为方便您集成和使用，LAS的算子 API 会尽可能兼容 OpenAI API。修改 base url、model 、api_key等少量配置，轻松将方舟模型服务集成到您已有的系统中。

调用算子前，您需要先生成算子调用的API Key，并建议将API Key配置为环境变量，便于更安全地调用算子，详情请参见API Key 管理。

• Python版本：3.7及以上。
• OpenAI SDK：1.0版本及以上，安装命令：

pip install --upgrade "openai>=1.0"

快速开始示例 #

from openai import OpenAI
import os

client = OpenAI(   
    # The base URL for model invocation
    base_url="https://operator.las.cn-beijing.volces.com/api/v1",   
    # Replace with your API Key
    api_key=os.environ.get("ARK_API_KEY"), 
)

completion = client.chat.completions.create(
    # Replace with Model ID
    model="doubao-seed-1-6-251015", 
    messages = [
        {"role": "user", "content": "Hello"},
    ],
)
print(completion.choices[0].message.content)

设置额外字段 #

传入OpenAI SDK中不支持的字段，可以通过 extra_body 字典传入，如开关模型是否深度思考的 thinking 字段。

from openai import OpenAI
import os

client = OpenAI(   
    # The base URL for model invocation 
    base_url="https://operator.las.cn-beijing.volces.com/api/v1",  
    # Replace with your API Key 
    api_key=os.environ.get("ARK_API_KEY"), 
)

completion = client.chat.completions.create(
    # Replace with Model ID
    model="doubao-seed-1-6-251015", 
    messages = [
        {"role": "user", "content": "Hello"},
    ],
    extra_body={
         "thinking": {
             "type": "disabled", # 不使用深度思考能力
             # "type": "enabled", # 使用深度思考能力
         }
     }
)
print(completion.choices[0].message.content)

设置自定义header #

可以用于传递额外信息，如配置 ID来串联日志，使能数据加密能力。

from openai import OpenAI
import os

client = OpenAI(   
    # The base URL for model invocation
    base_url="https://operator.las.cn-beijing.volces.com/api/v1",  
    # Replace with your API Key
    api_key=os.environ.get("ARK_API_KEY"), 
)

completion = client.chat.completions.create(
    # Replace with Model ID
    model="doubao-seed-1-6-251015", 
    messages = [
        {"role": "user", "content": "Hello"},
    ],
    # 自定义request id
    extra_headers={"X-Client-Request-Id": "202406251728190000B7EA7A9648AC08D9"}
)
print(completion.choices[0].message.content)

LangChain OpenAI SDK #

安装 LangChain OpenAI SDK：

pip install langchain-openai

示例代码 #

from langchain_openai import ChatOpenAI
from langchain_core.prompts import PromptTemplate
import os

llm = ChatOpenAI(
    # Replace with your API Key     
    openai_api_key=os.environ.get("ARK_API_KEY"), 
    # The base URL for model invocation
    openai_api_base="https://operator.las.cn-beijing.volces.com/api/v1",   
    # Replace with Model ID
    model="doubao-seed-1-6-251015", 
)

template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate.from_template(template)

question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"

llm_chain = prompt | llm

print(llm_chain.invoke(question))