Update app/config.py

app/config.py

@@ -1,39 +1,27 @@
-"""
-Configuration for Nur Brain Service
-"""
 import os
 from functools import lru_cache
 from pydantic_settings import BaseSettings
 
-
 class Settings(BaseSettings):
-    """Application settings loaded from environment variables."""
-    
-    # Service Info
-    service_name: str = "Nur Brain"
-    version: str = "1.0.0"
-    debug: bool = False
+    service_name: str = "Nur Brain (HF)"
+    version: str = "2.0.0-Parallel"
     
-    # Security
-    nur_internal_key: str
+    # Security Key (Set this in HF Settings -> Variables & Secrets)
+    nur_internal_key: str = os.getenv("NUR_INTERNAL_KEY", "default_insecure_key")
     
-    # LLM Configuration
-    model_path: str = "/app/models/llama-3-8b-instruct.Q4_K_M.gguf"
+    # Model Auto-Download Settings
+    repo_id: str = "NousResearch/Meta-Llama-3-8B-Instruct-GGUF"
+    filename: str = "Meta-Llama-3-8B-Instruct-Q4_K_M.gguf"
+    model_path: str = "" # Will be set dynamically after download
+
+    # Performance Settings
     model_n_ctx: int = 4096
-    model_n_threads: int = 4
-    model_n_gpu_layers: int = 0  # Set to higher value if GPU available
-    
-    # Generation defaults
-    default_max_tokens: int = 512
-    default_temperature: float = 0.7
-    default_top_p: float = 0.9
+    model_n_threads: int = 4  # Max CPU cores on HF Free
+    model_n_parallel: int = 8 # Allows 8 concurrent requests
     
     class Config:
         env_file = ".env"
-        env_file_encoding = "utf-8"
-
 
 @lru_cache()
 def get_settings() -> Settings:
-    """Get cached settings instance."""
     return Settings()