[Examples][1/n] Resettle basic examples. (#35579)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

examples/basic/online_serving/openai_chat_completion_client.py

@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+"""Example Python client for OpenAI Chat Completion using vLLM API server
+NOTE: start a supported chat completion model server with `vllm serve`, e.g.
+    vllm serve meta-llama/Llama-2-7b-chat-hf
+"""
+
+import argparse
+
+from openai import OpenAI
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "Who won the world series in 2020?"},
+    {
+        "role": "assistant",
+        "content": "The Los Angeles Dodgers won the World Series in 2020.",
+    },
+    {"role": "user", "content": "Where was it played?"},
+]
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Client for vLLM API server")
+    parser.add_argument(
+        "--stream", action="store_true", help="Enable streaming response"
+    )
+    return parser.parse_args()
+
+
+def main(args):
+    client = OpenAI(
+        # defaults to os.environ.get("OPENAI_API_KEY")
+        api_key=openai_api_key,
+        base_url=openai_api_base,
+    )
+
+    models = client.models.list()
+    model = models.data[0].id
+
+    # Chat Completion API
+    chat_completion = client.chat.completions.create(
+        messages=messages,
+        model=model,
+        stream=args.stream,
+    )
+
+    print("-" * 50)
+    print("Chat completion results:")
+    if args.stream:
+        for c in chat_completion:
+            print(c)
+    else:
+        print(chat_completion)
+    print("-" * 50)
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)