dw

model.py

@@ -1,4 +1,5 @@
 import os
+import shutil
 import requests
 from llama_cpp import Llama
 
@@ -9,12 +10,13 @@ MODEL_PATH = f"./models/{MODEL_FILENAME}"
 def download_model():
     os.makedirs("./models", exist_ok=True)
     print("📦 Downloading GGUF model directly from URL...")
-    with requests.get(MODEL_URL, stream=True) as r:
-        r.raise_for_status()
-        with open(MODEL_PATH, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                f.write(chunk)
-    print(f"✅ Model downloaded to {MODEL_PATH}")
+    response = requests.get(MODEL_URL, stream=True)
+    if response.status_code == 200:
+        with open(MODEL_PATH, 'wb') as f:
+            shutil.copyfileobj(response.raw, f)
+        print(f"✅ Model downloaded to {MODEL_PATH}")
+    else:
+        raise RuntimeError(f"❌ Failed to download model. Status code: {response.status_code}")
 
 # Only download if not already present
 if not os.path.exists(MODEL_PATH):

requirements.txt

@@ -1,5 +1,5 @@
 fastapi
 uvicorn
-llama-cpp-python==0.2.72  # prebuilt versions now available from PyPI
+llama-cpp-python==0.2.74  # prebuilt versions now available from PyPI
 python-dotenv
 huggingface_hub