fix: Fix for case where nothing is selected for context.

surfsense_backend/app/agents/researcher/qna_agent/nodes.py

@@ -3,7 +3,7 @@ from langchain_core.runnables import RunnableConfig
 from .state import State
 from typing import Any, Dict
 from app.config import config as app_config
-from .prompts import get_qna_citation_system_prompt
+from .prompts import get_qna_citation_system_prompt, get_qna_no_documents_system_prompt
 from langchain_core.messages import HumanMessage, SystemMessage
 
 async def rerank_documents(state: State, config: RunnableConfig) -> Dict[str, Any]:
@@ -73,7 +73,8 @@ async def answer_question(state: State, config: RunnableConfig) -> Dict[str, Any
     This node takes the relevant documents provided in the configuration and uses
     an LLM to generate a comprehensive answer to the user's question with
     proper citations. The citations follow IEEE format using source IDs from the
-    documents.
+    documents. If no documents are provided, it will use chat history to generate
+    an answer.
     
     Returns:
         Dict containing the final answer in the "final_answer" key.
@@ -87,55 +88,59 @@ async def answer_question(state: State, config: RunnableConfig) -> Dict[str, Any
     # Initialize LLM
     llm = app_config.fast_llm_instance
     
-    # If no documents were provided, return a message indicating this
-    if not documents or len(documents) == 0:
-        return {
-            "final_answer": "I don't have any relevant documents in your personal knowledge base to answer this question. Please try asking about topics covered in your saved content, or add more documents to your knowledge base."
-        }
+    # Check if we have documents to determine which prompt to use
+    has_documents = documents and len(documents) > 0
     
-    # Prepare documents for citation formatting
-    formatted_documents = []
-    for _i, doc in enumerate(documents):
-        # Extract content and metadata
-        content = doc.get("content", "")
-        doc_info = doc.get("document", {})
-        document_id = doc_info.get("id")  # Use document ID
+    # Prepare documents for citation formatting (if any)
+    documents_text = ""
+    if has_documents:
+        formatted_documents = []
+        for _i, doc in enumerate(documents):
+            # Extract content and metadata
+            content = doc.get("content", "")
+            doc_info = doc.get("document", {})
+            document_id = doc_info.get("id")  # Use document ID
+            
+            # Format document according to the citation system prompt's expected format
+            formatted_doc = f"""
+            <document>
+                <metadata>
+                    <source_id>{document_id}</source_id>
+                    <source_type>{doc_info.get("document_type", "CRAWLED_URL")}</source_type>
+                </metadata>
+                <content>
+                    {content}
+                </content>
+            </document>
+            """
+            formatted_documents.append(formatted_doc)
         
-        # Format document according to the citation system prompt's expected format
-        formatted_doc = f"""
-        <document>
-            <metadata>
-                <source_id>{document_id}</source_id>
-                <source_type>{doc_info.get("document_type", "CRAWLED_URL")}</source_type>
-            </metadata>
-            <content>
-                {content}
-            </content>
-        </document>
+        # Create the formatted documents text
+        documents_text = f"""
+        Source material from your personal knowledge base:
+        <documents>
+            {"\n".join(formatted_documents)}
+        </documents>
         """
-        formatted_documents.append(formatted_doc)
-    
-    # Create the formatted documents text
-    documents_text = "\n".join(formatted_documents)
     
     # Construct a clear, structured query for the LLM
     human_message_content = f"""
-    Source material from your personal knowledge base:
-    <documents>
-        {documents_text}
-    </documents>
+    {documents_text}
     
     User's question:
     <user_query>
         {user_query}
     </user_query>
     
-    Please provide a detailed, comprehensive answer to the user's question using the information from their personal knowledge sources. Make sure to cite all information appropriately and engage in a conversational manner.
+    {"Please provide a detailed, comprehensive answer to the user's question using the information from their personal knowledge sources. Make sure to cite all information appropriately and engage in a conversational manner." if has_documents else "Please provide a helpful answer to the user's question based on our conversation history and your general knowledge. Engage in a conversational manner."}
     """
     
+    # Choose the appropriate system prompt based on document availability
+    system_prompt = get_qna_citation_system_prompt() if has_documents else get_qna_no_documents_system_prompt()
+    
     # Create messages for the LLM, including chat history for context
     messages_with_chat_history = state.chat_history + [
-        SystemMessage(content=get_qna_citation_system_prompt()),
+        SystemMessage(content=system_prompt),
         HumanMessage(content=human_message_content)
     ]
     

surfsense_backend/app/agents/researcher/qna_agent/prompts.py

@@ -118,3 +118,49 @@ Make sure your response:
 5. Offers follow-up suggestions when appropriate
 </user_query_instructions>
 """
+
+
+def get_qna_no_documents_system_prompt():
+    return f"""
+Today's date: {datetime.datetime.now().strftime("%Y-%m-%d")}
+You are SurfSense, an advanced AI research assistant that provides helpful, detailed answers to user questions in a conversational manner.
+
+<context>
+The user has asked a question but there are no specific documents from their personal knowledge base available to answer it. You should provide a helpful response based on:
+1. The conversation history and context
+2. Your general knowledge and expertise
+3. Understanding of the user's needs and interests based on our conversation
+</context>
+
+<instructions>
+1. Provide a comprehensive, helpful answer to the user's question
+2. Draw upon the conversation history to understand context and the user's specific needs
+3. Use your general knowledge to provide accurate, detailed information
+4. Be conversational and engaging, as if having a detailed discussion with the user
+5. Acknowledge when you're drawing from general knowledge rather than their personal sources
+6. Provide actionable insights and practical information when relevant
+7. Structure your answer logically and clearly
+8. If the question would benefit from personalized information from their knowledge base, gently suggest they might want to add relevant content to SurfSense
+9. Be honest about limitations while still being maximally helpful
+10. Maintain the helpful, knowledgeable tone that users expect from SurfSense
+</instructions>
+
+<format>
+- Write in a clear, conversational tone suitable for detailed Q&A discussions
+- Provide comprehensive answers that thoroughly address the user's question
+- Use appropriate paragraphs and structure for readability
+- No citations are needed since you're using general knowledge
+- Be thorough and detailed in your explanations while remaining focused on the user's specific question
+- If asking follow-up questions would be helpful, suggest them at the end of your response
+- When appropriate, mention that adding relevant content to their SurfSense knowledge base could provide more personalized answers
+</format>
+
+<user_query_instructions>
+When answering the user's question without access to their personal documents:
+1. Provide the most helpful and comprehensive answer possible using general knowledge
+2. Be conversational and engaging
+3. Draw upon conversation history for context
+4. Be clear that you're providing general information
+5. Suggest ways the user could get more personalized answers by expanding their knowledge base when relevant
+</user_query_instructions>
+"""