ai: I don't care about streaming respones :)

jarvis.py

@@ -17,9 +17,7 @@ import gradio as gr
 import requests
 import json
 import os
-import threading
 import random
-import time
 import pytesseract
 import pdfplumber
 import docx
@@ -53,11 +51,6 @@ session = requests.Session()
 def get_model_key(display_name):
     return next((k for k, v in MODEL_MAPPING.items() if v == display_name), MODEL_CHOICES[0])
 
-def simulate_streaming_response(text):
-    for line in text.splitlines():
-        yield line + "\n"
-        time.sleep(0.05)
-
 def extract_file_content(file_path):
     ext = Path(file_path).suffix.lower()
     content = ""
@@ -102,8 +95,7 @@ def extract_file_content(file_path):
 
 def chat_with_model(history, user_input, selected_model_display):
     if not LINUX_SERVER_PROVIDER_KEYS or not LINUX_SERVER_HOSTS:
-        yield RESPONSES["RESPONSE_3"]
-        return
+        return RESPONSES["RESPONSE_3"]
     selected_model = get_model_key(selected_model_display)
     model_config = MODEL_CONFIG.get(selected_model, DEFAULT_CONFIG)
     messages = [{"role": "user", "content": user} for user, _ in history]
@@ -118,11 +110,10 @@ def chat_with_model(history, user_input, selected_model_display):
                 response = session.post(host, json=data, headers={"Authorization": f"Bearer {api_key}"})
                 if response.status_code < 400:
                     ai_text = response.json().get("choices", [{}])[0].get("message", {}).get("content", RESPONSES["RESPONSE_2"])
-                    yield from simulate_streaming_response(ai_text)
-                    return
+                    return ai_text
             except requests.exceptions.RequestException:
                 continue
-    yield RESPONSES["RESPONSE_3"]
+    return RESPONSES["RESPONSE_3"]
 
 def respond(multi_input, history, selected_model_display):
     message = {"text": multi_input.get("text", "").strip(), "files": multi_input.get("files", [])}
@@ -139,10 +130,8 @@ def respond(multi_input, history, selected_model_display):
     if message["text"]:
         combined_input += message["text"]
     history.append([combined_input, ""])
-    ai_response = ""
-    for chunk in chat_with_model(history, combined_input, selected_model_display):
-        ai_response += chunk
-        history[-1][1] = ai_response
+    ai_response = chat_with_model(history, combined_input, selected_model_display)
+    history[-1][1] = ai_response
     return history, gr.MultimodalTextbox(value=None, interactive=True)
 
 def change_model(new_model_display):