ChatOllama 集成 - Docs by LangChain

Ollama 允许您在本地运行开源大型语言模型（LLMs），例如 Llama 3.1。 Ollama 将模型权重、配置和数据打包成一个由 Modelfile 定义的单一包。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。有关所有 ChatOllama 功能和配置的详细文档，请访问 API 参考。

概述

集成详情

Ollama 允许您使用具有不同功能的广泛模型。下表详情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/ollama`	测试版	✅

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

请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

如果您想获得模型调用的自动跟踪，也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",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ],
    ["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 现在为其部分可用模型提供原生工具调用支持。以下示例演示了如何从 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: "Get the current weather in a given location",
  schema: z.object({
    location: z.string().describe("The city and state, e.g. 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(
  "What's the weather like today in San Francisco? Ensure you use the 'get_current_weather' tool."
);

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,
});

// 传递模式以强制特定输出格式
const structuredLlm = llm.withStructuredOutput(Country);

const result = await structuredLlm.invoke("Tell me about Canada.");
console.log(result);

{
  name: 'Canada',
  capital: 'Ottawa',
  languages: [ 'English', 'French' ]
}

如果您更喜欢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("Extract all nouns: A cat named Luna who is 5 years old and loves playing with yarn. She has grey fur");
console.log(result);

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

多模态模型

Ollama 支持 0.1.15 及更高版本中的开源多模态模型，如 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: "What is in this image?",
      },
      {
        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

有关所有 ChatOllama 功能和配置的详细文档，请访问 API 参考。

将这些文档通过 MCP 连接到 Claude、VSCode 等，以获取实时答案。

在 GitHub 上编辑此页面或提交问题。

​概述

​集成详情

​模型功能

​设置

​凭证

​安装

​实例化

​调用

​工具

​结构化输出

​多模态模型

​API 参考

概述

集成详情

模型功能

设置

凭证

安装

实例化

调用

工具

结构化输出

多模态模型

API 参考