Update chain_app.py

chain_app.py

@@ -2090,17 +2090,18 @@ async def main(message: cl.Message):
         for token in stream_list:
             await msg.stream_token(token)
     elif chat_profile == "gpt4-o-mini":
-        completion = openai_client.chat.completions.create(
+        stream = completion = openai_client.chat.completions.create(
             model="gpt-4o-mini",
             messages=[
                 {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
                 {"role": "user", "content": message.content}
-            ]
+            ],
+            stream=True
         )
-        model_response = completion.choices[0].message.content
-        await cl.Message(
-            content=model_response
-        ).send()
+
+        for part in stream:
+            if token := part.choices[0].delta.content or "":
+                await msg.stream_token(token)
   #   elif chat_profile == 'Image-Generation':
   #       result = hf_image_client.predict(
         # prompt=message.content,
@@ -2119,42 +2120,45 @@ async def main(message: cl.Message):
   #           elements=[image],
   #       ).send()
     elif chat_profile == 'GPT-4':
-        completion = openai_client.chat.completions.create(
+        stream = completion = openai_client.chat.completions.create(
             model="gpt-4",
             messages=[
                 {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
                 {"role": "user", "content": message.content}
-            ]
+            ],
+            stream=True
         )
-        model_response = completion.choices[0].message.content
-        await cl.Message(
-            content=model_response
-        ).send()
+
+        for part in stream:
+            if token := part.choices[0].delta.content or "":
+                await msg.stream_token(token)
 
     elif chat_profile == 'gpt-3.5-turbo':
-        completion = openai_client.chat.completions.create(
+        stream = completion = openai_client.chat.completions.create(
             model="gpt-3.5-turbo",
             messages=[
                 {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
                 {"role": "user", "content": message.content}
-            ]
+            ],
+            stream=True
         )
-        model_response = completion.choices[0].message.content
-        await cl.Message(
-            content=model_response
-        ).send()
+
+        for part in stream:
+            if token := part.choices[0].delta.content or "":
+                await msg.stream_token(token)
     elif chat_profile == 'GPT-3.5-turbo-0125':
-        completion = openai_client.chat.completions.create(
+        stream = completion = openai_client.chat.completions.create(
             model="GPT-3.5-turbo-0125",
             messages=[
                 {"role": "system", "content": f"You are neural nexus official chatbot, you are made by Artin Daneshvar and Sadra Noadoust and you are here to help people"},
                 {"role": "user", "content": message.content}
-            ]
+            ],
+            stream=True
         )
-        model_response = completion.choices[0].message.content
-        await cl.Message(
-            content=model_response
-        ).send()
+
+        for part in stream:
+            if token := part.choices[0].delta.content or "":
+                await msg.stream_token(token)
     elif chat_profile == 'gpt-3.5-turbo-1106':
         completion = openai_client.chat.completions.create(
             model="gpt-3.5-turbo-1106",