Deploy lightweight Gradio frontend with Modal backend integration

README.md

@@ -8,12 +8,22 @@ colorTo: "green"
 sdk: "gradio"
 app_file: "app.py"
 pinned: false
-# This app runs on the free CPU tier, as all heavy work is done by Modal
+# --- THIS IS THE MOST IMPORTANT LINE ---
+# This line tells Hugging Face that your app.py script needs permission
+# to access the secret named "MODAL_BACKEND_URL". Without this, os.getenv()
+# will not work.
 secrets:
 - MODAL_BACKEND_URL
 ---
 
 # 🧠 GHAPA: Intelligent Health AI Assistant (Powered by Modal ⚡)
-This is the user interface for the GHAPA system. It provides a simple, responsive UI that communicates with a powerful, GPU-accelerated backend hosted on Modal Labs.
+This is the user interface for the GHAPA multi-agent system. It provides a simple, responsive UI that communicates with a powerful, GPU-accelerated backend hosted on Modal Labs.
 
-Ask your health question in **English, Spanish, Hindi, or French**. The system will auto-detect your language, find the most relevant PubMed article, and provide a trusted answer at high speed.
+This decoupled architecture ensures that the user interface remains lightweight and fast, while all computationally intensive AI tasks are handled by a scalable, on-demand backend.
+
+### How to Use
+Ask your health question in **English, Spanish, Hindi, or French**. The system will:
+1.  Auto-detect your language.
+2.  Send the query to the Modal backend.
+3.  Receive a trusted answer generated from PubMed articles.
+4.  Display the result, usually within seconds.