> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatOllama 集成

> 使用 LangChain JavaScript 集成 ChatOllama 聊天模型。

[Ollama](https://ollama.ai/) 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](/oss/javascript/langchain/models)。有关 `ChatOllama` 所有功能和配置的详细文档，请参阅 [API 参考](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama)。

## 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](https://ollama.com/search) 并按标签搜索。

| 类                                                                                      | 包                                                                      | 可序列化 | [Python 支持](https://python.langchain.com/docs/integrations/chat/ollama) |                                                下载量                                                |                                               版本                                               |
| :------------------------------------------------------------------------------------- | :--------------------------------------------------------------------- | :--: | :---------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------: |
| [`ChatOllama`](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama) | [`@langchain/ollama`](https://www.npmjs.com/package/@langchain/ollama) | beta |                                    ✅                                    | ![NPM - Downloads](https://img.shields.io/npm/dm/@langchain/ollama?style=flat-square\&label=%20&) | ![NPM - Version](https://img.shields.io/npm/v/@langchain/ollama?style=flat-square\&label=%20&) |

### 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](/oss/javascript/langchain/tools) | [结构化输出](/oss/javascript/langchain/structured-output) | [图像输入](/oss/javascript/langchain/messages#multimodal) | 音频输入 | 视频输入 | [令牌级流式传输](/oss/javascript/langchain/streaming/) | [令牌使用量](/oss/javascript/langchain/models#token-usage) | [对数概率](/oss/javascript/langchain/models#log-probabilities) |
| :-------------------------------------: | :--------------------------------------------------: | :---------------------------------------------------: | :--: | :--: | :---------------------------------------------: | :---------------------------------------------------: | :--------------------------------------------------------: |
|                    ✅                    |                           ✅                          |                           ✅                           |   ❌  |   ❌  |                        ✅                        |                           ✅                           |                              ❌                             |

## 设置

按照 [这些说明](https://github.com/ollama/ollama) 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](/langsmith/home) API 密钥：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"
```

### 安装

LangChain ChatOllama 集成位于 `@langchain/ollama` 包中：

<CodeGroup>
  ```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  npm install @langchain/ollama @langchain/core
  ```

  ```bash yarn theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  yarn add @langchain/ollama @langchain/core
  ```

  ```bash pnpm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pnpm add @langchain/ollama @langchain/core
  ```
</CodeGroup>

## 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：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { ChatOllama } from "@langchain/ollama"

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

## 调用

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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
  }
}
```

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
console.log(aiMsg.content)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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](https://ollama.com/search?c=tools) 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。

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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);
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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](https://docs.ollama.com/capabilities/structured-outputs)，允许您通过调用 `.withStructuredOutput()` 强制模型返回特定格式。

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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);
```

```output theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{
  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：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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);
```

```output theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{ 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](https://ollama.ai/library/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](/oss/javascript/langchain/messages#multimodal) 模型，如下所示：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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);
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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](https://reference.langchain.com/javascript/langchain-ollama/ChatOllama)。

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\javascript\integrations\chat\ollama.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>