Update app.py

app.py

@@ -1,10 +1,8 @@
 import gradio as gr
 import tensorflow as tf
 import pdfplumber
-from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import timm
-import torch
-import pandas as pd
 
 # Load pre-trained zero-shot model for text classification
 classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
@@ -27,18 +25,27 @@ disease_details = {
     "diabetes": {"medication": "Metformin or insulin", "precaution": "Monitor sugar levels", "doctor": "Endocrinologist"},
 }
 
-# Passwords
-doctor_password = "doctor123"
-
-# Load PastelMedAW model
+# Doctor consultant models
 pastel_tokenizer = AutoTokenizer.from_pretrained("ahmed-7124/PastelMedAW")
 pastel_model = AutoModelForCausalLM.from_pretrained("ahmed-7124/PastelMedAW")
-
-# Load LynxMedAW model
 lynx_tokenizer = AutoTokenizer.from_pretrained("ahmed-7124/LynxMedAW")
 lynx_model = AutoModelForCausalLM.from_pretrained("ahmed-7124/LynxMedAW")
 
-# Functions
+# Passwords
+doctor_password = "doctor123"
+
+# Helper Functions
+def generate_consultation_response(prompt):
+    pastel_input = pastel_tokenizer(prompt, return_tensors="pt")
+    pastel_response = pastel_model.generate(**pastel_input, max_length=200, num_return_sequences=1)
+    pastel_output = pastel_tokenizer.decode(pastel_response[0], skip_special_tokens=True)
+
+    lynx_input = lynx_tokenizer(prompt, return_tensors="pt")
+    lynx_response = lynx_model.generate(**lynx_input, max_length=200, num_return_sequences=1)
+    lynx_output = lynx_tokenizer.decode(lynx_response[0], skip_special_tokens=True)
+
+    return f"**PastelMedAW Response:**\n{pastel_output}\n\n**LynxMedAW Response:**\n{lynx_output}"
+
 def register_patient(name, age, gender, password):
     patient_id = len(patients_db) + 1
     patients_db.append({
@@ -121,113 +128,33 @@ def doctor_dashboard(password):
                        f"👩‍⚕️ Recommended Doctor: {patient['Doctor']}")
     return "\n\n".join(details)
 
-def doctor_consultant(prompt):
-    # Generate response from PastelMedAW
-    pastel_input = pastel_tokenizer(prompt, return_tensors="pt")
-    pastel_output = pastel_model.generate(**pastel_input, max_length=200, num_return_sequences=1)
-    pastel_response = pastel_tokenizer.decode(pastel_output[0], skip_special_tokens=True)
-
-    # Generate response from LynxMedAW
-    lynx_input = lynx_tokenizer(prompt, return_tensors="pt")
-    lynx_output = lynx_model.generate(**lynx_input, max_length=200, num_return_sequences=1)
-    lynx_response = lynx_tokenizer.decode(lynx_output[0], skip_special_tokens=True)
-
-    # Combine responses
-    combined_response = (
-        f"🩺 **PastelMed Response:**\n{pastel_response}\n\n"
-        f"🩺 **LynxMed Response:**\n{lynx_response}"
-    )
-    return combined_response
-
 # Gradio Interfaces
 registration_interface = gr.Interface(
     fn=register_patient,
-    inputs=[gr.Textbox(label="Patient Name"),
-            gr.Number(label="Age"),
-            gr.Radio(label="Gender", choices=["Male", "Female", "Other"]),
-            gr.Textbox(label="Set Password", type="password")],
-    outputs="text",
-)
-
-pdf_extraction_interface = gr.Interface(
-    fn=extract_pdf_report,
-    inputs=gr.File(label="Upload PDF Report"),
+    inputs=[gr.Textbox(label="Patient Name"), gr.Number(label="Age"), gr.Radio(label="Gender", choices=["Male", "Female", "Other"]), gr.Textbox(label="Set Password", type="password")],
     outputs="text",
 )
 
-report_analysis_interface = gr.Interface(
-    fn=analyze_report,
-    inputs=[gr.Number(label="Patient ID"), gr.Textbox(label="Report Text")],
-    outputs="text",
-)
-
-eye_disease_interface = gr.Interface(
-    fn=predict_eye_disease,
-    inputs=gr.Image(label="Upload an Eye Image", type="numpy"),
-    outputs="text",
-)
-
-doctor_space_interface = gr.Interface(
-    fn=doctor_space,
-    inputs=gr.Number(label="Patient ID"),
-    outputs="text",
-)
-
-pharmacist_space_interface = gr.Interface(
-    fn=pharmacist_space,
-    inputs=gr.Number(label="Patient ID"),
-    outputs="text",
-)
-
-patient_dashboard_interface = gr.Interface(
-    fn=patient_dashboard,
-    inputs=[gr.Number(label="Patient ID"), gr.Textbox(label="Password", type="password")],
-    outputs="text",
-)
-
-doctor_dashboard_interface = gr.Interface(
-    fn=doctor_dashboard,
-    inputs=gr.Textbox(label="Doctor Password", type="password"),
-    outputs="text",
-)
-
-doctor_consultant_interface = gr.Interface(
-    fn=doctor_consultant,
-    inputs=gr.Textbox(lines=5, label="Enter Symptoms or Query"),
-    outputs="text",
-    title="Doctor Consultant Assistant",
-    description="Get medical advice or suggestions using two advanced AI models: PastelMedAW and LynxMedAW.",
-)
+pdf_extraction_interface = gr.Interface(fn=extract_pdf_report, inputs=gr.File(label="Upload PDF Report"), outputs="text")
+report_analysis_interface = gr.Interface(fn=analyze_report, inputs=[gr.Number(label="Patient ID"), gr.Textbox(label="Report Text")], outputs="text")
+eye_disease_interface = gr.Interface(fn=predict_eye_disease, inputs=gr.Image(label="Upload Eye Image", type="numpy"), outputs="text")
+doctor_space_interface = gr.Interface(fn=doctor_space, inputs=gr.Number(label="Patient ID"), outputs="text")
+pharmacist_space_interface = gr.Interface(fn=pharmacist_space, inputs=gr.Number(label="Patient ID"), outputs="text")
+patient_dashboard_interface = gr.Interface(fn=patient_dashboard, inputs=[gr.Number(label="Patient ID"), gr.Textbox(label="Password", type="password")], outputs="text")
+doctor_dashboard_interface = gr.Interface(fn=doctor_dashboard, inputs=gr.Textbox(label="Doctor Password", type="password"), outputs="text")
+doctor_consultant_interface = gr.Interface(fn=generate_consultation_response, inputs=gr.Textbox(label="Enter Symptoms or Query"), outputs="text")
 
 # Gradio App Layout
 with gr.Blocks() as app:
     gr.Markdown("# Medico GPT")
-    
-    with gr.Tab("Patient Registration"):
-        registration_interface.render()
-    
-    with gr.Tab("Analyze Medical Report"):
-        report_analysis_interface.render()
-    
-    with gr.Tab("Extract PDF Report"):
-        pdf_extraction_interface.render()
-    
-    with gr.Tab("Ophthalmologist Space"):
-        eye_disease_interface.render()
-    
-    with gr.Tab("Doctor Space"):
-        doctor_space_interface.render()
-    
-    with gr.Tab("Pharmacist Space"):
-        pharmacist_space_interface.render()
-    
-    with gr.Tab("Patient Dashboard"):
-        patient_dashboard_interface.render()
-    
-    with gr.Tab("Doctor Dashboard"):
-        doctor_dashboard_interface.render()
-    
-    with gr.Tab("Doctor Consultant/Assistant"):
-        doctor_consultant_interface.render()
+    with gr.Tab("Patient Registration"): registration_interface.render()
+    with gr.Tab("Analyze Medical Report"): report_analysis_interface.render()
+    with gr.Tab("Extract PDF Report"): pdf_extraction_interface.render()
+    with gr.Tab("Ophthalmologist Space"): eye_disease_interface.render()
+    with gr.Tab("Doctor Space"): doctor_space_interface.render()
+    with gr.Tab("Pharmacist Space"): pharmacist_space_interface.render()
+    with gr.Tab("Patient Dashboard"): patient_dashboard_interface.render()
+    with gr.Tab("Doctor Dashboard"): doctor_dashboard_interface.render()
+    with gr.Tab("Doctor Consultant"): doctor_consultant_interface.render()
 
 app.launch(share=True)