Update app.py

app.py

@@ -2,27 +2,7 @@ import gradio as gr
 from transformers import pipeline
 import threading
 
-# Number of backend servers (simulated instances of the pipeline)
-NUM_BACKEND_SERVERS = 3
 
-# Initialize backend servers (pipelines) and availability flags
-backend_servers = [
-    pipeline("question-answering", model="google-bert/bert-large-uncased-whole-word-masking-finetuned-squad"),
-    pipeline("question-answering", model="deepset/roberta-base-squad2"),
-    pipeline("question-answering", model="Intel/dynamic_tinybert")
-] * (NUM_BACKEND_SERVERS // 3)
-backend_locks = [threading.Lock() for _ in range(NUM_BACKEND_SERVERS)]
-
-# Function to select a backend server (pipeline) based on availability
-def select_backend():
-    for i in range(NUM_BACKEND_SERVERS):
-        if backend_locks[i].acquire(blocking=False):
-            return i
-    return None
-
-# Function to release a backend server (pipeline) after processing a request
-def release_backend(index):
-    backend_locks[index].release()
 
 # Use a pipeline as a high-level helper
 from transformers import pipeline
@@ -40,7 +20,6 @@ def chatbot_interface(Question):
     return answer
 
 knowledge_base_text = """
-
 3D+ :  ; 
 3GGT : The 3 Great Growth Things ; 
 4D : Four "D" model ;