You need to enable JavaScript to run this app.
文档中心
火山方舟

火山方舟

请输入
    火山方舟其他说明兼容 OpenAI SDK
复制全文
下载 pdf
其他说明
兼容 OpenAI SDK
复制全文
下载 pdf
兼容 OpenAI SDK
为方便您集成和使用，火山方舟模型 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。​
说明​
社区第三方 SDK 不由火山引擎团队维护，本文仅供参考。​
前提条件​
说明​
方舟平台的新用户？获取 API Key 及 开通模型等准备工作，请参见 快速入门。​
OpenAI SDK​
  • 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://ark.cn-beijing.volces.com/api/v3",​
# 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-2-1-pro-260628",​
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://ark.cn-beijing.volces.com/api/v3",​
# 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-2-1-pro-260628",​
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://ark.cn-beijing.volces.com/api/v3",​
# 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-2-1-pro-260628",​
messages = [​
{"role": "user", "content": "Hello"},​
],​
# 自定义request id​
extra_headers={"X-Client-Request-Id": "202406251728190000B7EA7A9648AC08D9"}​
)​
print(completion.choices[0].message.content)​
​
向量化 Embedding​
注意​
  • 文本向量化模型已经逐步下线，建议您使用多模态向量化模型。​
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://ark.cn-beijing.volces.com/api/v3",​
# Replace with Model ID​
model="doubao-seed-2-1-pro-260628",​
)​
​
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))​
​
​
最近更新时间：2026.08.21 11:18:10
这个页面对您有帮助吗？
有用
有用
无用
无用