ChatDatabricks 集成

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:  ········

pip install -qU databricks-langchain

from databricks_langchain import ChatDatabricks

chat_model = ChatDatabricks(
    endpoint="databricks-dbrx-instruct",
    temperature=0.1,
    max_tokens=256,
)

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')

# 您也可以传递消息列表
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')

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')

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|?||

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)

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

from pydantic import BaseModel, Field


class GetWeather(BaseModel):
    """获取给定位置的当前天气"""

    location: str = Field(description="城市和州，例如 San Francisco, CA")


class GetPopulation(BaseModel):
    """获取给定位置的当前人口"""

    location: str = Field(description="城市和州，例如 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)

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

chat_model_custom.invoke("How are you?")

# 将 `<scope>` 替换为您的范围
databricks secrets create-scope <scope>
databricks secrets put-secret <scope> openai-api-key --string-value $OPENAI_API_KEY

from mlflow.deployments import get_deploy_client

client = get_deploy_client("databricks")

secret = "secrets/<scope>/openai-api-key"  # 将 `<scope>` 替换为您的范围
endpoint_name = "my-chat"  # 如果 my-chat 已存在，请重命名
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 + "}}",
                    },
                },
            }
        ],
    },
)

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

llm = ChatDatabricks(endpoint="databricks-meta-llama-3-70b-instruct")
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "获取给定位置的当前天气",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "城市和州，例如 San Francisco, CA",
                    },
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
            },
        },
    }
]

# 支持的 tool_choice 值："auto"、"required"、"none"、字符串格式的函数名，
# 或字典格式 {"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))