Update app.py

app.py

@@ -11,7 +11,7 @@ from llama_index.core import (
     Document,
     Settings,
 )
-from llama_index.llms.huggingface_api import (HuggingFaceLLM, )
+from llama_index.llms.huggingface import (HuggingFaceLLM, )
 from llama_index.llms.huggingface_api import (HuggingFaceInferenceAPI, )
 from llama_index.core.base.llms.types import ChatMessage
 from huggingface_hub import login
@@ -77,7 +77,8 @@ Settings.llm = HuggingFaceInferenceAPI(model_name=LLM_NAME,
                                                "presence_penalty": presence_penalty, "frequency_penalty": frequency_penalty,
                                                "top_k": top_k, "do_sample": False},
 #                              tokenizer_kwargs={"max_length": 4096},
-                              tokenizer_name=LLM_NAME, 
+                              tokenizer_name=LLM_NAME,
+                              provider=auto,
                              )
 # "BAAI/bge-m3"
 Settings.embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")