ChatOCIModel部署

这将帮助您开始使用 OCIModelDeployment 聊天模型。有关所有 ChatOCIModelDeployment 功能和配置的详细文档，请参阅 API 参考。

OCI 数据科学是一个完全托管的无服务器平台，可供数据科学团队在 Oracle Cloud Infrastructure 中构建、训练和管理机器学习模型。您可以使用 AI 快速作在 OCI Data Science Model Deployment Service 上轻松部署 LLM。您可以选择使用流行的推理框架（如 vLLM 或 TGI）来部署模型。默认情况下，模型部署终端节点模拟 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

集成详细信息

类	包	本地化	序列 化	JS 支持	软件包下载	最新包装
ChatOCIModelDeployment	langchain-community	❌	beta	❌

模型特点

工具调用	结构化输出	JSON 模式	图像输入	音频输入	视频输入	令牌级流式处理	本机异步	Token 使用情况	日志
depends	depends	depends	depends	depends	depends	✅	✅	✅	✅

一些模型功能（包括工具调用、结构化输出、JSON 模式和多模式输入）取决于部署的模型。

设置

要使用 ChatOCIModelDeployment，您需要部署一个带有聊天完成终端节点的聊天模型，并安装langchain-community,langchain-openai和oracle-ads集成包。

您可以在 OCI 数据科学模型部署上使用 AI 快速作轻松部署基础模型。有关其他部署示例，请访问 Oracle GitHub 示例存储库。

政策

确保具有访问 OCI Data Science Model Deployment 端点所需的策略。

凭据

您可以通过 Oracle ADS 设置验证。在 OCI Data Science Notebook 会话中工作时，您可以利用资源主体访问其他 OCI 资源。

import ads

# 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，要将 API 密钥与特定配置文件一起使用：

import os

# 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 文档以查看更多选项。

安装

LangChain OCIModelDeployment 集成位于langchain-community包。以下命令将安装langchain-community和所需的依赖项。

%pip install -qU langchain-community langchain-openai oracle-ads

实例

您可以使用泛型ChatOCIModelDeployment或特定于框架的类（如ChatOCIModelDeploymentVLLM.

• 用ChatOCIModelDeployment当您需要一个通用的入口点来部署模型时。您可以通过model_kwargs在此类的实例化期间。这允许灵活和轻松的配置，而无需依赖特定于框架的详细信息。

from langchain_community.chat_models 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 ...
    },
)

API 参考：ChatOCIModelDeployment

• 使用特定于框架的类，如ChatOCIModelDeploymentVLLM：当您使用特定框架时（例如vLLM），并且需要直接通过构造函数传递模型参数，从而简化设置过程。

from langchain_community.chat_models 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",
)

API 参考：ChatOCIModelDeploymentVLLM

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.",
    }
)

API 参考：ChatPromptTemplate

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_community.chat_models 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",
    }
)

API 参考：ChatOCIModelDeployment

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

import os
import sys

from langchain_community.chat_models 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()

API 参考：ChatOCIModelDeployment | 聊天提示模板

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

结构化输出

from langchain_community.chat_models 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()

API 参考：ChatOCIModelDeployment

{'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全面详细信息，请参阅每个类的 API 参考文档：

• ChatOCIModel部署
• ChatOCIModelDeploymentVLLM
• ChatOCIModelDeploymentTGI

相关

• 聊天模型概念指南
• 聊天模型操作指南