Update app.py

app.py

@@ -1,8 +1,8 @@
 from flask import Flask, render_template, request, jsonify
-from llm.agents import query_all_llms_sync
-from llm.aggregator import aggregate_responses
+from llm.agents import query_moa_chain
 import os
 import dotenv
+import asyncio
 
 # Load secrets from .env
 dotenv.load_dotenv()
@@ -27,16 +27,15 @@ def chat():
         return jsonify({"error": "Empty prompt."}), 400
 
     try:
-        # Step 1: Query all agents synchronously
-        agent_outputs = query_all_llms_sync(user_input, settings)
+        # Fully async call to query MoA chain
+        results = asyncio.run(query_moa_chain(user_input, settings))
 
-        # Step 2: Aggregate responses with LLM #4
-        final_response = aggregate_responses(agent_outputs, settings)
+        final_response = "\n".join(results)
 
-        return jsonify({"response": f"Final synthesized response based on multiple agents:\n{final_response}"})
+        return jsonify({"response": final_response})
 
     except Exception as e:
         return jsonify({"error": str(e)}), 500
 
 if __name__ == "__main__":
-    app.run(host="0.0.0.0", port=7860, debug=False)
+    app.run(host="0.0.0.0", port=7860, debug=False)  # Hugging Face uses port 7860