src/app.py

import os
import gradio as gr
from llama_index.core import Settings
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from parse_tabular import create_symptom_index  # Change this import
import json

# Configure embeddings globally
Settings.embed_model = HuggingFaceEmbedding(
    model_name="sentence-transformers/all-MiniLM-L6-v2"
)

# Create the index at startup
symptom_index = create_symptom_index()

# --- System prompt ---
SYSTEM_PROMPT = """
You are a medical assistant helping a user narrow down to the most likely ICD-10 code.
At each turn, EITHER ask one focused clarifying question (e.g. "Is your cough dry or productive?")
or, if you have enough info, output a final JSON with fields:
{"diagnoses":[…], "confidences":[…]}.
"""

def process_speech(new_transcript, history):
    if not new_transcript:
        return history
    
    try:
        response = symptom_index.as_query_engine().query(new_transcript)
        
        formatted_response = {
            "diagnoses": [str(response).split(":")[0]],
            "confidences": [0.8],
            "follow_up": "Is the cough productive or dry?"
        }
        
        history.append({"role": "user", "content": new_transcript})
        history.append({"role": "assistant", "content": json.dumps(formatted_response, indent=2)})
        
    except Exception as e:
        error_response = {"error": str(e), "status": "error"}
        history.append({"role": "user", "content": new_transcript})
        history.append({"role": "assistant", "content": json.dumps(error_response, indent=2)})
    
    return history

# Build Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Symptom to ICD-10 Code Lookup")
    
    chatbot = gr.Chatbot(
        label="Conversation",
        type="messages",
        height=400
    )
    
    microphone = gr.Microphone(
        streaming=True,
        type="filepath"  # Use 'filepath' to get the path to the recorded audio file
    )
    
    # Connect the streaming microphone to the chat
    microphone.stream(
        fn=process_speech,
        inputs=[microphone, chatbot],
        outputs=chatbot,
        show_progress="hidden"
    )

if __name__ == "__main__":
    demo.launch(
        server_name="0.0.0.0",
        server_port=7860,
        mcp_server=True
    )