> ## Documentation Index > Fetch the complete documentation index at: https://langchain-docs-zh.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # ChatDatabricks 集成 > 使用 LangChain Python 集成 ChatDatabricks 对话模型。 > [Databricks](https://www.databricks.com/) Lakehouse Platform 在一个平台上统一了数据、分析和 AI。 本指南提供了快速入门 Databricks [对话模型](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/models.md) 的概述。 ## 概述 `ChatDatabricks` 类封装了在 [Databricks 模型服务](https://docs.databricks.com/en/machine-learning/model-serving/index.html) 上托管的对话模型端点。此示例笔记本展示了如何封装您的服务端点，并在您的 LangChain 应用程序中将其用作对话模型。 ### 集成细节 | 类 | 包 | 可序列化 | 下载 | 版本 | | :- | :- | :-: | :-: | :-: | | `ChatDatabricks` | `databricks-langchain` | beta | ![PyPI - 下载](https://img.shields.io/pypi/dm/langchain-databricks?style=flat-square\&label=%20) | ![PyPI - 版本](https://img.shields.io/pypi/v/langchain-databricks?style=flat-square\&label=%20) | ### 模型特性 | [工具调用](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/tools.md) | [结构化输出](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/structured-output.md) | [图像输入](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/messages.md#多模态) | 音频输入 | 视频输入 | [Token 级流式输出](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/streaming.md) | 原生异步 | [Token 使用](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/models.md#token-使用) | [Logprobs](https://langchain-docs-zh.mintlify.site/langchain/oss/langchain/models.md#对数概率) | | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | :-: | | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ### 支持的方法 `ChatDatabricks` 支持 `ChatModel` 的所有方法，包括异步 API。 ### 端点要求 服务端点 `ChatDatabricks` 封装必须具有 OpenAI 兼容的聊天输入/输出格式 ([参考](https://mlflow.org/docs/latest/llms/deployments/index.html#chat))。只要输入格式兼容，`ChatDatabricks` 可用于在 [Databricks 模型服务](https://docs.databricks.com/en/machine-learning/model-serving/index.html) 上托管的任何端点类型： 1. 基础模型 - 精选的当前最先进的基座模型列表，例如 DRBX、Llama3、Mixtral-8x7B 等。这些端点已准备好在您的 Databricks 工作区中使用，无需任何设置。 2. 自定义模型 - 您也可以通过 MLflow 将自定义模型部署到服务端点，并选择框架，如 LangChain、Pytorch、Transformers 等。 3. 外部模型 - Databricks 端点可以服务在 Databricks 外部托管的模型作为代理，例如专有模型服务如 OpenAI GPT4。 ## 设置 要访问 Databricks 模型，您需要创建一个 Databricks 账户，设置凭证（仅当您不在 Databricks 工作区时），并安装所需的包。 ### 凭证（仅当您不在 Databricks 工作区时） 如果您在 Databricks 内运行 LangChain 应用程序，可以跳过此步骤。 否则，您需要手动将 Databricks 工作区主机名和个人访问令牌设置为 `DATABRICKS_HOST` 和 `DATABRICKS_TOKEN` 环境变量。有关如何获取访问令牌的信息，请参阅 [身份验证文档](https://docs.databricks.com/en/dev-tools/auth/index.html#databricks-personal-access-tokens)。 ```python theme={null} import getpass import os os.environ["DATABRICKS_HOST"] = "https://your-workspace.cloud.databricks.com" if "DATABRICKS_TOKEN" not in os.environ: os.environ["DATABRICKS_TOKEN"] = getpass.getpass( "Enter your Databricks access token: " ) ``` ```text theme={null} Enter your Databricks access token: ········ ``` ### 安装 LangChain Databricks 集成位于 `databricks-langchain` 包中。 ```python theme={null} pip install -qU databricks-langchain ``` 我们首先演示了如何查询作为基础模型端点托管的 DBRX-instruct 模型使用 `ChatDatabricks`。 对于其他类型的端点，设置端点本身的方式有一些不同，但是一旦端点准备就绪，使用 `ChatDatabricks` 查询它的方式就没有区别。请参考此笔记本的底部，了解其他类型端点的示例。 ## 实例化 ```python theme={null} from databricks_langchain import ChatDatabricks chat_model = ChatDatabricks( endpoint="databricks-dbrx-instruct", temperature=0.1, max_tokens=256, ) ``` ## 调用 ```python theme={null} chat_model.invoke("What is MLflow?") ``` ```text theme={null} AIMessage(content='MLflow is an open-source platform for managing end-to-end machine learning workflows. It was introduced by Databricks in 2018. MLflow provides tools for tracking experiments, packaging and sharing code, and deploying models. It is designed to work with any machine learning library and can be used in a variety of environments, including local machines, virtual machines, and cloud-based clusters. MLflow aims to streamline the machine learning development lifecycle, making it easier for data scientists and engineers to collaborate and deploy models into production.', response_metadata={'prompt_tokens': 229, 'completion_tokens': 104, 'total_tokens': 333}, id='run-d3fb4d06-3e10-4471-83c9-c282cc62b74d-0') ``` ```python theme={null} # You can also pass a list of messages messages = [ ("system", "You are a chatbot that can answer questions about Databricks."), ("user", "What is Databricks Model Serving?"), ] chat_model.invoke(messages) ``` ```text theme={null} AIMessage(content='Databricks Model Serving is a feature of the Databricks platform that allows data scientists and engineers to easily deploy machine learning models into production. With Model Serving, you can host, manage, and serve machine learning models as APIs, making it easy to integrate them into applications and business processes. It supports a variety of popular machine learning frameworks, including TensorFlow, PyTorch, and scikit-learn, and provides tools for monitoring and managing the performance of deployed models. Model Serving is designed to be scalable, secure, and easy to use, making it a great choice for organizations that want to quickly and efficiently deploy machine learning models into production.', response_metadata={'prompt_tokens': 35, 'completion_tokens': 130, 'total_tokens': 165}, id='run-b3feea21-223e-4105-8627-41d647d5ccab-0') ``` ## 链接 与其他对话模型类似，`ChatDatabricks` 可以作为复杂链的一部分使用。 ```python theme={null} from langchain_core.prompts import ChatPromptTemplate prompt = ChatPromptTemplate.from_messages( [ ( "system", "You are a chatbot that can answer questions about {topic}.", ), ("user", "{question}"), ] ) chain = prompt | chat_model chain.invoke( { "topic": "Databricks", "question": "What is Unity Catalog?", } ) ``` ```text theme={null} AIMessage(content="Unity Catalog is a new data catalog feature in Databricks that allows you to discover, manage, and govern all your data assets across your data landscape, including data lakes, data warehouses, and data marts. It provides a centralized repository for storing and managing metadata, data lineage, and access controls for all your data assets. Unity Catalog enables data teams to easily discover and access the data they need, while ensuring compliance with data privacy and security regulations. It is designed to work seamlessly with Databricks' Lakehouse platform, providing a unified experience for managing and analyzing all your data.", response_metadata={'prompt_tokens': 32, 'completion_tokens': 118, 'total_tokens': 150}, id='run-82d72624-f8df-4c0d-a976-919feec09a55-0') ``` ## 调用（流式输出） ```python theme={null} stream = chat_model.stream_events("How are you?", version="v3") for token in stream.text: print(token, end="|") ``` ```text theme={null} I|'m| an| AI| and| don|'t| have| feelings|,| but| I|'m| here| and| ready| to| assist| you|.| How| can| I| help| you| today|?| ``` ## 异步调用 ```python theme={null} import asyncio country = ["Japan", "Italy", "Australia"] futures = [chat_model.ainvoke(f"Where is the capital of {c}?") for c in country] await asyncio.gather(*futures) ``` ## 工具调用 ChatDatabricks 支持与 OpenAI 兼容的工具调用 API，该 API 允许您描述工具及其参数，并让模型返回一个包含要调用的工具及其输入的 JSON 对象。工具调用对于构建使用工具的链和智能体，以及从模型获取结构化输出非常有用。 使用 `ChatDatabricks.bind_tools`，我们可以轻松地将 Pydantic 类、字典模式、LangChain 工具甚至函数作为工具传递给模型。在底层，这些被转换为与 OpenAI 兼容的工具模式，看起来像： ``` { "name": "...", "description": "...", "parameters": {...} # JSONSchema } ``` 并在每次模型调用时传递。 ```python theme={null} from pydantic import BaseModel, Field class GetWeather(BaseModel): """Get the current weather in a given location""" location: str = Field(description="The city and state, e.g. San Francisco, CA") class GetPopulation(BaseModel): """Get the current population in a given location""" location: str = Field(description="The city and state, e.g. San Francisco, CA") llm_with_tools = chat_model.bind_tools([GetWeather, GetPopulation]) ai_msg = llm_with_tools.invoke( "Which city is hotter today and which is bigger: LA or NY?" ) print(ai_msg.tool_calls) ``` ## 封装自定义模型端点 前提条件： * 一个 LLM 通过 MLflow 注册并部署到 [Databricks 服务端点](https://docs.databricks.com/machine-learning/model-serving/index.html)。端点必须具有 OpenAI 兼容的聊天输入/输出格式 ([参考](https://mlflow.org/docs/latest/llms/deployments/index.html#chat)) * 您拥有对端点的 ["Can Query" 权限](https://docs.databricks.com/security/auth-authz/access-control/serving-endpoint-acl.html)。 一旦端点准备就绪，其使用模式与基础模型相同。 ```python theme={null} chat_model_custom = ChatDatabricks( endpoint="YOUR_ENDPOINT_NAME", temperature=0.1, max_tokens=256, ) chat_model_custom.invoke("How are you?") ``` ## 封装外部模型 前提条件：创建代理端点 首先，创建一个新的 Databricks 服务端点，将请求代理到目标外部模型。端点创建对于代理外部模型应该相当快。 这需要在 Databricks 密钥管理器中注册您的 OpenAI API Key，如下所示： ```sh theme={null} # Replace `` with your scope databricks secrets create-scope databricks secrets put-secret openai-api-key --string-value $OPENAI_API_KEY ``` 有关如何设置 Databricks CLI 和管理密钥的信息，请参阅 [docs.databricks.com/en/security/secrets/secrets.html](https://docs.databricks.com/en/security/secrets/secrets.html) ```python theme={null} from mlflow.deployments import get_deploy_client client = get_deploy_client("databricks") secret = "secrets//openai-api-key" # replace `` with your scope endpoint_name = "my-chat" # rename this if my-chat already exists client.create_endpoint( name=endpoint_name, config={ "served_entities": [ { "name": "my-chat", "external_model": { "name": "gpt-3.5-turbo", "provider": "openai", "task": "llm/v1/chat", "openai_config": { "openai_api_key": "{{" + secret + "}}", }, }, } ], }, ) ``` 一旦端点状态变为 "Ready"，您就可以像查询其他类型的端点一样查询该端点。 ```python theme={null} chat_model_external = ChatDatabricks( endpoint=endpoint_name, temperature=0.1, max_tokens=256, ) chat_model_external.invoke("How to use Databricks?") ``` ## Databricks 函数调用 Databricks 函数调用与 OpenAI 兼容，并且仅在模型服务作为基础模型 API 的一部分时可用。 有关支持的模型的信息，请参阅 [Databricks 函数调用介绍](https://docs.databricks.com/en/machine-learning/model-serving/function-calling.html#supported-models)。 ```python theme={null} llm = ChatDatabricks(endpoint="databricks-meta-llama-3-70b-instruct") tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather in a given location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g. San Francisco, CA", }, "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, }, }, }, } ] # supported tool_choice values: "auto", "required", "none", function name in string format, # or a dictionary as {"type": "function", "function": {"name": <>}} model = llm.bind_tools(tools, tool_choice="auto") messages = [{"role": "user", "content": "What is the current temperature of Chicago?"}] print(model.invoke(messages)) ``` 有关如何在链中使用 UC 函数的信息，请参阅 [Databricks Unity Catalog](https://langchain-docs-zh.mintlify.site/langchain/oss/python/integrations/tools/databricks.md)。 *** ## API 参考 有关所有 `ChatDatabricks` 功能和配置的详细文档，请前往 API 参考：[api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks\_langchain.html#databricks\_langchain.ChatDatabricks](https://api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks_langchain.html#databricks_langchain.ChatDatabricks) *** > 官方原文：[src/oss/python/integrations/chat/databricks.mdx](https://github.com/langchain-ai/docs/blob/main/src/oss/python/integrations/chat/databricks.mdx) · 非官方翻译，译文由 AI 生成，以英文原文为准。 This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.