adding RAM utilization logs

app.py

@@ -18,6 +18,15 @@ from gguf_engine import (
     exclude_thinking_component,
     LLM_LORA_PATHS,
 )
+import psutil
+import os
+
+def check_memory():
+    process = psutil.Process(os.getpid())
+    # RAM usage in GB
+    return process.memory_info().rss / 1024**3 
+
+
 
 
 # ==========================================
@@ -30,7 +39,9 @@ def _stream_generate(prompt: str, max_tokens: int = 800):
     Generator that yields incremental text from the base model (no LoRA).
     Used exclusively for the orchestrator's final answer.
     """
+    print(f"[BEFORE MODEL LOAD] RAM Usage: {check_memory():.2f} GB")
     model = _load_text_model("default")
+    print(f"[AFTER MODEL LOAD] RAM Usage: {check_memory():.2f} GB")
     formatted = _format_gemma_prompt(prompt)
     accumulated = ""
     for chunk in model(
@@ -42,6 +53,7 @@ def _stream_generate(prompt: str, max_tokens: int = 800):
         top_p       = 1.0,
         stream      = True,
     ):
+        print(f"[STREAM] RAM Usage: {check_memory():.2f} GB")
         token = chunk["choices"][0]["text"]
         accumulated += token
         yield exclude_thinking_component(accumulated)
@@ -84,6 +96,7 @@ def process_patient_data(
     user_query, lab_values, behaviour_changes, wsi_image,
     progress=gr.Progress(track_tqdm=True)
 ):
+    print(f"[START] RAM Usage: {check_memory():.2f} GB")
     # ── Assemble clinical text ─────────────────────────────────────────────
     parts = []
     if lab_values.strip():
@@ -146,6 +159,7 @@ def process_patient_data(
     # Simpler: just run the full agent and grab intermediate results.
     progress(0.2, desc="Module 2 · Risk Stratification LoRA…")
     final_state = full_agent.invoke(initial_state)
+    print(f"[AFTER AGENT] RAM Usage: {check_memory():.2f} GB")
 
     # ── Unpack results ─────────────────────────────────────────────────────
     ran_m2 = bool(final_state.get("module2_risk_score",   "").strip())