ai-sdk-ollama weekly downloads statistics

AI SDK Ollama Provider

A Vercel AI SDK provider for Ollama, built on the official ollama package. Type-safe, cross-provider compatible, with access to native Ollama features.

Version compatibility

Each ai-sdk-ollama major targets one AI SDK major. Every line stays published on npm, so pick the one that matches your ai version:

ai-sdk-ollama	ai (peer)	Status
4.x (@latest)	ai@^7	Active. New features land here.
3.x	ai@^6	Maintenance. Critical fixes only.
2.x	ai@^5	Unmaintained.

AI SDK v7 is stable, so v4 installs from latest. The v3 line still works for AI SDK v6.

Quick Start

# AI SDK v7 (stable)
npm install ai-sdk-ollama ai

# AI SDK v6
npm install ai-sdk-ollama@^3 ai@^6

import { ollama } from 'ai-sdk-ollama';
import { generateText } from 'ai';

// Works in both Node.js and browsers
const { text } = await generateText({
  model: ollama('llama3.2'),
  prompt: 'Write a haiku about coding',
  temperature: 0.8,
});

console.log(text);

Why Choose AI SDK Ollama?

• Reliable tool calling - Response synthesis adds text after tool execution, so you don't get empty replies
• Wrapper functions - generateText and streamText return complete responses
• Built-in reliability - Reliability features run by default
• Automatic JSON repair - Cascade repair runs jsonrepair first, then an Ollama-specific fallback for trailing commas, comments, URLs, and Python constants
• Web search and fetch - Built-in tools powered by Ollama's web search API for current information
• Type-safe - Full TypeScript support with strict typing
• Cross-environment - Runs in Node.js and browsers automatically
• Native Ollama options - Use mirostat, repeat_penalty, num_ctx, and more
• Production-ready - Handles the tool-call and JSON edge cases that otherwise need manual workarounds

Enhanced Tool Calling

The problem this solves: Standard Ollama providers can execute a tool and then return empty text. These wrapper functions synthesize a response so you get complete output.

import { ollama, generateText, streamText } from 'ai-sdk-ollama';

// Enhanced generateText - returns complete responses after tool calls
const { text } = await generateText({
  model: ollama('llama3.2'),
  tools: {
    /* your tools */
  },
  prompt: 'Use the tools and explain the results',
});

// Enhanced streaming - tool-aware streaming
const { textStream } = await streamText({
  model: ollama('llama3.2'),
  tools: {
    /* your tools */
  },
  prompt: 'Stream with tools',
});

Web Search Tools

Web search and fetch: Built-in tools powered by Ollama's web search API for current information.

import { generateText } from 'ai';
import { ollama } from 'ai-sdk-ollama';

// 🔍 Web search for current information
const { text } = await generateText({
  model: ollama('deepseek-v4.1-flash:cloud'), // Cloud models recommended for web search
  prompt: 'What are the latest developments in AI this week?',
  tools: {
    webSearch: ollama.tools.webSearch({ maxResults: 5 }),
  },
});

// 📄 Fetch specific web content
const { text: summary } = await generateText({
  model: ollama('gpt-oss:120b-cloud'),
  prompt: 'Summarize this article: https://example.com/article',
  tools: {
    webFetch: ollama.tools.webFetch({ maxContentLength: 5000 }),
  },
});

// 🔄 Combine search and fetch for comprehensive research
const { text: research } = await generateText({
  model: ollama('gpt-oss:120b-cloud'),
  prompt: 'Research recent TypeScript updates and provide a detailed analysis',
  tools: {
    webSearch: ollama.tools.webSearch({ maxResults: 3 }),
    webFetch: ollama.tools.webFetch(),
  },
});

Web Search Prerequisites

1. Ollama API Key: Set OLLAMA_API_KEY environment variable
2. Cloud Models: Use cloud models for optimal web search performance:
   • deepseek-v4.1-flash:cloud - Best for general web search
   • gpt-oss:120b-cloud - Best for complex reasoning with web data

# Set your API key
export OLLAMA_API_KEY="your_api_key_here"

# Get your API key from: https://ollama.com/account

Contents…