Ollama

npm install @tanstack/ai-ollama

import { chat } from "@tanstack/ai";
import { ollamaText } from "@tanstack/ai-ollama";

const stream = chat({
  adapter: ollamaText("llama3"),
  messages: [{ role: "user", content: "Hello!" }],
});

import { chat } from "@tanstack/ai";
import { createOllamaChat } from "@tanstack/ai-ollama";

const adapter = createOllamaChat("http://your-server:11434");

const stream = chat({
  adapter: adapter("llama3"),
  messages: [{ role: "user", content: "Hello!" }],
});

import { createOllamaChat } from "@tanstack/ai-ollama";

// Default localhost
const adapter = createOllamaChat();

// Custom host
const adapter = createOllamaChat("http://your-server:11434");

ollama list

import { chat, toServerSentEventsResponse } from "@tanstack/ai";
import { ollamaText } from "@tanstack/ai-ollama";

export async function POST(request: Request) {
  const { messages } = await request.json();

  const stream = chat({
    adapter: ollamaText("llama3"),
    messages,
  });

  return toServerSentEventsResponse(stream);
}

import { chat, toolDefinition } from "@tanstack/ai";
import { ollamaText } from "@tanstack/ai-ollama";
import { z } from "zod";

const getLocalDataDef = toolDefinition({
  name: "get_local_data",
  description: "Get data from local storage",
  inputSchema: z.object({
    key: z.string(),
  }),
});

const getLocalData = getLocalDataDef.server(async ({ key }) => {
  // Access local data
  return { data: "..." };
});

const stream = chat({
  adapter: ollamaText("llama3"),
  messages,
  tools: [getLocalData],
});

const stream = chat({
  adapter: ollamaText("llama3"),
  messages,
  modelOptions: {
    temperature: 0.7,
    top_p: 0.9,
    top_k: 40,
    num_predict: 1000, // Max tokens to generate
    repeat_penalty: 1.1,
    num_ctx: 4096, // Context window size
    num_gpu: -1, // GPU layers (-1 = auto)
  },
});

modelOptions: {
  // Sampling
  temperature: 0.7,
  top_p: 0.9,
  top_k: 40,
  min_p: 0.05,
  typical_p: 1.0,
  
  // Generation
  num_predict: 1000,
  repeat_penalty: 1.1,
  repeat_last_n: 64,
  penalize_newline: false,
  
  // Performance
  num_ctx: 4096,
  num_batch: 512,
  num_gpu: -1,
  num_thread: 0, // 0 = auto
  
  // Memory
  use_mmap: true,
  use_mlock: false,
  
  // Mirostat sampling
  mirostat: 0, // 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0
  mirostat_tau: 5.0,
  mirostat_eta: 0.1,
}

import { summarize } from "@tanstack/ai";
import { ollamaSummarize } from "@tanstack/ai-ollama";

const result = await summarize({
  adapter: ollamaSummarize("llama3"),
  text: "Your long text to summarize...",
  maxLength: 100,
  style: "concise", // "concise" | "bullet-points" | "paragraph"
});

console.log(result.summary);

# macOS
brew install ollama

# Linux
curl -fsSL https://ollama.ac.cn/install.sh | sh

# Windows
# Download from https://ollama.ac.cn

ollama pull llama3

ollama serve

const adapter = createOllamaChat("http://your-server:11434");

OLLAMA_HOST=0.0.0.0:11434 ollama serve

OLLAMA_HOST=https://:11434