Update app.py

app.py

@@ -1,91 +1,35 @@
-import os
-from huggingface_hub import InferenceClient
 import gradio as gr
 
-# — your imports for embeddings, etc. —
-from sentence_transformers import SentenceTransformer
-import torch
-from sklearn.metrics.pairwise import cosine_similarity
+def chatbot_response(message, history):
+    # Example knowledge base — replace or expand with your own logic
+    responses = {
+        "covid": "COVID-19 is caused by the SARS-CoV-2 virus. Vaccination, mask use, and hand hygiene help prevent transmission.",
+        "flu": "Influenza (the flu) is caused by influenza viruses. Annual flu vaccines are recommended for everyone over 6 months old.",
+        "mental health": "Mental health is vital for overall well-being. Prioritizing self-care, social connection, and seeking professional help when needed can make a big difference.",
+        "nutrition": "A balanced diet with fruits, vegetables, whole grains, and lean proteins supports long-term health."
+    }
 
-# (Assuming you have helper functions get_top_chunks, etc.)
+    message_lower = message.lower()
+    for key, response in responses.items():
+        if key in message_lower:
+            return response
 
-# Create InferenceClient (no model name here)
-client = InferenceClient()
+    return "I'm not sure about that topic, but I can help you find reliable public health information."
 
-def respond(message, history):
-    # Your logic to pick context, e.g.:
-    info = get_top_chunks(message, chunk_embeddings, cleaned_chunks)
-    system_prompt = f"You are a friendly public health chatbot. Use this info as context: {info}"
-    messages = [{'role': 'system', 'content': system_prompt}]
-    if history:
-        messages.extend(history)
-    messages.append({'role': 'user', 'content': message})
+# Build Gradio interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🩺 Public Health Bot\n### Ask me anything about health, wellness, and disease prevention!")
 
-    try:
-        # Use the new chat completions API
-        response = client.chat.completions.create(
-            model="microsoft/phi-4",
-            messages=messages,
-            max_tokens=500,
-            top_p=0.8
-        )
-        # Extract the content
-        text = response.choices[0].message.content.strip()
-        return text
-    except Exception as e:
-        # Log error and return fallback message
-        print("Error during chat completion:", e)
-        return "Sorry — I ran into an internal error while generating a response."
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Type your question here...", label="Your message")
 
-def title():
-    return "Public Health Bot"
+    def respond(message, history):
+        response = chatbot_response(message, history)
+        history.append((message, response))
+        return "", history
 
-def description():
-    return (
-        "Public Health Bot uses scientific sources to answer questions about public health. "
-        "Ask me anything about epidemiology, prevention, health policy, etc."
-    )
-
-def css():
-    return """
-    /* custom CSS if any */
-    """
-
-def load_model():
-    # If you have any model loading (e.g. embedding model), do it here
-    global chunk_embeddings, cleaned_chunks
-    # Example:
-    model = SentenceTransformer("all-MiniLM-L6-v2")
-    # Load your chunks, embeddings, etc.
-    # chunk_embeddings = ...
-    # cleaned_chunks = ...
-    return
-
-def main():
-    load_model()
-    with gr.Blocks(css=css()) as demo:
-        chatbot = gr.Chatbot()
-        msg = gr.Textbox(
-            placeholder="Ask me a question about public health...",
-            show_label=False,
-            lines=1
-        )
-        submit = gr.Button("Send")
-        clear = gr.Button("Clear")
-
-        # Note: Temporarily disable examples to avoid startup crashes
-        demo_interface = gr.ChatInterface(
-            fn=respond,
-            title=title(),
-            description=description(),
-            type="messages",
-            theme="default"
-            # examples=[["What is epidemiology?"], ["How to prevent spread of disease?"]]
-        )
-
-        demo_interface.queue()
-    return demo
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
 
+# Run the app
 if __name__ == "__main__":
-    demo = main()
-    demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860)))
+    demo.launch()