Update app.py

app.py

@@ -1,7 +1,9 @@
 import gradio as gr
-from together import Together
+import pandas as pd
+import numpy as np
 import os
 import base64
+from together import Together
 
 def extract_medicines(api_key, image):
     """
@@ -56,39 +58,241 @@ def extract_medicines(api_key, image):
     except Exception as e:
         return f"Error: {str(e)}"
 
-# Create Gradio interface
-with gr.Blocks(title="Prescription Medicine Extractor") as app:
-    gr.Markdown("## Prescription Medicine Extractor")
-    gr.Markdown("Upload a prescription image to extract medicine names using Together AI's Llama-Vision-Free model.")
-    
-    with gr.Row():
-        with gr.Column():
-            api_key_input = gr.Textbox(
-                label="Together API Key", 
-                placeholder="Enter your Together API key here...",
-                type="password"
-            )
-            image_input = gr.Image(type="filepath", label="Upload Prescription Image")
-            submit_btn = gr.Button("Extract Medicines")
+def recommend_medicine(api_key, medicine_name, csv_file=None):
+    """
+    Use Together API to recommend alternative medicines based on input medicine name
+    using data from the provided CSV file with specific column structure
+    """
+    try:
+        # If CSV file is provided, use it; otherwise use default
+        if csv_file is not None:
+            # Read the uploaded CSV
+            if isinstance(csv_file, str):  # Path to default CSV
+                df = pd.read_csv(csv_file)
+            else:  # Uploaded file
+                df = pd.read_csv(csv_file.name)
+        else:
+            # Use the default medicine_dataset.csv in the current directory
+            df = pd.read_csv("medicine_dataset.csv")
+        
+        # Verify the medicine name exists in the dataset
+        if medicine_name not in df['name'].values:
+            return f"Error: Medicine '{medicine_name}' not found in the dataset. Please check the spelling or try another medicine."
+        
+        # Create system prompt with CSV data and column structure information
+        system_prompt = f"""Develop an expert system to recommend alternative medicines for {medicine_name} based on the medicine dataset. The dataset has the following columns:
+- name: Medicine name
+- substitute0 through substitute4: Potential substitute medicines
+- sideEffect0 through sideEffect41: Possible side effects
+- use0 through use4: Medical uses
+- Chemical Class: The chemical classification
+- Habit Forming: Whether the medicine is habit-forming
+- Therapeutic Class: The therapeutic classification
+- Action Class: How the medicine works
+
+Your task is to:
+1. Find the row in the dataset where name matches exactly "{medicine_name}"
+2. Find alternatives by:
+   - Using the substitute0-substitute4 values as primary alternatives
+   - Finding other medicines with similar Chemical Class, Therapeutic Class, or Action Class
+
+For each recommended alternative, provide:
+- Name of the alternative medicine
+- All side effects (from relevant sideEffect columns)
+- All uses (from relevant use columns)
+- Chemical Class, Habit Forming status, Therapeutic Class, and Action Class
+- A similarity score (0-1) indicating how similar it is to the original medicine
+
+Format the response clearly with headings for "Recommended Medicines", "Medicine Details", and "Similarity Score".
+"""
+
+        # Extract the specific row containing the medicine data to give more context
+        medicine_data = df[df['name'] == medicine_name]
+        if not medicine_data.empty:
+            # Convert the specific medicine data to a string representation
+            medicine_info = medicine_data.to_string(index=False)
+            system_prompt += f"\n\nThe specific data for {medicine_name} is:\n{medicine_info}\n\n"
             
-        with gr.Column():
-            output = gr.Textbox(label="Extracted Medicines", lines=10)
+            # Extract substitute information for better recommendations
+            substitutes = []
+            for i in range(5):  # substitute0 through substitute4
+                col_name = f"substitute{i}"
+                if col_name in medicine_data.columns:
+                    sub_value = medicine_data[col_name].iloc[0]
+                    if pd.notna(sub_value) and sub_value != "":
+                        substitutes.append(sub_value)
+            
+            if substitutes:
+                system_prompt += f"The primary substitutes for {medicine_name} are: {', '.join(substitutes)}\n\n"
+        
+        # Include a sample of other medicines for comparison
+        other_medicines = df[df['name'] != medicine_name].sample(min(10, len(df)-1)) if len(df) > 1 else pd.DataFrame()
+        if not other_medicines.empty:
+            system_prompt += "Here's a sample of other medicines in the dataset for comparison:\n"
+            for idx, row in other_medicines.iterrows():
+                system_prompt += f"- {row['name']}: Chemical Class: {row['Chemical Class']}, Therapeutic Class: {row['Therapeutic Class']}, Action Class: {row['Action Class']}\n"
+
+        # Initialize Together client with the API key
+        client = Together(api_key=api_key)
+        
+        # Make API call
+        response = client.chat.completions.create(
+            model="meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+            messages=[
+                {
+                    "role": "system",
+                    "content": system_prompt
+                },
+                {
+                    "role": "user",
+                    "content": f"Please recommend alternatives for {medicine_name} based on the dataset. Include detailed information about each alternative."
+                }
+            ],
+            max_tokens=2000
+        )
+        
+        # Return the generated recommendations
+        return response.choices[0].message.content
     
-    submit_btn.click(
-        fn=extract_medicines, 
-        inputs=[api_key_input, image_input], 
-        outputs=output
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+def send_medicine_to_recommender(api_key, medicine_names, csv_file=None):
+    """
+    Takes medicine names extracted from prescription and gets recommendations
+    """
+    if not medicine_names or medicine_names.startswith("Error") or medicine_names.startswith("Please"):
+        return "Please extract valid medicine names first"
+    
+    # Extract the first medicine name from the list (assuming it's the first line or first item)
+    medicine_lines = medicine_names.strip().split('\n')
+    if not medicine_lines:
+        return "No valid medicine name found in extraction results"
+    
+    # Get the first medicine name (remove any bullet points or numbers)
+    first_medicine = medicine_lines[0]
+    # Clean up the medicine name (remove bullets, numbers, etc.)
+    first_medicine = first_medicine.lstrip('•-*0123456789. ').strip()
+    
+    # Check if we have a valid medicine name
+    if not first_medicine:
+        return "Could not identify a valid medicine name from extraction"
+    
+    # Call the recommend medicine function with the first extracted medicine
+    return recommend_medicine(api_key, first_medicine, csv_file)
+
+# Create Gradio interface with tabs for both functionalities
+with gr.Blocks(title="Medicine Assistant") as app:
+    gr.Markdown("# Medicine Assistant")
+    gr.Markdown("This application helps you extract medicine names from prescriptions and find alternative medicines.")
+    
+    # API key input (shared between tabs)
+    api_key_input = gr.Textbox(
+        label="Together API Key", 
+        placeholder="Enter your Together API key here...",
+        type="password"
     )
     
+    with gr.Tabs():
+        with gr.Tab("Prescription Medicine Extractor"):
+            gr.Markdown("## Prescription Medicine Extractor")
+            gr.Markdown("Upload a prescription image to extract medicine names using Together AI's Llama-Vision-Free model.")
+            
+            with gr.Row():
+                with gr.Column():
+                    image_input = gr.Image(type="filepath", label="Upload Prescription Image")
+                    extract_btn = gr.Button("Extract Medicines")
+                    recommend_from_extract_btn = gr.Button("Get Recommendations for First Medicine")
+                    
+                with gr.Column():
+                    extracted_output = gr.Textbox(label="Extracted Medicines", lines=10)
+                    recommendation_from_extract_output = gr.Markdown(label="Recommendations")
+            
+            # Connect the buttons to functions
+            extract_btn.click(
+                fn=extract_medicines, 
+                inputs=[api_key_input, image_input], 
+                outputs=extracted_output
+            )
+            
+            recommend_from_extract_btn.click(
+                fn=send_medicine_to_recommender,
+                inputs=[api_key_input, extracted_output, None],  # Pass None as csv_file to use default
+                outputs=recommendation_from_extract_output
+            )
+            
+            gr.Markdown("""
+            ### How to use:
+            1. Enter your Together API key
+            2. Upload a clear image of a prescription
+            3. Click 'Extract Medicines' to see the identified medicines
+            4. Optionally click 'Get Recommendations for First Medicine' to find alternatives
+            
+            ### Note:
+            - Your API key is used only for the current session
+            - For best results, ensure the prescription image is clear and readable
+            """)
+        
+        with gr.Tab("Medicine Alternative Recommender"):
+            gr.Markdown("## Medicine Alternative Recommender")
+            gr.Markdown("This tool recommends alternative medicines based on an input medicine name using the Together API.")
+            
+            with gr.Row():
+                with gr.Column():
+                    medicine_name = gr.Textbox(
+                        label="Medicine Name", 
+                        placeholder="Enter a medicine name exactly as it appears in the dataset"
+                    )
+                    csv_file = gr.File(
+                        label="Upload Medicine CSV (Optional)", 
+                        file_types=[".csv"],
+                        type="file"
+                    )
+                    gr.Markdown("If no CSV is uploaded, the app will use the default 'medicine_dataset.csv' file.")
+                    
+                    submit_btn = gr.Button("Get Recommendations", variant="primary")
+                
+                with gr.Column():
+                    recommendation_output = gr.Markdown(label="Recommendations")
+            
+            submit_btn.click(
+                recommend_medicine,
+                inputs=[api_key_input, medicine_name, csv_file],
+                outputs=recommendation_output
+            )
+
+            gr.Markdown("""
+            ## How to use this tool:
+            1. Enter your Together API key (same key used across the application)
+            2. Enter a medicine name **exactly as it appears** in the CSV file
+            3. Optionally upload a custom medicine dataset CSV file (otherwise the default medicine_dataset.csv will be used)
+            4. Click "Get Recommendations" to see alternatives
+            
+            ### CSV Format Requirements:
+            The app expects a CSV with these columns:
+            - `name`: Medicine name
+            - `substitute0` through `substitute4`: Potential substitute medicines
+            - `sideEffect0` through `sideEffect41`: Possible side effects
+            - `use0` through `use4`: Medical uses
+            - `Chemical Class`: The chemical classification
+            - `Habit Forming`: Whether the medicine is habit-forming
+            - `Therapeutic Class`: The therapeutic classification
+            - `Action Class`: How the medicine works
+            """)
+    
     gr.Markdown("""
-    ### How to use:
-    1. Enter your Together API key
-    2. Upload a clear image of a prescription
-    3. Click 'Extract Medicines' to see the results
-    
-    ### Note:
-    - Your API key is used only for the current session
-    - For best results, ensure the prescription image is clear and readable
+    ## About This Application
+    
+    This Medicine Assistant application combines two powerful tools:
+    
+    1. **Prescription Medicine Extractor**: Uses computer vision AI to identify medicine names from prescription images
+    2. **Medicine Alternative Recommender**: Provides detailed information about alternative medications
+    
+    Both tools utilize the Together AI platform for advanced AI capabilities. Your API key is not stored and is only used to make API calls during your active session.
+    
+    ### Important Note
+    
+    This application is for informational purposes only. Always consult with a healthcare professional before making any changes to your medication regimen.
     """)
 
 # Launch the app