homepage.

Model Capabilities

This provider is capable of using hybrid reasoning models such as qwen3, allowing toggling of reasoning between messages.

import { ollama } from 'ollama-ai-provider-v2';
import { generateText } from 'ai';

const { text } = await generateText({
  model: ollama('qwen3:4b'),
  providerOptions: { ollama: { think: true } },
  prompt:
    'Write a vegetarian lasagna recipe for 4 people, but really think about it',
});

Embedding Models

You can create models that call the Ollama embeddings API using the .textEmbeddingModel() factory method.

const model = ollama.textEmbeddingModel('nomic-embed-text');

const { embeddings } = await embedMany({
  model: model,
  values: ['sunny day at the beach', 'rainy afternoon in the city'],
});

console.log(
  `cosine similarity: ${cosineSimilarity(embeddings[0], embeddings[1])}`,
);

Alternative Providers

There is an alternative provider package called ai-sdk-ollama by jagreehal, which uses the official Ollama JavaScript client library instead of direct HTTP API calls.

Key differences:

• Uses the official ollama npm package for communication
• Provides automatic environment detection (Node.js vs browser)
• Includes built-in error handling and retries via the official client
• Supports both CommonJS and ESM module formats
• Full TypeScript support with type-safe Ollama-specific options via providerOptions.ollama

This approach leverages Ollama's official client library, which may provide better compatibility with Ollama updates and additional features like model management. Both providers implement the AI SDK specification, so you can choose based on your specific requirements and preferences.