ChatDatabricks

Databricks Lakehouse Platform unifies data, analytics, and AI on one platform.

本笔记本提供了快速入门Databricks 聊天模型的概述。有关ChatDatabricks所有功能和配置的详细文档，请访问API参考。

概览

ChatDatabricks 类包装了托管在 Databricks 模型服务 上的聊天模型端点。此示例笔记本展示了如何包装您的服务端点并将其用作 LangChain 应用程序中的聊天模型。

集成详情

类	包	本地	可序列化的	软件包下载	最新包裹
ChatDatabricks	databricks-langchain	❌	beta

模型特性

工具调用	结构化输出	JSON模式	图像输入	音频输入	视频输入	令牌级流式传输	原生异步	令牌使用量	对数概率
✅	✅	✅	❌	❌	❌	✅	✅	✅	❌

支持的方法

ChatDatabricks 支持包括异步API在内的所有 ChatModel 方法。

端点要求

服务端点 ChatDatabricks 的封装必须具有与 OpenAI 兼容的聊天输入/输出格式（参考）。只要输入格式兼容，ChatDatabricks 就可以用于托管在 Databricks 模型服务 上的任何端点类型：

1. 基础模型 - 精选的前沿基础模型列表，例如 DRBX、Llama3、Mixtral-8x7B 等。这些端点可以在您的 Databricks 工作区中直接使用，无需任何设置。
2. 自定义模型 - 您还可以通过 MLflow 使用您选择的框架（例如 LangChain、Pytorch、Transformers 等）将自定义模型部署到服务端点。
3. 外部模型 - Databricks 终端可以作为代理，服务托管在 Databricks 之外的模型，例如像 OpenAI GPT4 这样的专有模型服务。

设置

要访问 Databricks 模型，你需要创建一个 Databricks 账户、设置凭据（仅当你在 Databricks 工作区之外时），并安装所需的包。

凭据（仅当您在Databricks外部时需要）

如果在 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分别设置为环境变量 DATABRICKS_HOST 和 DATABRICKS_TOKEN。有关如何获取访问令牌，请参阅 身份验证文档。

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: "
    )

Enter your Databricks access token:  ········

安装

LangChain Databricks 集成位于 databricks-langchain 包中。

%pip install -qU databricks-langchain

我们首先演示如何通过 ChatDatabricks 查询作为基础模型端点托管的 DBRX-instruct 模型。

对于其他类型的端点，在如何设置端点本身方面会有一些差异，但是一旦端点准备就绪，使用 ChatDatabricks 查询它的方式就没有区别了。有关其他类型端点的示例，请参阅此笔记本的底部。

实例化

from databricks_langchain import ChatDatabricks

chat_model = ChatDatabricks(
    endpoint="databricks-dbrx-instruct",
    temperature=0.1,
    max_tokens=256,
    # See https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.databricks.ChatDatabricks.html for other supported parameters
)

调用

chat_model.invoke("What is MLflow?")

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')

# 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)

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')

链式调用

与其他聊天模型类似，ChatDatabricks 可以用作复杂链的一部分。

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?",
    }
)

API 参考：ChatPromptTemplate

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（流式传输）

for chunk in chat_model.stream("How are you?"):
    print(chunk.content, end="|")

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

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，允许您描述工具及其参数，并让模型返回一个 JSON 对象，其中包含要调用的工具及该工具的输入。工具调用在构建使用工具的链和代理时非常有用，也更广泛地适用于从模型中获取结构化输出。

通过 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，这些会被转换为与 OpenAI 兼容的工具模式，其格式如下：

{
    "name": "...",
    "description": "...",
    "parameters": {...}  # JSONSchema
}

并在每次模型调用时传入。

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

Prerequisites:

• 一个LLM被注册并通过MLflow部署到Databricks服务端点。该端点必须具有与OpenAI兼容的聊天输入/输出格式（参考）。
• 您对端点拥有“可查询”权限。

一旦端点准备就绪，使用模式与基础模型完全相同。

chat_model_custom = ChatDatabricks(
    endpoint="YOUR_ENDPOINT_NAME",
    temperature=0.1,
    max_tokens=256,
)

chat_model_custom.invoke("How are you?")

包装外部模型

先决条件：创建代理端点

首先，创建一个新的 Databricks 服务端点，该端点将请求代理到目标外部模型。对于代理外部模型，端点的创建应该非常快速。

这需要在 Databricks 密钥管理器中注册您的 OpenAI API 密钥，操作如下：

# Replace `<scope>` with your scope
databricks secrets create-scope <scope>
databricks secrets put-secret <scope> openai-api-key --string-value $OPENAI_API_KEY

有关如何设置 Databricks CLI 和管理密钥，请参阅 https://docs.databricks.com/en/security/secrets/secrets.html

from mlflow.deployments import get_deploy_client

client = get_deploy_client("databricks")

secret = "secrets/<scope>/openai-api-key"  # replace `<scope>` 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“就绪”，您可以像查询其他类型的端点一样查询该端点。

chat_model_external = ChatDatabricks(
    endpoint=endpoint_name,
    temperature=0.1,
    max_tokens=256,
)
chat_model_external.invoke("How to use Databricks?")

在Databricks上进行函数调用

Databricks 函数调用与 OpenAI 兼容，仅在模型服务期间作为基础模型 API 的一部分提供。

参见Databricks 函数调用介绍以获取支持的模型。

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": <<tool_name>>}}
model = llm.bind_tools(tools, tool_choice="auto")

messages = [{"role": "user", "content": "What is the current temperature of Chicago?"}]
print(model.invoke(messages))

参见Databricks Unity Catalog，了解如何在链中使用UC功能。

API 参考

有关ChatDatabricks所有功能和配置的详细文档，请访问API参考： https://api-docs.databricks.com/python/databricks-ai-bridge/latest/databricks_langchain.html#databricks_langchain.ChatDatabricks

相关

• 聊天模型 概念指南
• 聊天模型 操操作指南