chore(examples-docs): upgrade to OpenAI V1 (#1785)

docs/source/getting_started/quickstart.rst

@@ -157,11 +157,16 @@ Since this server is compatible with OpenAI API, you can use it as a drop-in rep
 
 .. code-block:: python
 
-    import openai
+    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"
-    completion = openai.Completion.create(model="facebook/opt-125m",
+    openai_api_key = "EMPTY"
+    openai_api_base = "http://localhost:8000/v1"
+    client = OpenAI(
+        api_key=openai_api_key,
+        base_url=openai_api_base,
+    )
+    completion = client.completions.create(model="facebook/opt-125m",
                                           prompt="San Francisco is a")
     print("Completion result:", completion)
 
@@ -194,11 +199,17 @@ Using the `openai` python package, you can also communicate with the model in a
 
 .. code-block:: python
 
-    import openai
+    from openai import OpenAI
     # Set OpenAI's API key and API base to use vLLM's API server.
-    openai.api_key = "EMPTY"
-    openai.api_base = "http://localhost:8000/v1"
-    chat_response = openai.ChatCompletion.create(
+    openai_api_key = "EMPTY"
+    openai_api_base = "http://localhost:8000/v1"
+
+    client = OpenAI(
+        api_key=openai_api_key,
+        base_url=openai_api_base,
+    )
+
+    chat_response = client.chat.completions.create(
         model="facebook/opt-125m",
         messages=[
             {"role": "system", "content": "You are a helpful assistant."},

examples/openai_chatcompletion_client.py

-import openai
+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"
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
 
-# List models API
-models = openai.Model.list()
-print("Models:", models)
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
 
-model = models["data"][0]["id"]
+models = client.models.list()
+model = models.data[0].id
 
-# Chat completion API
-chat_completion = openai.ChatCompletion.create(
-    model=model,
+chat_completion = client.chat.completions.create(
     messages=[{
         "role": "system",
         "content": "You are a helpful assistant."
@@ -27,7 +28,10 @@ chat_completion = openai.ChatCompletion.create(
     }, {
         "role": "user",
         "content": "Where was it played?"
-    }])
+    }],
+    model=model,
+)
+
 
 print("Chat completion results:")
 print(chat_completion)

examples/openai_completion_client.py

-import openai
+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"
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
 
-# List models API
-models = openai.Model.list()
-print("Models:", models)
+client = OpenAI(
+    # defaults to os.environ.get("OPENAI_API_KEY")
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
 
-model = models["data"][0]["id"]
+models = client.models.list()
+model = models.data[0].id
 
 # Completion API
 stream = False
-completion = openai.Completion.create(
+completion = client.completions.create(
     model=model,
     prompt="A robot may not injure a human being",
     echo=False,
     n=2,
     stream=stream,
-    logprobs=3)
+    logprobs=3
+)
 
 print("Completion results:")
 if stream: