added word streaming

app.py

@@ -70,26 +70,32 @@ def respond(message, chat_history):
         model="gpt-3.5-turbo",
         messages= prompt,
         temperature=0.5,
-        max_tokens=1000
-        ).choices[0].message.content
-    chat_history.append((message, response))
-    return "",chat_history
-    #Streaming the tokens
-    # for idx, response in enumerate(stream):
-    #         text_token = response.token.text
-
-    #         if response.details:
-    #             return
-
-    #         if idx == 0 and text_token.startswith(" "):
-    #             text_token = text_token[1:]
-
-    #         acc_text += text_token
-    #         last_turn = list(chat_history.pop(-1))
-    #         last_turn[-1] += acc_text
-    #         chat_history = chat_history + [last_turn]
-    #         yield "", chat_history
-    #         acc_text = ""
+        max_tokens=1000,
+        stream = True
+        )#.choices[0].message.content
+    # chat_history.append((message, response))
+
+    token_counter = 0 
+    partial_words = "" 
+
+    for chunk in response:
+        chunk_message = chunk['choices'][0]['delta']
+        if(len(chat_history))<1:
+            # print("entró acaá")
+            partial_words += chunk_message.content
+            chat_history.append([message,chunk_message.content])
+        else:
+            # print("antes", chat_history)
+            if(len(chunk_message)!=0):
+                if(len(chunk_message)==2):
+                    partial_words += chunk_message.content
+                    chat_history.append([message,chunk_message.content])
+                else:
+                    partial_words += chunk_message.content
+                    chat_history[-1] =([message,partial_words])
+        yield "",chat_history
+
+    # return "",chat_history
 
 with gr.Blocks() as demo:
     gr.Markdown("""