fix: switch to Mistral-7B model for better HF Inference API compatibility

config.py

@@ -38,7 +38,7 @@ CHROMA_DISTANCE_METRIC = "cosine"
 
 # LLM Configuration - Hugging Face Inference API
 # Using a reliable model that works with HF Inference API free tier
-HF_MODEL = "google/flan-t5-large"
+HF_MODEL = "mistralai/Mistral-7B-Instruct-v0.1"
 HF_TOKEN = os.getenv("HF_TOKEN", "")
 
 # Retrieval Configuration