Update app.py

app.py

@@ -3,6 +3,11 @@ from llama_cpp import Llama
 from huggingface_hub import hf_hub_download
 import os
 
+import platform
+import psutil
+import multiprocessing
+
+
 app = FastAPI()
 
 # === Model Config ===
@@ -37,6 +42,37 @@ llm = Llama(
 def root():
     return {"message": "Mistral API is live!"}
 
+@app.get("/get_sys")
+def get_sys_specs():
+    cpu_info = {
+        "physical_cores": psutil.cpu_count(logical=False),
+        "logical_cores": psutil.cpu_count(logical=True),
+        "max_frequency_mhz": psutil.cpu_freq().max if psutil.cpu_freq() else None,
+        "cpu_usage_percent": psutil.cpu_percent(interval=1)
+    }
+
+    memory = psutil.virtual_memory()
+    ram_info = {
+        "total_gb": round(memory.total / (1024 ** 3), 2),
+        "available_gb": round(memory.available / (1024 ** 3), 2),
+        "used_percent": memory.percent
+    }
+
+    system_info = {
+        "system": platform.system(),
+        "machine": platform.machine(),
+        "platform": platform.platform(),
+        "processor": platform.processor(),
+        "python_version": platform.python_version(),
+    }
+
+    return {
+        "cpu": cpu_info,
+        "ram": ram_info,
+        "system": system_info,
+        "recommended_threads": min(psutil.cpu_count(logical=False) or 2, 8)
+    }
+
 @app.post("/generate")
 async def generate(request: Request):
     data = await request.json()