Update app.py

app.py

@@ -2,10 +2,10 @@ from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from llama_cpp import Llama
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from tqdm import tqdm
 import uvicorn
 from dotenv import load_dotenv
 import re
+import huggingface_hub
 import spaces
 
 load_dotenv()
@@ -59,7 +59,7 @@ class ModelManager:
                 try:
                     model = future.result()
                     models.append(model)
-                except Exception as e:
+                except Exception:
                     pass
         
         self.models = models
@@ -67,7 +67,6 @@ class ModelManager:
         return self.models
 
 model_manager = ModelManager()
-
 global_data['models'] = model_manager.load_all_models()
 
 class ChatRequest(BaseModel):
@@ -130,11 +129,11 @@ async def generate_chat(request: ChatRequest):
 
     with ThreadPoolExecutor() as executor:
         futures = [executor.submit(generate_chat_response, request, model_data) for model_data in global_data['models']]
-        for future in tqdm(as_completed(futures), total=num_models):
+        for future in as_completed(futures):
             try:
                 response = future.result()
                 responses.append(response)
-            except Exception as exc:
+            except Exception:
                 pass
 
     if not responses:
@@ -148,4 +147,4 @@ async def generate_chat(request: ChatRequest):
     }
 
 if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=7860)