Update app/app.py

app/app.py

@@ -7,24 +7,28 @@ import requests
 from app.policy_vector_db import PolicyVectorDB, ensure_db_populated
 
 MODEL_URL = "https://huggingface.co/Kalpokoch/QuantizedFineTunedPhi1.5/resolve/main/dop-phi-1.5-Q4_K_M.gguf"
-MODEL_DIR = "/app/models"
-MODEL_PATH = os.path.join(MODEL_DIR, "dop-phi-1.5-Q4_K_M.gguf")
-CHUNKS_PATH = "/app/processed_chunks_final.json"
+MODEL_PATH = "/tmp/models/dop-phi-1.5-Q4_K_M.gguf"
+CHUNKS_PATH = "/app/processed_chunks.json"
 
 # Download the model if not already present
 def download_model():
     if not os.path.exists(MODEL_PATH):
+        os.makedirs(os.path.dirname(MODEL_PATH), exist_ok=True)
         print("🔽 Downloading model...")
-        response = requests.get(MODEL_URL, stream=True)
-        with open(MODEL_PATH, "wb") as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-        print("✅ Model downloaded.")
+        url = "https://huggingface.co/Kalpokoch/QuantizedFineTunedPhi1.5/resolve/main/dop-phi-1.5-Q4_K_M.gguf"
+        response = requests.get(url, stream=True)
+        if response.status_code == 200:
+            with open(MODEL_PATH, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    f.write(chunk)
+            print("✅ Model downloaded successfully.")
+        else:
+            raise Exception(f"Failed to download model: {response.status_code}")
 
 download_model()
 
 # Initialize model and vector database
-llm = Llama(model_path=MODEL_PATH, n_ctx=2048)
+llm = Llama(model_path=MODEL_PATH, n_ctx=2048, n_threads=4)
 vector_db = PolicyVectorDB(CHUNKS_PATH)
 ensure_db_populated(vector_db)