Update app.py

app.py

@@ -16,7 +16,8 @@ import re
 
 class DocumentRetrievalAndGeneration:
     def __init__(self, embedding_model_name, lm_model_id, data_folder):
-        HF_TOKEN = os.getenv('HF_TOKEN')
+        hf_token = os.getenv('HF_TOKEN')
+        print(HF_TOKEN,hf_token)
         self.all_splits = self.load_documents(data_folder)
         self.embeddings = SentenceTransformer(embedding_model_name)
         self.cpu_index = self.create_faiss_index()
@@ -47,7 +48,7 @@ class DocumentRetrievalAndGeneration:
             bnb_4bit_compute_dtype=torch.bfloat16
         )
         device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config,token=HF_TOKEN)
+        model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config,token=hf_token)
         tokenizer = AutoTokenizer.from_pretrained(model_id)
         generate_text = pipeline(
             model=model,