Update logger

app.py

@@ -28,7 +28,6 @@ logger.setLevel(logging.DEBUG)
 
 # Debug Start
 logger.info("🚀 Starting Medical Chatbot API...")
-print("🚀 Starting Medical Chatbot API...")
 
 # ✅ Environment Variables
 mongo_uri = os.getenv("MONGO_URI")
@@ -47,7 +46,7 @@ def check_system_resources():
     cpu = psutil.cpu_percent(interval=1)
     disk = psutil.disk_usage("/")
     # Defines log info messages
-    logger.info(f"🔍 System Resources - RAM: {memory.percent}%, CPU: {cpu}%, Disk: {disk.percent}%")
+    logger.info(f"[System] 🔍 System Resources - RAM: {memory.percent}%, CPU: {cpu}%, Disk: {disk.percent}%")
     if memory.percent > 85:
         logger.warning("⚠️ High RAM usage detected!")
     if cpu > 90:
@@ -85,14 +84,12 @@ app.add_middleware(
 index = None  # Delay FAISS Index loading until first query
 
 # ✅ Load SentenceTransformer Model (Quantized/Halved)
-logger.info("📥 Loading SentenceTransformer Model...")
-print("📥 Loading SentenceTransformer Model...")
+logger.info("[Embedder] 📥 Loading SentenceTransformer Model...")
 MODEL_CACHE_DIR = "/app/model_cache"
 try:
     embedding_model = SentenceTransformer(MODEL_CACHE_DIR, device="cpu")
     embedding_model = embedding_model.half()  # Reduce memory
     logger.info("✅ Model Loaded Successfully.")
-    print("✅ Model Loaded Successfully.")
 except Exception as e:
     logger.error(f"❌ Model Loading Failed: {e}")
     exit(1)
@@ -115,17 +112,15 @@ fs = gridfs.GridFS(idb, collection="faiss_index_files")
 def load_faiss_index():
     global index
     if index is None:
-        print("⏳ Loading FAISS index from GridFS...")
+        logger.info("[KB] ⏳ Loading FAISS index from GridFS...")
         existing_file = fs.find_one({"filename": "faiss_index.bin"})
         if existing_file:
             stored_index_bytes = existing_file.read()
             index_bytes_np = np.frombuffer(stored_index_bytes, dtype='uint8')
             index = faiss.deserialize_index(index_bytes_np)
-            print("✅ FAISS Index Loaded")
-            logger.info("✅ FAISS Index Loaded")
+            logger.info("[KB] ✅ FAISS Index Loaded")
         else:
-            print("❌ FAISS index not found in GridFS.")
-            logger.error("❌ FAISS index not found in GridFS.")
+            logger.error("[KB] ❌ FAISS index not found in GridFS.")
     return index
 
 # ✅ Retrieve Medical Info
@@ -148,8 +143,7 @@ def gemini_flash_completion(prompt, model, temperature=0.7):
         response = client_genai.models.generate_content(model=model, contents=prompt)
         return response.text
     except Exception as e:
-        logger.error(f"❌ Error calling Gemini API: {e}")
-        print(f"❌ Error calling Gemini API: {e}")
+        logger.error(f"[LLM] ❌ Error calling Gemini API: {e}")
         return "Error generating response from Gemini."
 
 # ✅ Chatbot Class
@@ -177,6 +171,7 @@ class RAGMedicalChatbot:
         parts.append(f"Question: {user_query}")
         parts.append(f"Language: {lang}")
         prompt = "\n\n".join(parts)
+        logger.info(f"[LLM] Question query in `prompt`: {prompt}") # Debug out checking RAG on kb and history
         response = gemini_flash_completion(prompt, model=self.model_name, temperature=0.7)
          # Store exchange + chunking
         if user_id:
@@ -205,8 +200,7 @@ async def chat_endpoint(req: Request):
 
 # ✅ Run Uvicorn
 if __name__ == "__main__":
-    logger.info("✅ Starting FastAPI Server...")
-    print("✅ Starting FastAPI Server...")
+    logger.info("[System] ✅ Starting FastAPI Server...")
     try:
         uvicorn.run(app, host="0.0.0.0", port=7860, log_level="debug")
     except Exception as e:

memory.py

@@ -78,6 +78,7 @@ class MemoryManager:
                 results.append((score, chunk))
         # Sort result on best scored
         results.sort(key=lambda x: x[0], reverse=True)
+        logger.info(f"[Memory] RAG Retrieved Topic: {results}")
         return [f"### Topic: {c['tag']}\n{c['text']}" for _, c in results]
 
 
@@ -162,14 +163,13 @@ class MemoryManager:
                     # ,generation_config={"temperature": 0.4} # Skip temp configs for gem-flash
                 )
                 output = result.text.strip()
-                logger.info(f"📦 Gemini summarized chunk output: {output}")
-                print(f"📦 Gemini summarized chunk output: {output}")
+                logger.info(f"[Memory] 📦 Gemini summarized chunk output: {output}")
                 return [
                     {"tag": self._quick_extract_topic(chunk), "text": chunk.strip()}
                     for chunk in output.split('---') if chunk.strip()
                 ]
             except Exception as e:
-                logger.warning(f"❌ Gemini chunking failed: {e}")
+                logger.warning(f"[Memory] ❌ Gemini chunking failed: {e}")
                 retries += 1
                 time.sleep(0.5)
         return [{"tag": "general", "text": response.strip()}]  # fallback