Update app.py

app.py

@@ -61,7 +61,7 @@ Respond with:
 Format: Markdown with LaTeX mathematical notation where applicable
 """
 
-# Validation
+# Validate API key configuration
 if not ResearchConfig.DEEPSEEK_API_KEY:
     st.error("""**Research Portal Configuration Required**  
     1. Obtain DeepSeek API key: [platform.deepseek.com](https://platform.deepseek.com/)  
@@ -87,6 +87,8 @@ class QuantumDocumentManager:
             separators=["\n\n", "\n", "|||"]
         )
         docs = splitter.create_documents(documents)
+        # Log how many chunks were created
+        st.write(f"Created {len(docs)} chunks for collection '{collection_name}'")
         return Chroma.from_documents(
             documents=docs,
             embedding=self.embeddings,
@@ -134,8 +136,11 @@ class ResearchRetriever:
     
     def retrieve(self, query: str, domain: str) -> List[Any]:
         try:
-            return self.retrievers[domain].invoke(query)
+            results = self.retrievers[domain].invoke(query)
+            st.write(f"[DEBUG] Retrieved {len(results)} documents for query: '{query}' in domain '{domain}'")
+            return results
         except KeyError:
+            st.error(f"[ERROR] Retrieval domain '{domain}' not found.")
             return []
 
 retriever = ResearchRetriever()
@@ -150,7 +155,7 @@ class CognitiveProcessor:
     
     def process_query(self, prompt: str) -> Dict:
         futures = []
-        for _ in range(3):  # Triple redundancy
+        for _ in range(3):  # Triple redundancy for robustness
             futures.append(self.executor.submit(
                 self._execute_api_request,
                 prompt
@@ -197,6 +202,7 @@ class CognitiveProcessor:
         valid = [r for r in results if "error" not in r]
         if not valid:
             return {"error": "All API requests failed"}
+        # Choose the result with the longest content
         return max(valid, key=lambda x: len(x.get('choices', [{}])[0].get('message', {}).get('content', '')))
 
 # ------------------------------
@@ -209,6 +215,7 @@ class ResearchWorkflow:
         self._build_workflow()
 
     def _build_workflow(self):
+        # Register nodes in the state graph
         self.workflow.add_node("ingest", self.ingest_query)
         self.workflow.add_node("retrieve", self.retrieve_documents)
         self.workflow.add_node("analyze", self.analyze_content)
@@ -231,6 +238,7 @@ class ResearchWorkflow:
     def ingest_query(self, state: AgentState) -> Dict:
         try:
             query = state["messages"][-1].content
+            st.write(f"[DEBUG] Ingesting query: {query}")
             return {
                 "messages": [AIMessage(content="Query ingested successfully")],
                 "context": {"raw_query": query},
@@ -243,6 +251,8 @@ class ResearchWorkflow:
         try:
             query = state["context"]["raw_query"]
             docs = retriever.retrieve(query, "research")
+            # Log the retrieval result for debugging
+            st.write(f"[DEBUG] Retrieved {len(docs)} documents from retrieval node.")
             return {
                 "messages": [AIMessage(content=f"Retrieved {len(docs)} documents")],
                 "context": {
@@ -255,7 +265,13 @@ class ResearchWorkflow:
 
     def analyze_content(self, state: AgentState) -> Dict:
         try:
-            docs = "\n\n".join([d.page_content for d in state["context"]["documents"]])
+            # Ensure documents are present before proceeding
+            if "documents" not in state["context"] or not state["context"]["documents"]:
+                return self._error_state("No documents retrieved; please check your query or retrieval process.")
+            
+            # Concatenate all document content for analysis
+            docs = "\n\n".join([d.page_content for d in state["context"]["documents"] if hasattr(d, "page_content")])
+            st.write(f"[DEBUG] Analyzing content from {len(state['context']['documents'])} documents.")
             prompt = ResearchConfig.ANALYSIS_TEMPLATE.format(context=docs)
             response = self.processor.process_query(prompt)
             
@@ -304,9 +320,11 @@ Improve:
 
     def _quality_check(self, state: AgentState) -> str:
         content = state["messages"][-1].content
+        # Check for the keyword "VALID" in the output; if missing, trigger refinement
         return "valid" if "VALID" in content else "invalid"
 
     def _error_state(self, message: str) -> Dict:
+        st.write(f"[ERROR] {message}")
         return {
             "messages": [AIMessage(content=f"❌ {message}")],
             "context": {"error": True},