import openai

ip = "0.0.0.0"
service_http_port = "13188"  # 服务配置的

client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")

response = client.chat.completions.create(
    model="default",
    messages=[
        {"role": "user", "content": "北京天安门在哪里?"},
    ],
    temperature=1,
    stream=False,
    seed=None,（也可以不加这一行)
)

print(response.choices[0].message.content)
print("\n")

curl -X POST "http://10.54.104.207:13188/v1/chat/completions" -H "Content-Type: application/json" -d '{
  "messages": [
    {"role": "user", "content": "北京天安门在哪里？"}
  ]
}'

import openai

ip = "0.0.0.0"
service_http_port = "13188"  # 服务配置的

client = openai.Client(base_url=f"http://{ip}:{service_http_port}/v1", api_key="EMPTY_API_KEY")

response = client.chat.completions.create(
    model="default",
    messages=[
        {"role": "user", "content": "北京天安门在哪里?"},
    ],
    temperature=1,
    stream=False,
    seed=1，
)

print(response.choices[0].message.content)
print("\n")

curl -X POST "http://10.54.104.207:13188/v1/chat/completions" -H "Content-Type: application/json" -d '{
  "messages": [
    {"role": "user", "content": "北京天安门在哪里？"}
  ],
  "seed":1
}'

from fastdeploy.engine.sampling_params import SamplingParams
from fastdeploy.entrypoints.llm import LLM

model_name_or_path = "Qwen/Qwen3-0.6B"

# 超参设置
sampling_params = SamplingParams(temperature=0.1)
llm = LLM(model=model_name_or_path, tensor_parallel_size=1,reasoning_parser="qwen3")
prompt = "北京天安门在哪里?"
messages = [{"role": "user", "content": prompt}]
output = llm.chat([messages],
                   sampling_params)
              
print(output)    

from fastdeploy.engine.sampling_params import SamplingParams
from fastdeploy.entrypoints.llm import LLM

model_name_or_path = "Qwen/Qwen3-0.6B"

# 超参设置
sampling_params = SamplingParams(temperature=0.1,seed=1)
llm = LLM(model=model_name_or_path, tensor_parallel_size=1,reasoning_parser="qwen3")
prompt = "北京天安门在哪里?"
messages = [{"role": "user", "content": prompt}]
output = llm.chat([messages],
                   sampling_params)
              
print(output)