ChatOllama 集成 - Docs by LangChain

Ollama allows you to run open-source Large Language Models (LLMs), such as Llama 3.1, locally. Ollama bundles model weights, configuration, and data into a single package, defined by a Modelfile. It optimizes setup and configuration details, including GPU usage. 本指南将帮助你开始使用 ChatOllama chat models。有关所有 ChatOllama 功能和配置的详细文档，请前往 API 参考。

概述

集成详情

Ollama allows you to use a wide range of models with different capabilities. Some of the fields in the details table below only apply to a subset of models that Ollama offers. For a complete list of supported models and model variants, see the Ollama model library and search by tag.

Class	Package	Serializable	PY support	Downloads	Version
`ChatOllama`	`@langchain/ollama`	beta	✅

模型功能

请参阅下表标题中的链接，了解如何使用特定功能。

Tool calling	Structured output	Image input	Audio input	Video input	Token-level streaming	Token usage	Logprobs
✅	✅	✅	❌	❌	✅	✅	❌

设置

Follow these instructions to set up and run a local Ollama instance. Then, download the @langchain/ollama package.

凭证

如果你想要自动追踪模型调用，还可以设置你的 LangSmith API 密钥，取消注释以下内容：

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

安装

LangChain 的 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.)

Tools

Ollama now offers support for native tool calling for a subset of their available models. The example below demonstrates how you can invoke a tool from an Ollama model.

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"),
  }),
});

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

// Bind the tool to the model
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 natively supports structured output for all models, allowing you to force the model to return a specific format by calling .withStructuredOutput().

import { ChatOllama } from "@langchain/ollama";
import { z } from "zod";

// Define the schema
const Country = z.object({
  name: z.string(),
  capital: z.string(),
  languages: z.array(z.string()),
});

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

// Pass the schema to enforce a specific output format
const structuredLlm = llm.withStructuredOutput(Country);

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

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

If you prefer to use structured output via tool calling, pass the method: "functionCalling" option:

import { ChatOllama } from "@langchain/ollama";
import { z } from "zod";

// Define the schema
const Sentence = z.object({
  nouns: z.array(z.string()),
});

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

// Use structured output via tool calling
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' ] }

Multimodal models

Ollama supports open source multimodal models like LLaVA in versions 0.1.15 and up. You can pass images as part of a message’s content field to multimodal-capable models like this:

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，请前往 API 参考。

将这些文档连接到 Claude、VSCode 等工具，通过 MCP 获取实时答案。

在 GitHub 上编辑此页面或提交 issue。

Documentation Index

​概述

​集成详情

​模型功能

​设置

​凭证

​安装

​实例化

​调用

​Tools

​结构化输出

​Multimodal models

​API 参考

概述

集成详情

模型功能

设置

凭证

安装

实例化

调用

Tools

结构化输出

Multimodal models

API 参考