Skip to main content
Ollama 允许您在本地运行开源大语言模型（LLM），例如 Llama 3.1。 Ollama 将模型权重、配置和数据打包成一个单一的包，由 Modelfile 定义。它优化了设置和配置细节，包括 GPU 使用。 本指南将帮助您开始使用 ChatOllama 聊天模型。有关 ChatOllama 所有功能和配置的详细文档，请参阅 API 参考。

​
概述

​
集成详情

Ollama 允许您使用具有不同功能的各种模型。下面详情表中的某些字段仅适用于 Ollama 提供的部分模型。 有关支持的模型和模型变体的完整列表，请参阅 Ollama 模型库 并按标签搜索。
类包可序列化Python 支持下载量版本
ChatOllama@langchain/ollamabeta✅NPM - DownloadsNPM - Version

​
模型功能

有关如何使用特定功能的指南，请参阅下表标题中的链接。
工具调用结构化输出图像输入音频输入视频输入令牌级流式传输令牌使用量对数概率
✅✅✅❌❌✅✅❌

​
设置

按照 这些说明 设置并运行本地 Ollama 实例。然后，下载 @langchain/ollama 包。

​
凭证

如果您希望自动跟踪模型调用，还可以通过取消注释以下内容来设置您的 LangSmith API 密钥： 
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

​
安装

LangChain ChatOllama 集成位于 @langchain/ollama 包中： 
npm install @langchain/ollama @langchain/core

​
实例化

现在我们可以实例化我们的模型对象并生成聊天补全： 
import { ChatOllama } from "@langchain/ollama"

const llm = new ChatOllama({
    model: "llama3",
    temperature: 0,
    maxRetries: 2,
    // 其他参数...
})

​
调用

const aiMsg = await llm.invoke([
    [
        "system",
        "你是一个将英语翻译成法语的助手。请翻译用户的句子。",
    ],
    ["human", "I love programming."],
])
aiMsg

AIMessage {
  "content": "Je adore le programmation.\n\n(Note: \"programmation\" is the feminine form of the noun in French, but if you want to use the masculine form, it would be \"le programme\" instead.)",
  "additional_kwargs": {},
  "response_metadata": {
    "model": "llama3",
    "created_at": "2024-08-01T16:59:17.359302Z",
    "done_reason": "stop",
    "done": true,
    "total_duration": 6399311167,
    "load_duration": 5575776417,
    "prompt_eval_count": 35,
    "prompt_eval_duration": 110053000,
    "eval_count": 43,
    "eval_duration": 711744000
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 35,
    "output_tokens": 43,
    "total_tokens": 78
  }
}

console.log(aiMsg.content)

Je adore le programmation.

(Note: "programmation" is the feminine form of the noun in French, but if you want to use the masculine form, it would be "le programme" instead.)

​
工具

Ollama 现在为 其可用模型的一个子集 提供原生工具调用支持。下面的示例演示了如何从 Ollama 模型调用工具。 
import { tool } from "@langchain/core/tools";
import { ChatOllama } from "@langchain/ollama";
import * as z from "zod";

const weatherTool = tool((_) => "Da weather is weatherin", {
  name: "get_current_weather",
  description: "获取给定位置的当前天气",
  schema: z.object({
    location: z.string().describe("城市和州，例如 San Francisco, CA"),
  }),
});

// 定义模型
const llmForTool = new ChatOllama({
  model: "llama3-groq-tool-use",
});

// 将工具绑定到模型
const llmWithTools = llmForTool.bindTools([weatherTool]);

const resultFromTool = await llmWithTools.invoke(
  "今天旧金山的天气怎么样？请确保使用 'get_current_weather' 工具。"
);

console.log(resultFromTool);

AIMessage {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "model": "llama3-groq-tool-use",
    "created_at": "2024-08-01T18:43:13.2181Z",
    "done_reason": "stop",
    "done": true,
    "total_duration": 2311023875,
    "load_duration": 1560670292,
    "prompt_eval_count": 177,
    "prompt_eval_duration": 263603000,
    "eval_count": 30,
    "eval_duration": 485582000
  },
  "tool_calls": [
    {
      "name": "get_current_weather",
      "args": {
        "location": "San Francisco, CA"
      },
      "id": "c7a9d590-99ad-42af-9996-41b90efcf827",
      "type": "tool_call"
    }
  ],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 177,
    "output_tokens": 30,
    "total_tokens": 207
  }
}

​
结构化输出

Ollama 原生支持所有模型的 结构化输出，允许您通过调用 .withStructuredOutput() 强制模型返回特定格式。 
import { ChatOllama } from "@langchain/ollama";
import { z } from "zod";

// 定义模式
const Country = z.object({
  name: z.string(),
  capital: z.string(),
  languages: z.array(z.string()),
});

// 定义模型
const llm = new ChatOllama({
  model: "llama3.1",
  temperature: 0,
});

// 传递模式以强制执行特定的输出格式
const structuredLlm = llm.withStructuredOutput(Country);

const result = await structuredLlm.invoke("告诉我关于加拿大的信息。");
console.log(result);

{
  name: 'Canada',
  capital: 'Ottawa',
  languages: [ 'English', 'French' ]
}
如果您希望通过工具调用使用结构化输出，请传递 method: "functionCalling" 选项： 
import { ChatOllama } from "@langchain/ollama";
import { z } from "zod";

// 定义模式
const Sentence = z.object({
  nouns: z.array(z.string()),
});

// 定义模型
const llm = new ChatOllama({
  model: "llama3.1",
  temperature: 0,
});

// 通过工具调用使用结构化输出
const structuredLlm = llm.withStructuredOutput(Sentence, { method: "functionCalling" });

const result = await structuredLlm.invoke("提取所有名词：一只名叫 Luna 的猫，5 岁，喜欢玩毛线。她有灰色的毛");
console.log(result);

{ nouns: [ 'cat', 'Luna', 'years', 'yarn', 'fur' ] }

​
多模态模型

Ollama 支持开源多模态模型，如 0.1.15 及以上版本的 LLaVA。 您可以将图像作为消息 content 字段的一部分传递给 支持多模态的 模型，如下所示： 
import { ChatOllama } from "@langchain/ollama";
import { HumanMessage } from "@langchain/core/messages";
import * as fs from "node:fs/promises";

const imageData = await fs.readFile("../../../../../examples/hotdog.jpg");
const llmForMultiModal = new ChatOllama({
  model: "llava",
  baseUrl: "http://127.0.0.1:11434",
});
const multiModalRes = await llmForMultiModal.invoke([
  new HumanMessage({
    content: [
      {
        type: "text",
        text: "这张图片里有什么？",
      },
      {
        type: "image_url",
        image_url: `data:image/jpeg;base64,${imageData.toString("base64")}`,
      },
    ],
  }),
]);
console.log(multiModalRes);

AIMessage {
  "content": " The image shows a hot dog in a bun, which appears to be a footlong. It has been cooked or grilled to the point where it's browned and possibly has some blackened edges, indicating it might be slightly overcooked. Accompanying the hot dog is a bun that looks toasted as well. There are visible char marks on both the hot dog and the bun, suggesting they have been cooked directly over a source of heat, such as a grill or broiler. The background is white, which puts the focus entirely on the hot dog and its bun. ",
  "additional_kwargs": {},
  "response_metadata": {
    "model": "llava",
    "created_at": "2024-08-01T17:25:02.169957Z",
    "done_reason": "stop",
    "done": true,
    "total_duration": 5700249458,
    "load_duration": 2543040666,
    "prompt_eval_count": 1,
    "prompt_eval_duration": 1032591000,
    "eval_count": 127,
    "eval_duration": 2114201000
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 1,
    "output_tokens": 127,
    "total_tokens": 128
  }
}

​
API 参考

有关 ChatOllama 所有功能和配置的详细文档，请参阅 API 参考。
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.