[Fix] Add chat completion Example and simplify dependencies (#576)

examples/openai_chatcompletion_client.py

@@ -0,0 +1,33 @@
+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"
+
+# List models API
+models = openai.Model.list()
+print("Models:", models)
+
+model = models["data"][0]["id"]
+
+# Chat completion API
+chat_completion = openai.ChatCompletion.create(
+    model=model,
+    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?"
+    }])
+
+print("Chat completion results:")
+print(chat_completion)

examples/openai_completion_client.py

@@ -3,26 +3,26 @@ 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"
-model = "facebook/opt-125m"
 
-# Test list models API
+# List models API
 models = openai.Model.list()
 print("Models:", models)
 
-# Test completion API
-stream = True
+model = models["data"][0]["id"]
+
+# Completion API
+stream = False
 completion = openai.Completion.create(
     model=model,
     prompt="A robot may not injure a human being",
     echo=False,
     n=2,
-    best_of=3,
     stream=stream,
     logprobs=3)
 
-# print the completion
+print("Completion results:")
 if stream:
     for c in completion:
         print(c)
 else:
-    print("Completion result:", completion)
+    print(completion)