Update interface.py

interface.py

@@ -66,115 +66,10 @@ def make_request_with_retry(method: str, endpoint: str, **kwargs) -> requests.Re
     
     raise gr.Error("❌ Maximum retries exceeded. Please try again later.", duration=10)
 
-# ==================== WEB SCRAPING FUNCTIONS ====================
-
-def extract_links(url: str, progress=gr.Progress()) -> List[str]:
-    """Extract links from URL with progress tracking"""
-    if not url:
-        raise gr.Error("❌ Please provide a URL", duration=5)
-    
-    progress(0, desc="Connecting to website...")
-    
-    try:
-        response = make_request_with_retry(
-            "POST",
-            "/extract_links",
-            json={"url": url},
-            timeout=30
-        )
-        progress(1, desc="Links extracted!")
-        return response.json()["unique_links"]
-    except Exception as e:
-        raise gr.Error(f"❌ Failed to extract links: {str(e)}", duration=10)
-
-def extract_text(urls: List[str], progress=gr.Progress()) -> str:
-    """Extract text from URLs with progress tracking"""
-    progress(0, desc="Starting text extraction...")
-    
-    try:
-        response = make_request_with_retry(
-            "POST",
-            "/extract_text",
-            json=urls,
-            timeout=120
-        )
-        progress(1, desc="Text extraction complete!")
-        return response.json()["file_saved"]
-    except Exception as e:
-        raise gr.Error(f"❌ Failed to extract text: {str(e)}", duration=10)
-
-def perform_rag(file_path: str, prompt: str, progress=gr.Progress()) -> dict:
-    """Perform RAG with progress tracking"""
-    progress(0.3, desc="Analyzing content...")
-    
-    try:
-        response = make_request_with_retry(
-            "POST",
-            "/rag",
-            json={"file_path": file_path, "prompt": prompt},
-            timeout=60
-        )
-        progress(1, desc="Analysis complete!")
-        return response.json()
-    except Exception as e:
-        raise gr.Error(f"❌ Failed to perform RAG: {str(e)}", duration=10)
-
-def process_multiple_links(url: str, prompt: str, progress=gr.Progress()) -> Tuple[str, str, dict]:
-    """Process multiple links with comprehensive progress tracking"""
-    if not url or not prompt:
-        raise gr.Error("❌ Please provide both URL and prompt", duration=5)
-    
-    try:
-        progress(0, desc="🔍 Extracting links from webpage...")
-        links = extract_links(url, progress)
-        
-        progress(0.3, desc=f"📄 Found {len(links)} links. Processing top 5...")
-        sample_links = links[:5]
-        file_path = extract_text(sample_links, progress)
-        
-        progress(0.7, desc="🤖 Generating AI response...")
-        result = perform_rag(file_path, prompt, progress)
-        
-        progress(1, desc="✅ Complete!")
-        
-        status_msg = f"✅ Processed {len(sample_links)} pages from {len(links)} total links found"
-        response_text = f"**Query:** {result['user_query']}\n\n**Response:** {result['assistant_response']}"
-        
-        return status_msg, response_text, result['sources']
-        
-    except gr.Error:
-        raise
-    except Exception as e:
-        raise gr.Error(f"❌ Processing error: {str(e)}", duration=10)
-
-def process_homepage_only(url: str, prompt: str, progress=gr.Progress()) -> Tuple[str, str, dict]:
-    """Process homepage only with progress tracking"""
-    if not url or not prompt:
-        raise gr.Error("❌ Please provide both URL and prompt", duration=5)
-    
-    try:
-        progress(0.2, desc="📄 Extracting homepage content...")
-        file_path = extract_text([url], progress)
-        
-        progress(0.6, desc="🤖 Generating AI response...")
-        result = perform_rag(file_path, prompt, progress)
-        
-        progress(1, desc="✅ Complete!")
-        
-        status_msg = "✅ Processed homepage content"
-        response_text = f"**Query:** {result['user_query']}\n\n**Response:** {result['assistant_response']}"
-        
-        return status_msg, response_text, result['sources']
-        
-    except gr.Error:
-        raise
-    except Exception as e:
-        raise gr.Error(f"❌ Processing error: {str(e)}", duration=10)
-
-# ==================== DOCUMENT UPLOAD FUNCTIONS (FIXED) ====================
+# ==================== DOCUMENT UPLOAD FUNCTIONS ====================
 
 def upload_single_document(file, collection_name: str, progress=gr.Progress()) -> Tuple[str, dict]:
-    """Upload single document with progress tracking - FIXED FOR 415 ERROR"""
+    """Upload single document with progress tracking"""
     if not file:
         raise gr.Error("❌ Please select a file to upload", duration=5)
     
@@ -192,7 +87,6 @@ def upload_single_document(file, collection_name: str, progress=gr.Progress()) -
             raise gr.Error(f"❌ File not found: {file_path}", duration=5)
         
         with open(file_path, 'rb') as f:
-            # FIX: Use generic MIME type to avoid 415 error
             files = {
                 'file': (os.path.basename(file_path), f, 'application/octet-stream')
             }
@@ -223,7 +117,7 @@ def upload_single_document(file, collection_name: str, progress=gr.Progress()) -
         raise gr.Error(f"❌ Upload failed: {str(e)}", duration=10)
 
 def upload_multiple_documents(files, collection_name: str, progress=gr.Progress()) -> Tuple[str, dict]:
-    """Upload multiple documents with progress tracking - FIXED FOR 415 ERROR"""
+    """Upload multiple documents with progress tracking"""
     if not files or len(files) == 0:
         raise gr.Error("❌ Please select files to upload", duration=5)
     
@@ -243,7 +137,6 @@ def upload_multiple_documents(files, collection_name: str, progress=gr.Progress(
                 
             with open(file_path, 'rb') as f:
                 file_content = f.read()
-                # FIX: Use generic MIME type for all files
                 files_to_upload.append(
                     ('files', (os.path.basename(file_path), file_content, 'application/octet-stream'))
                 )
@@ -500,63 +393,24 @@ label {
 """
 
 # Build interface
-with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as interface:
+with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Document Assistant") as interface:
     gr.HTML("""
         <div class="main-container">
             <h1 class="animated-title">
-                <span class="floating-icon">🌐</span> Advanced RAG Assistant
+                <span class="floating-icon">📄</span> RAG Document Assistant
             </h1>
             <p class="subtitle" style="color: #b0b0b0; font-size: 1.3rem; text-align: center; margin-bottom: 2rem;">
-                Upload documents (PDF/Markdown) or extract from web pages - Ask questions using AI-powered retrieval
+                Upload documents (PDF/Markdown/TXT) and ask questions using AI-powered retrieval
             </p>
         </div>
     """)
     
     with gr.Tabs() as tabs:
-        # Web Scraping Tabs
-        with gr.Tab("🔗 Multiple Links Analysis"):
-            with gr.Row():
-                with gr.Column():
-                    url_input_multi = gr.Textbox(label="🌍 Website URL", placeholder="https://example.com")
-                    prompt_input_multi = gr.Textbox(label="💭 Your Question", placeholder="What is this website about?", lines=3)
-                    submit_btn_multi = gr.Button("✨ Analyze Multiple Links", variant="primary")
-            
-            with gr.Row():
-                with gr.Column():
-                    status_output_multi = gr.Textbox(label="📊 Status", elem_classes="output-box")
-                    response_output_multi = gr.Markdown(label="🤖 AI Response", elem_classes="output-box")
-                    sources_output_multi = gr.JSON(label="📚 Sources", elem_classes="output-box")
-            
-            submit_btn_multi.click(
-                fn=process_multiple_links,
-                inputs=[url_input_multi, prompt_input_multi],
-                outputs=[status_output_multi, response_output_multi, sources_output_multi]
-            )
-        
-        with gr.Tab("🏠 Homepage Only Analysis"):
-            with gr.Row():
-                with gr.Column():
-                    url_input_home = gr.Textbox(label="🌍 Website URL", placeholder="https://example.com")
-                    prompt_input_home = gr.Textbox(label="💭 Your Question", placeholder="What is this website about?", lines=3)
-                    submit_btn_home = gr.Button("✨ Analyze Homepage", variant="primary")
-            
-            with gr.Row():
-                with gr.Column():
-                    status_output_home = gr.Textbox(label="📊 Status", elem_classes="output-box")
-                    response_output_home = gr.Markdown(label="🤖 AI Response", elem_classes="output-box")
-                    sources_output_home = gr.JSON(label="📚 Sources", elem_classes="output-box")
-            
-            submit_btn_home.click(
-                fn=process_homepage_only,
-                inputs=[url_input_home, prompt_input_home],
-                outputs=[status_output_home, response_output_home, sources_output_home]
-            )
-        
         # Document Upload Tab
         with gr.Tab("📄 Document Upload & Query"):
             gr.Markdown("""
             ### Upload PDF or Markdown documents and query them using RAG
-            - Supports **PDF** and **Markdown** files
+            - Supports **PDF**, **Markdown**, and **TXT** files
             - Documents are chunked and stored in FAISS vector database
             - Organize documents into collections for better management
             """)
@@ -572,7 +426,7 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as
                     
                     with gr.Tab("Single File"):
                         file_upload_single = gr.File(
-                            label="📁 Select Document (PDF/Markdown)",
+                            label="📁 Select Document (PDF/Markdown/TXT)",
                             file_types=[".pdf", ".md", ".txt"]
                         )
                         upload_btn_single = gr.Button("📤 Upload Single Document", variant="primary")
@@ -581,7 +435,7 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as
                     
                     with gr.Tab("Multiple Files"):
                         file_upload_multi = gr.File(
-                            label="📁 Select Documents (PDF/Markdown)",
+                            label="📁 Select Documents (PDF/Markdown/TXT)",
                             file_count="multiple",
                             file_types=[".pdf", ".md", ".txt"]
                         )
@@ -647,6 +501,17 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as
                 fn=refresh_collections,
                 outputs=[collection_dropdown]
             )
+            
+            gr.HTML("""
+                <div class="example-box" style="background: linear-gradient(135deg, rgba(0, 242, 254, 0.1) 0%, rgba(79, 172, 254, 0.1) 100%); border-radius: 16px; padding: 1.5rem; border-left: 4px solid #00f2fe; margin-top: 2rem;">
+                    <h3 style="margin-top: 0; font-size: 1.4rem; color: #e0e0e0;">
+                        <span class="floating-icon">💡</span> Example Usage
+                    </h3>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>1.</strong> Upload your PDF/Markdown documents to a collection</p>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>2.</strong> Ask questions like: "What are the main findings?" or "Summarize the methodology"</p>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>3.</strong> System returns answers with source citations</p>
+                </div>
+            """)
         
         # Collection Management Tab
         with gr.Tab("🗂️ Collection Management"):
@@ -674,6 +539,14 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as
                 inputs=[collection_to_delete],
                 outputs=[delete_status, collections_output, collections_json, collection_to_delete]
             )
+            
+            gr.HTML("""
+                <div class="note-box" style="background: linear-gradient(135deg, rgba(0, 242, 254, 0.08) 0%, rgba(79, 172, 254, 0.08) 100%); border-radius: 12px; padding: 1rem; border-left: 4px solid #00f2fe; margin-top: 1rem;">
+                    <p style="margin: 0; font-size: 1.05rem; color: #00c6ff;">
+                        ⚠️ <strong>Warning:</strong> Deleting a collection is permanent and cannot be undone. All documents in the collection will be removed.
+                    </p>
+                </div>
+            """)
         
         # System Health Tab
         with gr.Tab("⚙️ System Health"):
@@ -687,6 +560,17 @@ with gr.Blocks(css=custom_css, theme=gr.themes.Soft(), title="RAG Assistant") as
                 fn=get_system_health,
                 outputs=[health_output, health_json]
             )
+            
+            gr.HTML("""
+                <div class="example-box" style="background: linear-gradient(135deg, rgba(0, 242, 254, 0.1) 0%, rgba(79, 172, 254, 0.1) 100%); border-radius: 16px; padding: 1.5rem; border-left: 4px solid #00f2fe; margin-top: 2rem;">
+                    <h3 style="margin-top: 0; font-size: 1.4rem; color: #e0e0e0;">
+                        <span class="floating-icon">📊</span> Health Check Information
+                    </h3>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>Supabase:</strong> Cloud storage for documents (optional)</p>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>Groq API:</strong> LLM for generating answers</p>
+                    <p style="font-size: 1.1rem; color: #e0e0e0;"><strong>Vector Stores:</strong> FAISS collections for document embeddings</p>
+                </div>
+            """)
     
     gr.HTML("""
         <div class="note-box" style="margin-top: 2rem; background: linear-gradient(135deg, rgba(0, 242, 254, 0.08) 0%, rgba(79, 172, 254, 0.08) 100%); border-radius: 12px; padding: 1rem; border-left: 4px solid #00f2fe;">