ChatDatabricks
Databricks 数据湖存储平台在一个平台上统一了数据、分析和 AI。
此笔记本提供了有关开始使用 Databricks 聊天模型 的快速概述。有关所有 ChatDatabricks 功能和配置的详细文档,请访问 API 参考。
概述
ChatDatabricks
类包装了托管在 Databricks 模型服务 上的聊天模型端点。此示例笔记本演示了如何包装您的服务端点并在 LangChain 应用程序中将其用作聊天模型。
集成详细信息
类 | 包 | 本地 | 可序列化 | 包下载 | 最新包 |
---|---|---|---|---|---|
ChatDatabricks | langchain-databricks | ❌ | 测试版 |
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 | 原生异步 | 令牌使用情况 | Logprobs |
---|---|---|---|---|---|---|---|---|---|
✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ |
支持的方法
ChatDatabricks
支持 ChatModel
的所有方法,包括异步 API。
端点要求
ChatDatabricks
包装的服务端点必须具有与 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。
- 基础模型 - DRBX、Llama3、Mixtral-8x7B 等最先进基础模型的精选列表。这些端点无需任何设置即可在您的 Databricks 工作区中使用。
- 自定义模型 - 您还可以使用您选择的框架(如 LangChain、Pytorch、Transformers 等)将自定义模型部署到 MLflow 的服务端点。
- 外部模型 - Databricks 端点可以充当代理,为托管在 Databricks 之外的模型提供服务,例如 OpenAI GPT4 等专有模型服务。
设置
要访问 Databricks 模型,您需要创建一个 Databricks 帐户,设置凭据(仅当您在 Databricks 工作区外部时),并安装所需的包。
凭据(仅当您在 Databricks 外部时)
如果您在 Databricks 内部运行 LangChain 应用程序,则可以跳过此步骤。
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 DATABRICKS_HOST
和 DATABRICKS_TOKEN
环境变量。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 langchain-databricks
包中。
%pip install -qU langchain-databricks
我们首先演示如何使用 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,设置端点本身的方式略有不同,但是,一旦端点准备就绪,使用 ChatDatabricks
查询它的方式就没有任何区别。请参阅此笔记本的底部,了解其他类型端点的示例。
实例化
from langchain_databricks import ChatDatabricks
chat_model = ChatDatabricks(
endpoint="databricks-dbrx-instruct",
temperature=0.1,
max_tokens=256,
# See https://python.langchain.ac.cn/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')
链接
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?",
}
)
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)
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)
包装自定义模型端点
先决条件
- LLM 已注册并通过 MLflow 部署到 Databricks 服务端点。端点必须具有与 OpenAI 兼容的聊天输入/输出格式(参考)
- 您对端点具有 “可以查询”权限。
一旦端点准备就绪,使用模式与基础模型的模式相同。
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,端点创建应该非常快。
这需要在 Databricks 密钥管理器中注册您的 OpenAI API 密钥,如下所示
# 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”,您就可以像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?")
Databricks 上的函数调用
Databricks 函数调用与 OpenAI 兼容,并且仅在模型服务期间作为基础模型 API 的一部分可用。
有关支持的模型,请参阅 Databricks 函数调用简介。
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))
有关如何在链中使用 UC 函数,请参阅 Databricks Unity Catalog。
API 参考
有关所有 ChatDatabricks 功能和配置的详细文档,请访问 API 参考:https://python.langchain.ac.cn/api_reference/databricks/chat_models/langchain_databricks.chat_models.ChatDatabricks.html