Remove ~1,200 lines of dead code across codebase

backend/ollama_client.py

@@ -166,37 +166,3 @@ def chat_stream(self, message: str, model: str = "llama3.2", conversation_histor
         except requests.exceptions.RequestException as e:
             yield f"Connection error: {e}"
 
-def main():
-    """Test the Ollama client"""
-    client = OllamaClient()
-
-    # Check if Ollama is running
-    if not client.is_ollama_running():
-        print("❌ Ollama is not running. Please start Ollama first.")
-        print("Install: https://ollama.ai")
-        print("Run: ollama serve")
-        return
-
-    print("✅ Ollama is running!")
-
-    # List available models
-    models = client.list_models()
-    print(f"Available models: {models}")
-
-    # Try to use llama3.2, pull if needed
-    model_name = "llama3.2"
-    if model_name not in [m.split(":")[0] for m in models]:
-        print(f"Model {model_name} not found. Pulling...")
-        if client.pull_model(model_name):
-            print(f"✅ Model {model_name} pulled successfully!")
-        else:
-            print(f"❌ Failed to pull model {model_name}")
-            return
-
-    # Test chat
-    print("\n🤖 Testing chat...")
-    response = client.chat("Hello! Can you tell me a short joke?", model_name)
-    print(f"AI: {response}")
-
-if __name__ == "__main__":
-    main()    

backend/server.py

@@ -730,19 +730,6 @@ def handle_index_documents(self, session_id: str):
             print(f"❌ Exception during indexing: {str(e)}")
             self.send_json_response({"error": f"An unexpected error occurred: {str(e)}"}, status_code=500)
 
-    def handle_pdf_upload(self, session_id: str):
-        """
-        Processes PDF files: extracts text and stores it in the database.
-        DEPRECATED: This is the old method. Use handle_file_upload instead.
-        """
-        # This function is now deprecated in favor of the new indexing workflow
-        # but is kept for potential legacy/compatibility reasons.
-        # For new functionality, it should not be used.
-        self.send_json_response({
-            "warning": "This upload method is deprecated. Use the new file upload and indexing flow.",
-            "message": "No action taken."
-        }, status_code=410) # 410 Gone
-
     def handle_get_models(self):
         """Get available models from both Ollama and HuggingFace, grouped by capability"""
         try:
@@ -907,15 +894,9 @@ def handle_build_index(self, index_id: str):
             # Set per-index overview file path
             overview_path = f"index_store/overviews/{index_id}.jsonl"
 
-            # Ensure config_override includes overview_path
-            def ensure_overview_path(cfg: dict):
-                cfg["overview_path"] = overview_path
-
-            # we'll inject later when we build config_override
-
             # Delegate to advanced RAG API same as session indexing
             rag_api_url = "http://localhost:8001/index"
-            import requests, json as _json
+            import requests
             # Use the index's dedicated LanceDB table so retrieval matches
             table_name = index.get("vector_table_name")
             payload = {
@@ -1098,14 +1079,6 @@ def main():
             print(f"❌ Error initializing PDF processor: {e}")
             print("⚠️ PDF processing disabled - server will run without RAG functionality")
 
-        # Set a global reference to the initialized processor if needed elsewhere
-        global pdf_processor
-        pdf_processor = pdf_module.simple_pdf_processor
-        if pdf_processor:
-            print("✅ Global PDF processor initialized")
-        else:
-            print("⚠️ PDF processing disabled - server will run without RAG functionality")
-
         # Cleanup empty sessions on startup
         print("🧹 Cleaning up empty sessions...")
         cleanup_count = db.cleanup_empty_sessions()

backend/simple_pdf_processor.py

@@ -199,16 +199,3 @@ def initialize_simple_pdf_processor():
         print(f"❌ Failed to initialize PDF processor: {str(e)}")
         simple_pdf_processor = None
 
-def get_simple_pdf_processor():
-    """Get the global PDF processor instance"""
-    global simple_pdf_processor
-    if simple_pdf_processor is None:
-        initialize_simple_pdf_processor()
-    return simple_pdf_processor
-
-if __name__ == "__main__":
-    # Test the simple PDF processor
-    print("🧪 Testing simple PDF processor...")
-
-    processor = SimplePDFProcessor()
-    print("✅ Simple PDF processor test completed!") 

rag_system/agent/loop.py

@@ -267,18 +267,6 @@ async def _run_async(self, query: str, table_name: str = None, session_id: str =
         # 🚀 NEW: Get conversation history
         history = self.chat_histories.get(session_id, []) if session_id else []
 
-        # 🔄 Refresh overviews for this session if available
-        # if session_id and session_id != getattr(self, "_current_overview_session", None):
-        #     candidate_path = os.path.join("index_store", "overviews", f"{session_id}.jsonl")
-        #     if os.path.exists(candidate_path):
-        #         self._load_overviews(candidate_path)
-        #         self._current_overview_session = session_id
-        #     else:
-        #         # Fall back to global overviews if per-session file not found
-        #         if self._current_overview_session != "GLOBAL":
-        #             self._load_overviews(self._global_overview_path)
-        #             self._current_overview_session = "GLOBAL"
-
         query_type = await self._triage_query_async(query, history)
         print(f"🎯 ROUTING DEBUG: Final triage decision: '{query_type}'")
         print(f"Agent Triage Decision: '{query_type}'")

rag_system/api_server.py

@@ -1,7 +1,7 @@
 import json
 import http.server
 import socketserver
-from urllib.parse import urlparse, parse_qs
+from urllib.parse import urlparse
 import os
 import requests
 import sys
@@ -39,34 +39,23 @@
 # Add helper near top after db & agent init
 # -------------- Helper ----------------
 
+_embed_logger = logging.getLogger("embedding_debug")
+
 def _apply_index_embedding_model(idx_ids):
     """Ensure retrieval pipeline uses the embedding model stored with the first index."""
-    debug_info = f"🔧 _apply_index_embedding_model called with idx_ids: {idx_ids}\n"
-
     if not idx_ids:
-        debug_info += "⚠️ No index IDs provided\n"
-        with open("logs/embedding_debug.log", "a") as f:
-            f.write(debug_info)
+        _embed_logger.debug("No index IDs provided")
         return
     try:
         idx = db.get_index(idx_ids[0])
-        debug_info += f"🔧 Retrieved index: {idx.get('id')} with metadata: {idx.get('metadata', {})}\n"
         model = (idx.get("metadata") or {}).get("embedding_model")
-        debug_info += f"🔧 Embedding model from metadata: {model}\n"
+        _embed_logger.debug("Index %s embedding_model=%s", idx_ids[0], model)
         if model:
             rp = RAG_AGENT.retrieval_pipeline
-            current_model = rp.config.get("embedding_model_name")
-            debug_info += f"🔧 Current embedding model: {current_model}\n"
             rp.update_embedding_model(model)
-            debug_info += f"🔧 Updated embedding model to: {model}\n"
-        else:
-            debug_info += "⚠️ No embedding model found in metadata\n"
+            _embed_logger.debug("Updated embedding model to: %s", model)
     except Exception as e:
-        debug_info += f"⚠️ Could not apply index embedding model: {e}\n"
-
-    # Write debug info to file
-    with open("logs/embedding_debug.log", "a") as f:
-        f.write(debug_info)
+        _embed_logger.warning("Could not apply index embedding model: %s", e)
 
 def _get_table_name_for_session(session_id):
     """Get the correct vector table name for a session by looking up its linked indexes."""