两个文档:
火山引擎 文档中心:https://www.volcengine.com/docs/82379/1108216
火山方舟 模型广场:https://console.volcengine.com/ark/region:ark+cn-beijing/model
首先在模型广场把API搞到手:
然后再模型广场的在线推理,创建推理接入点
创建好后,如下图
在接入点中选择API调用
这里显示了示例
示例代码如下:
from volcenginesdkarkruntime import Ark
import os
# Doub的配置需要:
os.environ["ARK_API_KEY"] = "YOUR_API_KEY"
client = Ark(
base_url="https://ark.cn-beijing.volces.com/api/v3",
)
# Non-streaming:
print("----- standard request -----")
completion = client.chat.completions.create(
model="ep-20241114133215-75z5q",
messages = [
{"role": "system", "content": "你是豆包,是由字节跳动开发的 AI 人工智能助手"},
{"role": "user", "content": "常见的十字花科植物有哪些?"},
],
)
print(completion.choices[0].message.content)
# Streaming:
print("----- streaming request -----")
stream = client.chat.completions.create(
model="ep-20241114133215-75z5q",
messages = [
{"role": "system", "content": "你是豆包,是由字节跳动开发的 AI 人工智能助手"},
{"role": "user", "content": "常见的十字花科植物有哪些?"},
],
stream=True
)
for chunk in stream:
if not chunk.choices:
continue
print(chunk.choices[0].delta.content, end="")
print()
结果如下: