Update app.py

app.py

@@ -164,15 +164,15 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
     collected_messages = []
     key = os.getenv('OPENAI_API_KEY')
     client.api_key = key
-    
-    for chunk in client.chat.completions.create(
-        model='gpt-3.5-turbo',
-        messages=conversation,
-        temperature=0.5,
-        stream=True  
-    ):
-        collected_chunks.append(chunk)  # save the event response
-        chunk_message = chunk['choices'][0]['delta']  # extract the message
+
+    client = AsyncOpenAI()
+    stream = await client.chat.completions.create(
+        prompt="Say this is a test",
+        messages=[{"role": "user", "content": "Say this is a test"}],
+        stream=True,
+    )
+    async for part in stream:
+        chunk_message = (part.choices[0].delta.content or "")
         collected_messages.append(chunk_message)  # save the message
         content=chunk["choices"][0].get("delta",{}).get("content")
         try:
@@ -182,8 +182,28 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
                 res_box.markdown(f'*{result}*') 
         except:
             st.write(' ')
-            
     full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
+
+    
+    #for chunk in client.chat.completions.create(
+    #    model='gpt-3.5-turbo',
+    #    messages=conversation,
+    #    temperature=0.5,
+    #    stream=True  
+    #):
+    #    collected_chunks.append(chunk)  # save the event response
+    #    chunk_message = chunk['choices'][0]['delta']  # extract the message
+    #    collected_messages.append(chunk_message)  # save the message
+    #    content=chunk["choices"][0].get("delta",{}).get("content")
+    #    try:
+    #        report.append(content)
+    #        if len(content) > 0:
+    #            result = "".join(report).strip()
+    #            res_box.markdown(f'*{result}*') 
+    #    except:
+    #        st.write(' ')
+            
+    # full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
     st.write("Elapsed time:")
     st.write(time.time() - start_time)
     readitaloud(full_reply_content)