mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-24 04:33:04 +08:00
49 lines
1.4 KiB
Python
49 lines
1.4 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
#!/usr/bin/env python3
|
|
"""Example 1: Basic Non-Streaming Responses.
|
|
|
|
Demonstrates a simple responses request with the OpenAI-compatible API.
|
|
"""
|
|
|
|
from openai import OpenAI
|
|
|
|
# Initialize the client
|
|
client = OpenAI(
|
|
base_url="http://localhost:8000/v1",
|
|
api_key="tensorrt_llm",
|
|
)
|
|
|
|
# Get the model name from the server
|
|
models = client.models.list()
|
|
model = models.data[0].id
|
|
|
|
print("=" * 80)
|
|
print("Example 1: Basic Non-Streaming Responses")
|
|
print("=" * 80)
|
|
print()
|
|
|
|
# Create a simple responses request
|
|
response = client.responses.create(
|
|
model=model,
|
|
input="What is the capital of France?",
|
|
max_output_tokens=4096,
|
|
)
|
|
|
|
# Print the response
|
|
print("Response:")
|
|
print(f"Content: {response.output_text}")
|