Create app.py

app.py

@@ -0,0 +1,122 @@
+import gradio as gr
+from datasets import load_dataset
+import pandas as pd
+import random
+
+# Load the Indian Law dataset
+print("Loading Indian Law Dataset...")
+ds = load_dataset("viber1/indian-law-dataset")
+
+# Convert to pandas for easier manipulation
+df = pd.DataFrame(ds['train'])
+
+print(f"Dataset loaded successfully with {len(df)} entries")
+print(f"Dataset columns: {df.columns.tolist()}")
+
+# Preview first few entries
+print("\nFirst 3 entries:")
+for i in range(min(3, len(df))):
+    print(f"\nEntry {i+1}:")
+    for col in df.columns:
+        print(f"  {col}: {df.iloc[i][col][:100] if isinstance(df.iloc[i][col], str) else df.iloc[i][col]}...")
+
+def search_legal_info(question):
+    """Search the dataset for relevant legal information based on user question"""
+    if not question or len(question.strip()) == 0:
+        return "Please enter a legal question."
+    
+    question_lower = question.lower()
+    results = []
+    
+    # Search through the dataset
+    for idx, row in df.iterrows():
+        # Check all text columns for matches
+        for col in df.columns:
+            if isinstance(row[col], str) and any(word in row[col].lower() for word in question_lower.split()):
+                results.append(row.to_dict())
+                break
+        
+        if len(results) >= 5:  # Limit to top 5 results
+            break
+    
+    if not results:
+        return "No relevant information found in the dataset. Try rephrasing your question or use different keywords."
+    
+    # Format the response
+    response = "📋 **Legal Information Found:**\n\n"
+    for i, result in enumerate(results, 1):
+        response += f"**Result {i}:**\n"
+        for key, value in result.items():
+            if value and isinstance(value, str):
+                # Truncate long text
+                display_value = value[:500] + "..." if len(value) > 500 else value
+                response += f"- **{key}**: {display_value}\n"
+        response += "\n---\n\n"
+    
+    return response
+
+def get_random_sample():
+    """Get a random entry from the dataset"""
+    random_idx = random.randint(0, len(df) - 1)
+    sample = df.iloc[random_idx]
+    
+    response = "📝 **Random Dataset Entry:**\n\n"
+    for key, value in sample.items():
+        if value and isinstance(value, str):
+            display_value = value[:500] + "..." if len(value) > 500 else value
+            response += f"**{key}**: {display_value}\n\n"
+    
+    return response
+
+# Create Gradio interface
+with gr.Blocks(title="Indian Law Q&A Assistant") as demo:
+    gr.Markdown("""
+    # 🏛️ Indian Law Q&A Assistant
+    
+    Welcome to the Indian Law Question-Answer Assistant powered by the `viber1/indian-law-dataset`.
+    
+    ### How to use:
+    1. Enter your legal question in the text box below
+    2. Click "Search" to find relevant information from the dataset
+    3. Or click "Random Sample" to explore a random entry from the dataset
+    
+    ---
+    
+    ⚠️ **DISCLAIMER**: This application is for **informational purposes only**. The information provided 
+    is based on a dataset and should NOT be considered as legal advice. Always consult with a qualified 
+    legal professional for specific legal matters and guidance.
+    
+    ---
+    """)
+    
+    with gr.Row():
+        with gr.Column():
+            question_input = gr.Textbox(
+                label="Your Legal Question",
+                placeholder="E.g., What are the provisions related to property rights?",
+                lines=3
+            )
+            
+            with gr.Row():
+                search_btn = gr.Button("🔍 Search", variant="primary")
+                random_btn = gr.Button("🎲 Random Sample")
+            
+    output_box = gr.Markdown(label="Response")
+    
+    # Button actions
+    search_btn.click(fn=search_legal_info, inputs=question_input, outputs=output_box)
+    random_btn.click(fn=get_random_sample, inputs=None, outputs=output_box)
+    
+    gr.Markdown("""
+    ---
+    
+    ### Dataset Information:
+    - **Dataset**: viber1/indian-law-dataset
+    - **Total Entries**: """ + str(len(df)) + """
+    - **Columns**: """ + ", ".join(df.columns.tolist()) + """
+    
+    *Built with 💙 using Gradio and Hugging Face Datasets*
+    """)
+
+if __name__ == "__main__":
+    demo.launch()