Update app.py

app.py

@@ -19,7 +19,7 @@ class DocumentRetrievalAndGeneration:
         # hf_token = os.getenv('HF_TOKEN')
         hf="hf_VuNNBwnFqlcKzV"
         token="vCfLXEBxyAOftxvlWpwf"
-        hf_token=hf+token
+        self.hf_token=hf+token
         # print(HF_TOKEN,hf_token)
         self.all_splits = self.load_documents(data_folder)
         self.embeddings = SentenceTransformer(embedding_model_name)
@@ -51,7 +51,7 @@ 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=self.hf_token)
         tokenizer = AutoTokenizer.from_pretrained(model_id)
         generate_text = pipeline(
             model=model,