Update app.py

app.py

@@ -18,9 +18,14 @@ from llama_index.core import Document
 from llama_index.core.retrievers import VectorIndexRetriever
 from llama_index.core import QueryBundle
 import time
+from huggingface_hub import login
 
 nest_asyncio.apply()
 hf_token = os.getenv('hf_token')
+
+
+# Replace 'your_token_here' with your actual Hugging Face API token
+login(token=hf_token)
 # quantize to save memory
 quantization_config = BitsAndBytesConfig(
     load_in_4bit=True,
@@ -37,12 +42,11 @@ llm = HuggingFaceLLM(
     model_kwargs={"quantization_config": quantization_config},
     generate_kwargs={"temperature": 0.1, "top_k": 50, "top_p": 0.95},
     device_map="cuda:0",
-    token = hf_token,
+ 
 )
 
 embed_model = HuggingFaceEmbedding(
     model_name="kheopss/kheops_embedding_e5_v3",
-    token = hf_token,
 )
 Settings.llm=llm
 Settings.embed_model=embed_model