Skip to main content
Open In Colab在 GitHub 上打开

OCI 数据科学模型部署端点

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。

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

此笔记本介绍如何使用 OCI Data Science Model Deployment 上托管的 LLM。

对于验证，oracle-ads 库用于自动加载调用端点所需的凭证。

!pip3 install oracle-ads

先决条件

部署模型

您可以在 OCI 数据科学模型部署上使用 AI 快速作轻松部署、微调和评估基础模型。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。

建立

部署模型后，您必须设置以下调用所需的参数：

  • endpoint：来自已部署模型的模型 HTTP 端点，例如https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict.

认证

您可以通过 ads 或 environment variables 设置身份验证。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。查看此处以查看更多选项。

例子

import ads
from langchain_community.llms import OCIModelDeploymentLLM

# 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")

# Create an instance of OCI Model Deployment Endpoint
# Replace the endpoint uri and model name with your own
# Using generic class as entry point, you will be able
# to pass model parameters through model_kwargs during
# instantiation.
llm = OCIModelDeploymentLLM(
    endpoint="https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict",
    model="odsc-llm",
)

# Run the LLM
llm.invoke("Who is the first president of United States?")
import ads
from langchain_community.llms import OCIModelDeploymentVLLM

# 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")

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

# Run the LLM
llm.invoke("Who is the first president of United States?")
import os

from langchain_community.llms import OCIModelDeploymentTGI

# 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"

# Set endpoint through environment variables
# Replace the endpoint uri with your own
os.environ["OCI_LLM_ENDPOINT"] = (
    "https://modeldeployment.<region>.oci.customer-oci.com/<md_ocid>/predict"
)

# Create an instance of OCI Model Deployment Endpoint
# Using framework specific class as entry point, you will
# be able to pass model parameters in constructor.
llm = OCIModelDeploymentTGI()

# Run the LLM
llm.invoke("Who is the first president of United States?")

异步调用

await llm.ainvoke("Tell me a joke.")

流式调用

for chunk in llm.stream("Tell me a joke."):
    print(chunk, end="", flush=True)

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：