Update app.py

app.py

@@ -6,9 +6,6 @@ from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 import os
 from dotenv import load_dotenv
-import gradio as gr
-import requests
-import asyncio
 from pydantic import BaseModel
 
 load_dotenv()
@@ -50,7 +47,7 @@ def generate_model_response(model, inputs):
     try:
         if model is None:
             return "Model loading failed."
-        response = model(inputs, max_tokens=512) #max_tokens adjusted for practicality
+        response = model(inputs, max_tokens=512)
         return remove_duplicates(response['choices'][0]['text'])
     except Exception as e:
         print(f"Error generating response: {e}")
@@ -65,7 +62,7 @@ app.add_middleware(
 @app.post("/generate")
 async def generate(request: ChatRequest):
     inputs = normalize_input(request.message)
-    chunk_size = 400  #Reduced chunk size
+    chunk_size = 400
     chunks = [inputs[i:i + chunk_size] for i in range(0, len(inputs), chunk_size)]
     overall_response = ""
     for chunk in chunks:
@@ -76,24 +73,6 @@ async def generate(request: ChatRequest):
             overall_response += f"**{response['model']}:**\n{response['response']}\n\n"
     return {"response": overall_response}
 
-async def process_message(message, history):
-    try:
-        port = os.environ.get("PORT", 7860)
-        response = requests.post(f"http://localhost:{port}/generate", json={"message": message}).json()
-        formatted_response = response["response"]
-        history.append((message, formatted_response))
-        return history, history
-    except requests.exceptions.RequestException as e:
-        return history, f"Error: {e}"
-
-iface = gr.Interface(
-    fn=process_message,
-    inputs=[gr.Textbox(lines=2, placeholder="Enter your message here..."), gr.State([])],
-    outputs=[gr.Chatbot(), gr.State([])],
-    title="Multi-Model LLM API", description="Enter a message and get responses from multiple LLMs."
-)
-
 if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
-    uvicorn.run(app, host="0.0.0.0", port=port)
-    iface.launch(server_port=7860)
+    uvicorn.run(app, host="0.0.0.0", port=port)