Fix RAG preview integration and clean dependencies

- Fix RAG context integration in preview tab (was showing placeholder)
- Remove unused web search dependencies from requirements.txt
- Update preview functionality to actually retrieve RAG context

app.py

@@ -1073,7 +1073,7 @@ def update_sandbox_preview(config_data):
     
     return preview_text, preview_html
 
-def on_preview_combined(name, description, system_prompt, enable_research_assistant, model, temperature, max_tokens, examples_text, enable_dynamic_urls, enable_vector_rag):
+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=""):
     """Generate configuration and return preview updates"""
     if not name or not name.strip():
         return (
@@ -1084,7 +1084,7 @@ def on_preview_combined(name, description, system_prompt, enable_research_assist
         )
     
     try:
-        # Use the system prompt directly (research assistant toggle already updates it)
+        # Use the system prompt directly (template selector already updates it)
         if not system_prompt or not system_prompt.strip():
             return (
                 {},
@@ -1104,7 +1104,12 @@ def on_preview_combined(name, description, system_prompt, enable_research_assist
             'temperature': temperature,
             'max_tokens': max_tokens,
             'enable_dynamic_urls': enable_dynamic_urls,
+            'url1': url1,
+            '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
         }
@@ -1237,14 +1242,31 @@ Once you set your API key, you'll be able to test real conversations in this pre
         return "", history
     
     try:
-        # Get grounding context from URLs if configured
-        grounding_urls = [url1, url2, url3, url4]
+        # Get grounding context from URLs - prioritize config_data URLs, fallback to preview tab URLs
+        config_urls = [
+            config_data.get('url1', ''),
+            config_data.get('url2', ''),
+            config_data.get('url3', ''),
+            config_data.get('url4', '')
+        ]
+        # Use config URLs if available, otherwise use preview tab URLs
+        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 (simplified for preview)
+        # Add RAG context if available (actual retrieval for preview)
         rag_context = ""
-        if config_data.get('enable_vector_rag'):
-            rag_context = "\n\n[RAG context would be retrieved here based on similarity search]\n\n"
+        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"
         
         # If dynamic URLs are enabled, check message for URLs to fetch
         dynamic_context = ""
@@ -1353,7 +1375,7 @@ def export_preview_conversation(history):
     
     return gr.update(value=temp_file, visible=True)
 
-def on_generate(name, description, system_prompt, enable_research_assistant, 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, enable_vector_rag, rag_tool_state):
     if not name or not name.strip():
         return gr.update(value="Error: Please provide a Space Title", visible=True), gr.update(visible=False), {}
     
@@ -1364,7 +1386,7 @@ def on_generate(name, description, system_prompt, enable_research_assistant, mod
         if enable_vector_rag and rag_tool_state:
             rag_data = rag_tool_state.get_serialized_data()
         
-        # Use the system prompt directly (research assistant toggle already updates it)
+        # 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), {}
         
@@ -1610,17 +1632,23 @@ def perform_web_search(query, description="Web search"):
 
 # Code execution functionality removed - no longer supported
 
-def toggle_research_assistant(enable_research):
-    """Toggle research assistant system prompt and dynamic URL fetching"""
-    if enable_research:
-        combined_prompt = "You are a research aid specializing in academic literature search and analysis. Your expertise spans discovering peer-reviewed sources, assessing research methodologies, synthesizing findings across studies, and delivering properly formatted citations. When responding, anchor claims in specific sources from provided URL contexts, differentiate between direct evidence and interpretive analysis, and note any limitations or contradictory results. Employ clear, accessible language that demystifies complex research, and propose connected research directions when appropriate. Your purpose is to serve as an informed research tool supporting users through initial concept development, exploratory investigation, information collection, and source compilation."
+def toggle_template(template_choice):
+    """Toggle between different assistant templates"""
+    if template_choice == "Research Template":
+        research_prompt = "You are a research aid specializing in academic literature search and analysis. Your expertise spans discovering peer-reviewed sources, assessing research methodologies, synthesizing findings across studies, and delivering properly formatted citations. When responding, anchor claims in specific sources from provided URL contexts, differentiate between direct evidence and interpretive analysis, and note any limitations or contradictory results. Employ clear, accessible language that demystifies complex research, and propose connected research directions when appropriate. Your purpose is to serve as an informed research tool supporting users through initial concept development, exploratory investigation, information collection, and source compilation."
         return (
-            gr.update(value=combined_prompt),  # Update main system prompt
+            gr.update(value=research_prompt),  # Update main system prompt
             gr.update(value=True)  # Enable dynamic URL fetching for research template
         )
-    else:
+    elif template_choice == "Socratic Template":
+        socratic_prompt = "You are a pedagogically-minded academic assistant designed for introductory courses. Your approach follows constructivist learning principles: build on students' prior knowledge, scaffold complex concepts through graduated questioning, and use Socratic dialogue to guide discovery. Provide concise, evidence-based explanations that connect theory to lived experiences. Each response should model critical thinking by acknowledging multiple perspectives, identifying assumptions, and revealing conceptual relationships. Conclude with open-ended questions that promote higher-order thinking—analysis, synthesis, or evaluation—rather than recall."
+        return (
+            gr.update(value=socratic_prompt),  # Update main system prompt
+            gr.update(value=False)  # Socratic template doesn't need dynamic URLs by default
+        )
+    else:  # "None" or any other value
         return (
-            gr.update(value=""),  # Clear main system prompt when disabling
+            gr.update(value=""),  # Clear main system prompt
             gr.update(value=False)  # Disable dynamic URL setting
         )
 
@@ -1795,12 +1823,14 @@ with gr.Blocks(
                         info="Define the assistant's role, purpose, and behavior in a single prompt"
                     )
                     
-                    # Assistant configuration options
-                    enable_research_assistant = gr.Checkbox(
-                        label="Research Template",
-                        value=False,
-                        info="Enable to use pre-configured research assistant settings"
-                    )
+                    # Template selection
+                    with gr.Row():
+                        template_selector = gr.Radio(
+                            label="Assistant Template",
+                            choices=["None", "Research Template", "Socratic Template"],
+                            value="None",
+                            info="Select a pre-configured template or use custom system prompt"
+                        )
                     
             
                     
@@ -1905,10 +1935,10 @@ with gr.Blocks(
             
             
             
-            # Connect the research assistant checkbox
-            enable_research_assistant.change(
-                toggle_research_assistant,
-                inputs=[enable_research_assistant],
+            # Connect the template selector
+            template_selector.change(
+                toggle_template,
+                inputs=[template_selector],
                 outputs=[system_prompt, enable_dynamic_urls]
             )
             
@@ -1947,7 +1977,7 @@ with gr.Blocks(
             # Connect the generate button
             generate_btn.click(
                 on_generate,
-                inputs=[name, description, system_prompt, enable_research_assistant, 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, enable_vector_rag, rag_tool_state],
                 outputs=[status, download_file, sandbox_state]
             )
             
@@ -2066,7 +2096,7 @@ with gr.Blocks(
     # Connect cross-tab functionality after all components are defined
     preview_btn.click(
         on_preview_combined,
-        inputs=[name, description, system_prompt, enable_research_assistant, model, temperature, max_tokens, examples_text, enable_dynamic_urls, enable_vector_rag],
+        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]
     )
 

requirements.txt

@@ -3,10 +3,6 @@ requests>=2.32.3
 beautifulsoup4>=4.12.3
 python-dotenv>=1.0.0
 
-# Web Scraping service
-crawl4ai==0.7.0
-playwright==1.53.0
-
 # Vector RAG dependencies (optional)
 sentence-transformers>=2.2.2
 faiss-cpu>=1.11.0