Update app.py

app.py

@@ -1,5 +1,5 @@
 from flask import Flask, render_template, request, jsonify
-from llm.agents import query_all_llms_sync  # fixed: use the sync wrapper
+from llm.agents import query_all_llms
 from llm.aggregator import aggregate_responses
 import os
 import dotenv
@@ -7,7 +7,7 @@ import dotenv
 # Load secrets from .env
 dotenv.load_dotenv()
 
-app = Flask(__name__, static_url_path='/static')
+app = Flask(__name__)
 
 @app.route("/")
 def index():
@@ -23,15 +23,16 @@ def chat():
         return jsonify({"error": "Empty prompt."}), 400
 
     try:
-        # ✅ fixed: run the async LLM queries safely in sync context
-        agent_outputs = query_all_llms_sync(user_input, settings)
+        # Step 1: Query all agents asynchronously
+        agent_outputs = query_all_llms(user_input, settings)
 
-        final_response = aggregate_responses(agent_outputs)
+        # Step 2: Aggregate responses with LLM #4
+        final_response = aggregate_responses(agent_outputs, settings)
 
-        return jsonify({"response": final_response})
+        return jsonify({"response": f"Final synthesized response based on multiple agents:\n{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