这将帮助您开始使用 OCIModelDeployment 聊天模型。有关所有功能的详细文档 ChatOCIModelDeployment 和配置，请参阅 langchain-oci 包.

OCI Data Science 是一个完全托管的无服务器平台，供数据科学团队在 Oracle Cloud Infrastructure 上构建、训练和管理机器学习模型。您可以使用 AI Quick Actions 在以下服务上轻松部署 LLM OCI Data Science Model Deployment Service。您可以选择使用流行的推理框架（如 vLLM 或 TGI）部署模型。默认情况下，模型部署端点模拟 OpenAI API 协议。

> 有关最新的更新、示例和实验性功能，请参阅 ADS LangChain 集成.

概述

集成详情

模型功能

某些模型功能（包括工具调用、结构化输出和多模态输入）取决于所部署的模型。

设置

要使用 ChatOCIModelDeployment，请部署一个具有聊天补全端点的聊天模型并安装 langchain-oci 和 oracle-ads packages.

您可以使用 OCI Data Science Model deployment 上的 AI Quick Actions 轻松部署基础模型。有关其他部署示例，请访问 Oracle GitHub 示例仓库.

策略

请确保拥有访问 OCI Data Science Model Deployment 端点所需的 策略 。

凭证

您可以通过 Oracle ADS 设置身份验证。当您在 OCI Data Science Notebook Session 中工作时，可以使用资源主体访问其他 OCI 资源。

# Set authentication through ads
# Use resource principal are operating within a
# OCI service that has resource principal based
# authentication configured
ads.set_auth("resource_principal")

或者，您可以使用以下环境变量配置凭证。例如，要使用带有特定配置文件的 API 密钥：

# Set authentication through environment variables
# Use API Key setup when you are working from a local
# workstation or on platform which does not support
# resource principals.
os.environ["OCI_IAM_TYPE"] = "api_key"
os.environ["OCI_CONFIG_PROFILE"] = "default"
os.environ["OCI_CONFIG_LOCATION"] = "~/.oci"

查看 Oracle ADS 文档 了解更多选项。

安装

LangChain OCIModelDeployment 集成位于 langchain-oci package.

pip install -qU langchain-oci oracle-ads

uv add langchain-oci oracle-ads

实例化

您可以使用通用类实例化模型 ChatOCIModelDeployment 或框架特定的类，例如 ChatOCIModelDeploymentVLLM.

• * 使用 ChatOCIModelDeployment 当您需要通用入口点来部署模型时。您可以通过以下方式传递模型参数 model_kwargs 在此类实例化期间。这允许灵活性和易于配置，而无需依赖框架特定的细节。

from langchain_oci import ChatOCIModelDeployment

# Create an instance of OCI Model Deployment Endpoint
# Replace the endpoint uri with your own
# Using generic class as entry point, you will be able
# to pass model parameters through model_kwargs during
# instantiation.
chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.<region>.oci.customer-oci.com/<ocid>/predict",
    streaming=True,
    max_retries=1,
    model_kwargs={
        "temperature": 0.2,
        "max_tokens": 512,
    },  # other model params...
    default_headers={
        "route": "/v1/chat/completions",
        # other request headers ...
    },
)

• * 使用框架特定的类，例如 ChatOCIModelDeploymentVLLM：这适用于您正在使用特定框架（例如 vLLM）并需要通过构造函数直接传递模型参数的情况，简化了设置过程。

from langchain_oci import ChatOCIModelDeploymentVLLM

# Create an instance of OCI Model Deployment Endpoint
# Replace the endpoint uri with your own
# Using framework specific class as entry point, you will
# be able to pass model parameters in constructor.
chat = ChatOCIModelDeploymentVLLM(
    endpoint="https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict",
)

调用

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]

ai_msg = chat.invoke(messages)
ai_msg

AIMessage(content="J'adore programmer.", response_metadata={'token_usage': {'prompt_tokens': 44, 'total_tokens': 52, 'completion_tokens': 8}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-ca145168-efa9-414c-9dd1-21d10766fdd3-0')

print(ai_msg.content)

J'adore programmer.

链接

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | chat
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

AIMessage(content='Ich liebe Programmierung.', response_metadata={'token_usage': {'prompt_tokens': 38, 'total_tokens': 48, 'completion_tokens': 10}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-5dd936b0-b97e-490e-9869-2ad3dd524234-0')

异步调用

from langchain_oci import ChatOCIModelDeployment

system = "You are a helpful translator that translates {input_language} to {output_language}."
human = "{text}"
prompt = ChatPromptTemplate.from_messages([("system", system), ("human", human)])

chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict"
)
chain = prompt | chat

await chain.ainvoke(
    {
        "input_language": "English",
        "output_language": "Chinese",
        "text": "I love programming",
    }
)

AIMessage(content='我喜欢编程', response_metadata={'token_usage': {'prompt_tokens': 37, 'total_tokens': 50, 'completion_tokens': 13}, 'model_name': 'odsc-llm', 'system_fingerprint': '', 'finish_reason': 'stop'}, id='run-a2dc9393-f269-41a4-b908-b1d8a92cf827-0')

流式调用

from langchain_oci import ChatOCIModelDeployment
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [("human", "List out the 5 states in the United State.")]
)

chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict"
)

chain = prompt | chat

for chunk in chain.stream({}):
    sys.stdout.write(chunk.content)
    sys.stdout.flush()

1. California
2. Texas
3. Florida
4. New York
5. Illinois

结构化输出

from langchain_oci import ChatOCIModelDeployment
from pydantic import BaseModel


class Joke(BaseModel):
    """A setup to a joke and the punchline."""

    setup: str
    punchline: str


chat = ChatOCIModelDeployment(
    endpoint="https://modeldeployment.us-ashburn-1.oci.customer-oci.com/<ocid>/predict",
)
structured_llm = chat.with_structured_output(Joke, method="json_mode")
output = structured_llm.invoke(
    "Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys"
)

output.dict()

{'setup': 'Why did the cat get stuck in the tree?',
 'punchline': 'Because it was chasing its tail!'}

API 参考

有关所有功能和配置的详细信息，请参阅 langchain-oci 包 每个类的文档：

• * ChatOCIModelDeployment
• * ChatOCIModelDeploymentVLLM
• * ChatOCIModelDeploymentTGI