AI

Ollama Provider

The AI SDK supports Ollama through two community providers:

Both provide language model support for the AI SDK with different approaches and feature sets.

Choosing Your Provider

The AI SDK ecosystem offers multiple Ollama providers, each optimized for different use cases:

For Simple Text Generation

nordwestt/ollama-ai-provider-v2 provides straightforward access to Ollama models with direct HTTP API calls, making it ideal for basic text generation and getting started quickly.

For Advanced Features & Tool Reliability

ai-sdk-ollama by jagreehal is recommended when you need:

  • Reliable tool calling with guaranteed complete responses (solves common empty response issues)
  • Web search capabilities using Ollama's new web search API for current information
  • Cross-environment support with automatic detection for Node.js and browsers
  • Advanced Ollama features like mirostat, repeat_penalty, num_ctx for fine-tuned control
  • Enhanced reliability with built-in error handling and retries via the official client

Key technical advantages:

  • Built on the official Ollama JavaScript client library
  • Supports both CommonJS and ESM module formats
  • Full TypeScript support with type-safe Ollama-specific options

Both providers implement the AI SDK specification and offer excellent TypeScript support. Choose based on your project's complexity and feature requirements.

Setup

Choose and install your preferred Ollama provider:

ollama-ai-provider-v2

pnpm
npm
yarn
bun
pnpm add ollama-ai-provider-v2

ai-sdk-ollama

pnpm
npm
yarn
bun
pnpm add ai-sdk-ollama

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])}`,
);