Stream Mode

from openai import OpenAI

client = OpenAI(
    base_url='https://api.siliconflow.cn/v1',
    api_key='your-api-key'
)

# 发送带有流式输出的请求
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V2.5",
    messages=[
        {"role": "user", "content": "SiliconFlow公测上线，每用户送3亿token 解锁开源大模型创新能力。对于整个大模型应用领域带来哪些改变？"}
    ],
    stream=True  # 启用流式输出
)

# 逐步接收并处理响应
for chunk in response:
    if not chunk.choices:
        continue
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    if chunk.choices[0].delta.reasoning_content:
        print(chunk.choices[0].delta.reasoning_content, end="", flush=True)

from openai import OpenAI
import requests
import json
   
url = "https://api.siliconflow.cn/v1/chat/completions"
   
payload = {
        "model": "deepseek-ai/DeepSeek-V2.5", # 替换成你的模型
        "messages": [
            {
                "role": "user",
                "content": "SiliconFlow公测上线，每用户送3亿token 解锁开源大模型创新能力。对于整个大模型应用领域带来哪些改变？"
            }
        ],
        "stream": True # 此处需要设置为stream模式
}

headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": "Bearer your-api-key"
    }
   
response = requests.post(url, json=payload, headers=headers, stream=True) # 此处request需要指定stream模式

# 打印流式返回信息
if response.status_code == 200:
    full_content = ""
    full_reasoning_content = ""

    for chunk in response.iter_lines():
        if chunk:
            chunk_str = chunk.decode('utf-8').replace('data: ', '')
            if chunk_str != "[DONE]":
                chunk_data = json.loads(chunk_str)
                delta = chunk_data['choices'][0].get('delta', {})
                content = delta.get('content', '')
                reasoning_content = delta.get('reasoning_content', '')
                if content:
                    print(content, end="", flush=True)
                    full_content += content
                if reasoning_content:
                    print(reasoning_content, end="", flush=True)
                    full_reasoning_content += reasoning_content
else:
    print(f"请求失败，状态码：{response.status_code}")

curl -N -s \
  --request POST \
  --url https://api.siliconflow.cn/v1/chat/completions \
  --header 'Authorization: Bearer token' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "Qwen/Qwen2.5-72B-Instruct",
    "messages": [
      {"role":"user","content":"有诺贝尔数学奖吗？"}
    ],
    "stream": true
}'