Remove RAG functionality and enhance template system

- Add enhanced template system with Research and Socratic templates
- Remove all RAG/vector search functionality and dependencies
- Clean up requirements.txt to remove RAG-related packages
- Update documentation to remove RAG references
- Maintain core functionality: URL grounding, dynamic URL fetching, template system
- Fix preview functionality and export features
- Update support documentation

README.md

@@ -14,14 +14,14 @@ short_description: Configure, download, and deploy a simple chat interface
 
 # Chat UI Helper
 
-A Gradio-based tool for generating and configuring chat interfaces for HuggingFace Spaces. Create deployable packages with custom assistants, web scraping capabilities, and optional vector RAG functionality.
+A Gradio-based tool for generating and configuring chat interfaces for HuggingFace Spaces. Create deployable packages with custom assistants and web scraping capabilities.
 
 ## Features
 
 ### Spaces Configuration
 - **Custom Assistant Creation**: Define role, purpose, audience, and tasks
-- **Template System**: Choose from research assistant template or build from scratch
-- **Tool Integration**: Optional dynamic URL fetching and document RAG
+- **Template System**: Choose from research assistant template or build from scratch  
+- **Tool Integration**: Optional dynamic URL fetching
 - **Access Control**: Secure access code protection for educational use
 - **Complete Deployment Package**: Generates app.py, requirements.txt, README.md, and config.json
 
@@ -48,14 +48,12 @@ Set your OpenRouter API key as a secret:
 Each generated space includes:
 - **OpenRouter API Integration**: Support for multiple LLM models
 - **Web Scraping**: Simple HTTP requests with BeautifulSoup for URL content fetching
-- **Document RAG**: Optional upload and search through PDF, DOCX, TXT, MD files
 - **Access Control**: Environment-based student access codes
 - **Modern UI**: Gradio 5.x ChatInterface with proper message formatting
 
 ## Architecture
 
-- **Main Application**: `app.py` with two-tab interface
-- **Document Processing**: RAG pipeline with FAISS vector search
+- **Main Application**: `app.py` with three-tab interface
 - **Web Scraping**: HTTP requests with BeautifulSoup for content extraction
 - **Template Generation**: Complete HuggingFace Space creation
 

app.py

@@ -39,13 +39,7 @@ def get_grounding_context_simple(urls):
         return "\n\n" + "\n\n".join(context_parts) + "\n\n"
     return ""
 
-# Import RAG components
-try:
-    from rag_tool import RAGTool
-    HAS_RAG = True
-except ImportError:
-    HAS_RAG = False
-    RAGTool = None
+# RAG functionality removed
 
 # Load environment variables from .env file
 load_dotenv()
@@ -152,8 +146,7 @@ GROUNDING_URLS = {grounding_urls}
 # Get access code from environment variable for security
 ACCESS_CODE = os.environ.get("SPACE_ACCESS_CODE", "{access_code}")
 ENABLE_DYNAMIC_URLS = {enable_dynamic_urls}
-ENABLE_VECTOR_RAG = {enable_vector_rag}
-RAG_DATA = {rag_data_json}
+# RAG functionality removed
 
 # Get API key from environment - customizable variable name with validation
 API_KEY = os.environ.get("{api_key_var}")
@@ -309,10 +302,31 @@ def export_conversation_to_markdown(conversation_history):
     markdown_content = f"""# Conversation Export
 Generated on: {{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}}
 
----
+## Configuration Information
 
+**Assistant Name:** {name}
+**Description:** {description}
+**Model:** {{MODEL}}
+**Temperature:** {temperature}
+**Max Tokens:** {max_tokens}
+**API Key Variable:** {api_key_var}
 """
     
+    # Add URL grounding information
+    if GROUNDING_URLS:
+        markdown_content += f"\\n**URL Grounding ({{len(GROUNDING_URLS)}} URLs):**\\n"
+        for i, url in enumerate(GROUNDING_URLS, 1):
+            markdown_content += f"- URL {{i}}: {{url}}\\n"
+    
+    # Add feature flags
+    if ENABLE_DYNAMIC_URLS:
+        markdown_content += f"\\n**Dynamic URL Fetching:** Enabled\\n"
+    
+    # Add system prompt
+    markdown_content += f"\\n**System Prompt:**\\n```\\n{{SYSTEM_PROMPT}}\\n```\\n"
+    
+    markdown_content += "\\n---\\n\\n"
+    
     message_pair_count = 0
     for i, message in enumerate(conversation_history):
         if isinstance(message, dict):
@@ -335,35 +349,7 @@ Generated on: {{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}}
     
     return markdown_content
 
-# Initialize RAG context if enabled
-if ENABLE_VECTOR_RAG and RAG_DATA:
-    try:
-        import faiss
-        import numpy as np
-        import base64
-        
-        class SimpleRAGContext:
-            def __init__(self, rag_data):
-                # Deserialize FAISS index
-                index_bytes = base64.b64decode(rag_data['index_base64'])
-                self.index = faiss.deserialize_index(index_bytes)
-                
-                # Restore chunks and mappings
-                self.chunks = rag_data['chunks']
-                self.chunk_ids = rag_data['chunk_ids']
-            
-            def get_context(self, query, max_chunks=3):
-                """Get relevant context - simplified version"""
-                # In production, you'd compute query embedding here
-                # For now, return a simple message
-                return "\\n\\n[RAG context would be retrieved here based on similarity search]\\n\\n"
-        
-        rag_context_provider = SimpleRAGContext(RAG_DATA)
-    except Exception as e:
-        print(f"Failed to initialize RAG: {{e}}")
-        rag_context_provider = None
-else:
-    rag_context_provider = None
+# RAG functionality removed
 
 def generate_response(message, history):
     """Generate response using OpenRouter API"""
@@ -383,11 +369,7 @@ def generate_response(message, history):
     # Get grounding context
     grounding_context = get_grounding_context()
     
-    # Add RAG context if available
-    if ENABLE_VECTOR_RAG and rag_context_provider:
-        rag_context = rag_context_provider.get_context(message)
-        if rag_context:
-            grounding_context += rag_context
+    # RAG functionality removed
     
     # If dynamic URLs are enabled, check message for URLs to fetch
     if ENABLE_DYNAMIC_URLS:
@@ -643,9 +625,6 @@ def get_configuration_status():
     
     if ENABLE_DYNAMIC_URLS:
         status_parts.append("🔄 **Dynamic URLs:** Enabled")
-        
-    if ENABLE_VECTOR_RAG:
-        status_parts.append("📚 **Document RAG:** Enabled")
     
     if ACCESS_CODE:
         status_parts.append("🔐 **Access Control:** Enabled")
@@ -861,18 +840,11 @@ Generated on {datetime.now().strftime('%Y-%m-%d %H:%M:%S')} with Chat U/I Helper
     
     return readme_content
 
-def create_requirements(enable_vector_rag=False):
+def create_requirements():
     """Generate requirements.txt"""
-    base_requirements = "gradio>=4.44.1\nrequests>=2.32.3\nbeautifulsoup4>=4.12.3\npython-dotenv>=1.0.0"
-
-    
-    if enable_vector_rag:
-        base_requirements += "\n\n# Vector RAG dependencies"
-        base_requirements += "\nfaiss-cpu>=1.11.0\nnumpy>=1.25.0,<3.0\nsentence-transformers>=2.2.2\nPyMuPDF>=1.23.0\npython-docx>=0.8.11"
-    
-    return base_requirements
+    return "gradio>=4.44.1\nrequests>=2.32.3\nbeautifulsoup4>=4.12.3\npython-dotenv>=1.0.0"
 
-def generate_zip(name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code="", enable_dynamic_urls=False, url1="", url2="", url3="", url4="", enable_vector_rag=False, rag_data=None):
+def generate_zip(name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code="", enable_dynamic_urls=False, url1="", url2="", url3="", url4=""):
     """Generate deployable zip file"""
     
     # Process examples
@@ -906,9 +878,7 @@ def generate_zip(name, description, system_prompt, model, api_key_var, temperatu
         'examples': examples_json,
         'grounding_urls': json.dumps(grounding_urls),
         'access_code': "",  # Access code stored in environment variable for security
-        'enable_dynamic_urls': enable_dynamic_urls,
-        'enable_vector_rag': enable_vector_rag,
-        'rag_data_json': json.dumps(rag_data) if rag_data else 'None'
+        'enable_dynamic_urls': enable_dynamic_urls
     }
     
     # Generate files
@@ -917,7 +887,7 @@ def generate_zip(name, description, system_prompt, model, api_key_var, temperatu
     readme_config = config.copy()
     readme_config['access_code'] = access_code or ""
     readme_content = create_readme(readme_config)
-    requirements_content = create_requirements(enable_vector_rag)
+    requirements_content = create_requirements()
     
     # Create zip file with clean naming
     filename = f"{name.lower().replace(' ', '_').replace('-', '_')}.zip"
@@ -938,93 +908,7 @@ def generate_zip(name, description, system_prompt, model, api_key_var, temperatu
     return filename
 
 # Define callback functions outside the interface
-def toggle_rag_section(enable_rag):
-    """Toggle visibility of RAG section"""
-    return gr.update(visible=enable_rag)
-
-def process_documents(files, current_rag_tool):
-    """Process uploaded documents"""
-    if not files:
-        return "Please upload files first", current_rag_tool
-    
-    if not HAS_RAG:
-        return "RAG functionality not available. Please install required dependencies.", current_rag_tool
-    
-    try:
-        # Check file paths are valid
-        file_paths = []
-        for file in files:
-            if hasattr(file, 'name'):
-                file_paths.append(file.name)
-            else:
-                file_paths.append(str(file))
-        
-        print(f"Processing {len(file_paths)} files for RAG...")
-        
-        # Initialize RAG tool if not exists
-        if not current_rag_tool and RAGTool is not None:
-            print("Initializing RAG tool...")
-            current_rag_tool = RAGTool()
-        
-        # Process files with progress feedback
-        print("Processing documents and creating embeddings...")
-        result = current_rag_tool.process_uploaded_files(file_paths)
-        
-        if result['success']:
-            # Create status message
-            status_parts = [f"✅ {result['message']}"]
-            
-            # Add file summary
-            if result['summary']['files_processed']:
-                status_parts.append("\n**Processed files:**")
-                for file_info in result['summary']['files_processed']:
-                    status_parts.append(f"- {file_info['name']} ({file_info['chunks']} chunks)")
-            
-            # Add errors if any
-            if result.get('errors'):
-                status_parts.append("\n**Errors:**")
-                for error in result['errors']:
-                    status_parts.append(f"- {error['file']}: {error['error']}")
-            
-            # Add index stats
-            if result.get('index_stats'):
-                stats = result['index_stats']
-                status_parts.append(f"\n**Index stats:** {stats['total_chunks']} chunks, {stats['dimension']}D embeddings")
-            
-            return "\n".join(status_parts), current_rag_tool
-        else:
-            return f"❌ {result['message']}", current_rag_tool
-            
-    except ImportError as e:
-        error_msg = f"❌ Missing dependencies: {str(e)}\n\n"
-        error_msg += "To use RAG functionality, install:\n"
-        error_msg += "- sentence-transformers>=2.2.2\n"
-        error_msg += "- faiss-cpu==1.7.4\n"
-        error_msg += "- PyMuPDF>=1.23.0 (for PDF files)\n"
-        error_msg += "- python-docx>=0.8.11 (for DOCX files)"
-        return error_msg, current_rag_tool
-    except RuntimeError as e:
-        error_msg = f"❌ Model initialization error: {str(e)}\n\n"
-        if "network" in str(e).lower() or "download" in str(e).lower():
-            error_msg += "This appears to be a network issue. Please:\n"
-            error_msg += "1. Check your internet connection\n"
-            error_msg += "2. Try again in a few moments\n"
-            error_msg += "3. If the problem persists, restart the application"
-        elif "memory" in str(e).lower():
-            error_msg += "This appears to be a memory issue. Please:\n"
-            error_msg += "1. Try uploading smaller documents\n"
-            error_msg += "2. Process documents one at a time\n"
-            error_msg += "3. Restart the application if needed"
-        return error_msg, current_rag_tool
-    except Exception as e:
-        error_msg = f"❌ Unexpected error processing documents: {str(e)}\n\n"
-        error_msg += "This may be due to:\n"
-        error_msg += "- Large files causing memory issues\n"
-        error_msg += "- Network problems downloading the embedding model\n"
-        error_msg += "- File format issues\n\n"
-        error_msg += "Try: uploading smaller files, checking your internet connection, or restarting the application."
-        print(f"RAG processing error: {e}")
-        return error_msg, current_rag_tool
+# RAG functionality removed
 
 def update_sandbox_preview(config_data):
     """Update the sandbox preview with generated content"""
@@ -1038,7 +922,7 @@ def update_sandbox_preview(config_data):
 - **Temperature:** {config_data.get('temperature', 'N/A')}
 - **Max Tokens:** {config_data.get('max_tokens', 'N/A')}
 - **Dynamic URLs:** {'✅ Enabled' if config_data.get('enable_dynamic_urls') else '❌ Disabled'}
-- **Vector RAG:** {'✅ Enabled' if config_data.get('enable_vector_rag') else '❌ Disabled'}
+# RAG functionality removed
 
 **System Prompt Preview:**
 ```
@@ -1073,14 +957,21 @@ def update_sandbox_preview(config_data):
     
     return preview_text, preview_html
 
-def on_preview_combined(name, description, system_prompt, model, temperature, max_tokens, examples_text, enable_dynamic_urls, enable_vector_rag, rag_tool_state, url1="", url2="", url3="", url4=""):
+def on_preview_combined(name, description, system_prompt, model, temperature, max_tokens, examples_text, enable_dynamic_urls, url1="", url2="", url3="", url4=""):
     """Generate configuration and return preview updates"""
     if not name or not name.strip():
         return (
             {},
             gr.update(value="**Error:** Please provide a Space Title to preview", visible=True),
             gr.update(visible=False),
-            gr.update(value="Configuration will appear here after preview generation.")
+            gr.update(value="Configuration will appear here after preview generation."),
+            gr.update(),  # preview_url1
+            gr.update(),  # preview_url2
+            gr.update(),  # preview_url3
+            gr.update(),  # preview_url4
+            gr.update(),  # preview_add_url_btn
+            gr.update(),  # preview_remove_url_btn
+            2            # preview_url_count
         )
     
     try:
@@ -1090,7 +981,14 @@ def on_preview_combined(name, description, system_prompt, model, temperature, ma
                 {},
                 gr.update(value="**Error:** Please provide a System Prompt for the assistant", visible=True),
                 gr.update(visible=False),
-                gr.update(value="Configuration will appear here after preview generation.")
+                gr.update(value="Configuration will appear here after preview generation."),
+                gr.update(),  # preview_url1
+                gr.update(),  # preview_url2
+                gr.update(),  # preview_url3
+                gr.update(),  # preview_url4
+                gr.update(),  # preview_add_url_btn
+                gr.update(),  # preview_remove_url_btn
+                2            # preview_url_count
             )
         
         final_system_prompt = system_prompt.strip()
@@ -1108,8 +1006,6 @@ def on_preview_combined(name, description, system_prompt, model, temperature, ma
             'url2': url2,
             'url3': url3,
             'url4': url4,
-            'enable_vector_rag': enable_vector_rag,
-            'rag_tool_state': rag_tool_state,
             'examples_text': examples_text,
             'preview_ready': True
         }
@@ -1119,9 +1015,7 @@ def on_preview_combined(name, description, system_prompt, model, temperature, ma
 > *{final_system_prompt[:600]}{'...' if len(final_system_prompt) > 600 else '...'}*
 
 Tip: Try different configurations of your space before generating the deployment package."""
-        config_display = f"""### Current Configuration
-
-> **Configuration**:
+        config_display = f"""> **Configuration**:
 - **Name:** {name}
 - **Description:** {description or 'No description provided'}
 - **Model:** {model}
@@ -1140,11 +1034,42 @@ Tip: Try different configurations of your space before generating the deployment
         # Show success notification
         gr.Info(f"✅ Preview generated successfully for '{name}'! Switch to Preview tab.")
 
+        # Determine how many URLs are configured
+        url_count = 2  # Start with 2 (always visible)
+        if url3 and url3.strip():
+            url_count = 3
+        if url4 and url4.strip():
+            url_count = 4
+        
+        # Update preview URL visibility and button states based on count
+        if url_count == 2:
+            preview_url3_update = gr.update(value=url3, visible=False)
+            preview_url4_update = gr.update(value=url4, visible=False)
+            preview_add_btn_update = gr.update(value="+ Add URLs", interactive=True)
+            preview_remove_btn_update = gr.update(visible=False)
+        elif url_count == 3:
+            preview_url3_update = gr.update(value=url3, visible=True)
+            preview_url4_update = gr.update(value=url4, visible=False)
+            preview_add_btn_update = gr.update(value="+ Add URLs", interactive=True)
+            preview_remove_btn_update = gr.update(visible=True)
+        else:  # url_count == 4
+            preview_url3_update = gr.update(value=url3, visible=True)
+            preview_url4_update = gr.update(value=url4, visible=True)
+            preview_add_btn_update = gr.update(value="Max URLs", interactive=False)
+            preview_remove_btn_update = gr.update(visible=True)
+        
         return (
             config_data,
             gr.update(value=preview_text, visible=True),
             gr.update(visible=True),
-            gr.update(value=config_display)
+            gr.update(value=config_display),
+            gr.update(value=url1),  # preview_url1
+            gr.update(value=url2),  # preview_url2
+            preview_url3_update,    # preview_url3
+            preview_url4_update,    # preview_url4
+            preview_add_btn_update, # preview_add_url_btn
+            preview_remove_btn_update, # preview_remove_url_btn
+            url_count              # preview_url_count
         )
         
     except Exception as e:
@@ -1152,7 +1077,14 @@ Tip: Try different configurations of your space before generating the deployment
             {},
             gr.update(value=f"**Error:** {str(e)}", visible=True),
             gr.update(visible=False),
-            gr.update(value="Configuration will appear here after preview generation.")
+            gr.update(value="Configuration will appear here after preview generation."),
+            gr.update(),  # preview_url1
+            gr.update(),  # preview_url2
+            gr.update(),  # preview_url3
+            gr.update(),  # preview_url4
+            gr.update(),  # preview_add_url_btn
+            gr.update(),  # preview_remove_url_btn
+            2            # preview_url_count
         )
 
 def update_preview_display(config_data):
@@ -1173,7 +1105,7 @@ Your assistant "{config_data['name']}" is configured and ready to test.
 - **Temperature:** {config_data['temperature']}
 - **Max Tokens:** {config_data['max_tokens']}
 - **Dynamic URLs:** {'✅ Enabled' if config_data['enable_dynamic_urls'] else '❌ Disabled'}
-- **Vector RAG:** {'✅ Enabled' if config_data['enable_vector_rag'] else '❌ Disabled'}
+# RAG functionality removed
 
 **System Prompt:** 
 {config_data['system_prompt'][:600]}{'...' if len(config_data['system_prompt']) > 600 else ''}
@@ -1193,7 +1125,7 @@ Use the chat interface below to test your assistant before generating the deploy
 
 **Features:**
 - **Dynamic URL Fetching:** {'✅ Enabled' if config_data['enable_dynamic_urls'] else '❌ Disabled'}
-- **Document RAG:** {'✅ Enabled' if config_data['enable_vector_rag'] else '❌ Disabled'}
+# RAG functionality removed
 
 **System Prompt:**
 ```
@@ -1253,20 +1185,7 @@ Once you set your API key, you'll be able to test real conversations in this pre
         grounding_urls = config_urls if any(url for url in config_urls if url) else [url1, url2, url3, url4]
         grounding_context = get_cached_grounding_context([url for url in grounding_urls if url and url.strip()])
         
-        # Add RAG context if available (actual retrieval for preview)
-        rag_context = ""
-        if config_data.get('enable_vector_rag') and HAS_RAG:
-            try:
-                # Get RAG tool from config_data if available
-                rag_tool_state = config_data.get('rag_tool_state')
-                if rag_tool_state:
-                    rag_context = rag_tool_state.get_relevant_context(message, max_chunks=2)
-                    if rag_context:
-                        rag_context = f"\n\n**RAG Context (Preview):**\n{rag_context}\n\n"
-                else:
-                    rag_context = "\n\n[RAG: No processed documents available for context]\n\n"
-            except Exception as e:
-                rag_context = f"\n\n[RAG context error: {str(e)}]\n\n"
+        # RAG functionality removed
         
         # If dynamic URLs are enabled, check message for URLs to fetch
         dynamic_context = ""
@@ -1281,7 +1200,7 @@ Once you set your API key, you'll be able to test real conversations in this pre
                     dynamic_context = "\n".join(dynamic_context_parts)
         
         # Build enhanced system prompt with all contexts
-        enhanced_system_prompt = config_data.get('system_prompt', '') + grounding_context + rag_context + dynamic_context
+        enhanced_system_prompt = config_data.get('system_prompt', '') + grounding_context + dynamic_context
         
         # Build messages array for the API
         messages = [{"role": "system", "content": enhanced_system_prompt}]
@@ -1360,12 +1279,12 @@ def clear_preview_chat():
     """Clear preview chat"""
     return "", []
 
-def export_preview_conversation(history):
+def export_preview_conversation(history, config_data=None):
     """Export preview conversation to markdown"""
     if not history:
         return gr.update(visible=False)
     
-    markdown_content = export_conversation_to_markdown(history)
+    markdown_content = export_conversation_to_markdown(history, config_data)
     
     # Save to temporary file
     import tempfile
@@ -1375,24 +1294,19 @@ def export_preview_conversation(history):
     
     return gr.update(value=temp_file, visible=True)
 
-def on_generate(name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4, enable_vector_rag, rag_tool_state):
+def on_generate(name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4):
     if not name or not name.strip():
         return gr.update(value="Error: Please provide a Space Title", visible=True), gr.update(visible=False), {}
     
     
     try:
-        # Get RAG data if enabled
-        rag_data = None
-        if enable_vector_rag and rag_tool_state:
-            rag_data = rag_tool_state.get_serialized_data()
-        
         # Use the system prompt directly (template selector already updates it)
         if not system_prompt or not system_prompt.strip():
             return gr.update(value="Error: Please provide a System Prompt for the assistant", visible=True), gr.update(visible=False), {}
         
         final_system_prompt = system_prompt.strip()
         
-        filename = generate_zip(name, description, final_system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4, enable_vector_rag, rag_data)
+        filename = generate_zip(name, description, final_system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4)
         
         success_msg = f"""**Deployment package ready!**
 
@@ -1420,7 +1334,6 @@ def on_generate(name, description, system_prompt, model, api_key_var, temperatur
             'temperature': temperature,
             'max_tokens': max_tokens,
             'enable_dynamic_urls': enable_dynamic_urls,
-            'enable_vector_rag': enable_vector_rag,
             'filename': filename
         }
         
@@ -1834,63 +1747,8 @@ with gr.Blocks(
                     
             
                     
-                    # Document RAG section
-                    enable_vector_rag = gr.Checkbox(
-                        label="Enable Document RAG",
-                        value=False,
-                        info="Upload documents for context-aware responses (PDF, DOCX, TXT, MD)",
-                        visible=HAS_RAG
-                    )
+                    # RAG functionality removed
                     
-                    with gr.Column(visible=False) as rag_section:
-                        gr.Markdown("### Document Upload")
-                        file_upload = gr.File(
-                            label="Upload Documents",
-                            file_types=[".pdf", ".docx", ".txt", ".md"],
-                            file_count="multiple"
-                        )
-                        process_btn = gr.Button("Process Documents", variant="secondary")
-                        rag_status = gr.Markdown()
-                        
-                        # State to store RAG tool
-                        rag_tool_state = gr.State(None)
-                    
-                    with gr.Accordion("URL Grounding (Optional)", open=True):
-                        gr.Markdown("Add URLs to provide context. Content will be fetched and added to the system prompt.")
-                        
-                        # Initial URL fields
-                        url1 = gr.Textbox(
-                            label="URL 1",
-                            placeholder="https://example.com/page1",
-                            info="First URL for context grounding"
-                        )
-                        
-                        url2 = gr.Textbox(
-                            label="URL 2", 
-                            placeholder="https://example.com/page2",
-                            info="Second URL for context grounding"
-                        )
-                        
-                        # Additional URL fields (initially hidden)
-                        url3 = gr.Textbox(
-                            label="URL 3",
-                            placeholder="https://example.com/page3", 
-                            info="Third URL for context grounding",
-                            visible=False
-                        )
-                        
-                        url4 = gr.Textbox(
-                            label="URL 4",
-                            placeholder="https://example.com/page4",
-                            info="Fourth URL for context grounding",
-                            visible=False
-                        )
-                        
-                        # URL management buttons
-                        with gr.Row():
-                            add_url_btn = gr.Button("+ Add URLs", size="sm")
-                            remove_url_btn = gr.Button("- Remove URLs", size="sm", visible=False)
-                        url_count = gr.State(2)  # Track number of visible URLs
                     
                     examples_text = gr.Textbox(
                         label="Example Prompts (one per line)",
@@ -1925,6 +1783,44 @@ with gr.Blocks(
                             value=1500,
                             step=50
                         )
+                    
+                    # URL Grounding section
+                    gr.Markdown("**URL Grounding (Optional)**")
+                    gr.Markdown("Add URLs to provide context. Content will be fetched and added to the system prompt.")
+                    
+                    # Initial URL fields
+                    url1 = gr.Textbox(
+                        label="URL 1",
+                        placeholder="https://example.com/page1",
+                        info="First URL for context grounding"
+                    )
+                    
+                    url2 = gr.Textbox(
+                        label="URL 2", 
+                        placeholder="https://example.com/page2",
+                        info="Second URL for context grounding"
+                    )
+                    
+                    # Additional URL fields (initially hidden)
+                    url3 = gr.Textbox(
+                        label="URL 3",
+                        placeholder="https://example.com/page3", 
+                        info="Third URL for context grounding",
+                        visible=False
+                    )
+                    
+                    url4 = gr.Textbox(
+                        label="URL 4",
+                        placeholder="https://example.com/page4",
+                        info="Fourth URL for context grounding",
+                        visible=False
+                    )
+                    
+                    # URL management buttons
+                    with gr.Row():
+                        add_url_btn = gr.Button("+ Add URLs", size="sm")
+                        remove_url_btn = gr.Button("- Remove URLs", size="sm", visible=False)
+                    url_count = gr.State(2)  # Track number of visible URLs
                 
                 with gr.Row():
                     preview_btn = gr.Button("Preview Deployment Package", variant="secondary")
@@ -1960,24 +1856,13 @@ with gr.Blocks(
                 outputs=[url3, url4, add_url_btn, remove_url_btn, url_count]
             )
             
-            # Connect RAG functionality
-            enable_vector_rag.change(
-                toggle_rag_section,
-                inputs=[enable_vector_rag],
-                outputs=[rag_section]
-            )
-            
-            process_btn.click(
-                process_documents,
-                inputs=[file_upload, rag_tool_state],
-                outputs=[rag_status, rag_tool_state]
-            )
+            # RAG functionality removed
             
             
             # Connect the generate button
             generate_btn.click(
                 on_generate,
-                inputs=[name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4, enable_vector_rag, rag_tool_state],
+                inputs=[name, description, system_prompt, model, api_key_var, temperature, max_tokens, examples_text, access_code, enable_dynamic_urls, url1, url2, url3, url4],
                 outputs=[status, download_file, sandbox_state]
             )
             
@@ -2073,7 +1958,7 @@ with gr.Blocks(
             
             preview_export_btn.click(
                 export_preview_conversation,
-                inputs=[preview_chatbot],
+                inputs=[preview_chatbot, preview_config_state],
                 outputs=[export_file]
             )
             
@@ -2096,8 +1981,8 @@ with gr.Blocks(
     # Connect cross-tab functionality after all components are defined
     preview_btn.click(
         on_preview_combined,
-        inputs=[name, description, system_prompt, model, temperature, max_tokens, examples_text, enable_dynamic_urls, enable_vector_rag, rag_tool_state, url1, url2, url3, url4],
-        outputs=[preview_config_state, preview_status_comp, preview_chat_section_comp, config_display_comp]
+        inputs=[name, description, system_prompt, model, temperature, max_tokens, examples_text, enable_dynamic_urls, url1, url2, url3, url4],
+        outputs=[preview_config_state, preview_status_comp, preview_chat_section_comp, config_display_comp, preview_url1, preview_url2, preview_url3, preview_url4, preview_add_url_btn, preview_remove_url_btn, preview_url_count]
     )
 
 if __name__ == "__main__":

requirements.txt

@@ -1,11 +1,4 @@
 gradio>=4.44.1
 requests>=2.32.3
 beautifulsoup4>=4.12.3
-python-dotenv>=1.0.0
-
-# Vector RAG dependencies (optional)
-sentence-transformers>=2.2.2
-faiss-cpu>=1.11.0
-PyMuPDF>=1.23.0
-python-docx>=0.8.11
-numpy>=1.25.0,<3.0
+python-dotenv>=1.0.0

support_docs.py

@@ -25,7 +25,7 @@ def create_support_docs():
             **Workflow Steps:**
             1. **Configure your Space** in the Configuration tab (space title, description, model selection)
             2. **Set up Assistant** with system prompt and optional research template
-            3. **Enable Tools** like web search, document RAG, or URL grounding as needed
+            3. **Enable Tools** like dynamic URL fetching or URL grounding as needed
             4. **Preview & Test** using the Preview tab to validate your configuration
             5. **Generate Package** with the "Generate Deployment Package" button
             6. **Deploy to HuggingFace** following the included README instructions
@@ -213,7 +213,7 @@ def create_support_docs():
             - **System Prompt**: Main field defining assistant behavior and knowledge
             - **Research Template**: Pre-configured academic research assistant checkbox
             - **Web Search Integration**: Enable crawl4ai web search capabilities
-            - **Document RAG**: Upload documents for knowledge base (PDF/DOCX/TXT/MD support)
+            # Document RAG functionality removed
             - **URL Grounding**: Add up to 4 static URLs for context (dynamic add/remove)
             - **Example Prompts**: Clickable suggestions for users (one per line)
             - **Dynamic URL Fetching**: Hidden field (always enabled) for runtime URL processing
@@ -233,11 +233,7 @@ def create_support_docs():
             - Advanced content extraction and crawling
             - Automatically enabled with Research Template
             
-            **Document RAG (Vector Search)**
-            - Upload files: PDF, DOCX, TXT, MD (10MB max each)
-            - Semantic chunking and FAISS vector search
-            - Embedded in deployment package for offline use
-            - Requires `sentence-transformers` and `faiss-cpu`
+            # Document RAG functionality removed
             
             **URL Grounding (Static Context)**
             - Add 2-4 URLs for consistent context across all responses
@@ -270,7 +266,7 @@ def create_support_docs():
             
             **Token Usage Notes:**
             - Tokens include both input (your prompt + context) and output
-            - Longer contexts (documents, URLs) use more input tokens
+            - Longer contexts (URLs) use more input tokens
             - Consider costs when setting high token limits
             """)
         
@@ -359,10 +355,7 @@ def create_support_docs():
             - Check for typos in the access code
             - Case-sensitive matching
             
-            **Documents not loading (RAG)**
-            - Check file formats are supported (PDF, DOCX, TXT, MD)
-            - Verify file sizes are under 10MB
-            - Ensure RAG dependencies are installed
+            # Document RAG functionality removed
             
             **URLs not fetching content**
             - Check URLs are publicly accessible
@@ -378,7 +371,7 @@ def create_support_docs():
             - Use appropriate model for your use case
             - Set reasonable token limits
             - Cache static content with URL grounding
-            - Limit document uploads to essential materials
+            # Document RAG functionality removed
             
             **User Experience**
             - Write clear, helpful example prompts