Error - LLM Provider NOT provided.

[sabatale]

Hello,

Initially we had the following error:

File "C:\Python311\Lib\site-packages\pydantic\deprecated\class_validators.py", line 240, in root_validator
    raise PydanticUserError(
pydantic.errors.PydanticUserError: If you use `@root_validator` with pre=False (the default) you MUST specify `skip_on_failure=True`. Note that `@root_validator` is deprecated and should be replaced with `@model_validator`.

After reading some other issues, we ran:

pip install pydantic==1.10.18

But now, with JSON documents from read_files_as_documents, embed_model="default" or (local:intfloat/multilingual-e5-small) returns the error below (Windows, latest autollm).

We tried installing a few different litellm versions with no success (same error, or another one because it's incompatible with autollm):

Traceback (most recent call last):
  File "llm.py", line 9, in <module>
    query_engine = AutoQueryEngine.from_defaults(
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\query_engine.py", line 258, in from_defaults
    return create_query_engine(
           ^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\query_engine.py", line 105, in create_query_engine
    vector_store_index = AutoVectorStoreIndex.from_defaults(
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\vector_store_index.py", line 107, in from_defaults
    index = AutoVectorStoreIndex._create_index(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\vector_store_index.py", line 215, in _create_index
    index = VectorStoreIndex.from_documents(
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\base.py", line 107, in from_documents
    return cls(
           ^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\vector_store\base.py", line 52, in __init__
    super().__init__(
  File "C:\Python311\Lib\site-packages\llama_index\indices\base.py", line 72, in __init__
    index_struct = self.build_index_from_nodes(nodes)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\vector_store\base.py", line 262, in build_index_from_nodes
    return self._build_index_from_nodes(nodes, **insert_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\vector_store\base.py", line 243, in _build_index_from_nodes
    self._add_nodes_to_index(
  File "C:\Python311\Lib\site-packages\llama_index\indices\vector_store\base.py", line 196, in _add_nodes_to_index
    nodes_batch = self._get_node_with_embedding(nodes_batch, show_progress)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\vector_store\base.py", line 104, in _get_node_with_embedding
    id_to_embed_map = embed_nodes(
                      ^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\indices\utils.py", line 137, in embed_nodes
    new_embeddings = embed_model.get_text_embedding_batch(
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\core\embeddings\base.py", line 256, in get_text_embedding_batch
    embeddings = self._get_text_embeddings(cur_batch)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\core\embeddings\base.py", line 183, in _get_text_embeddings
    return [self._get_text_embedding(text) for text in texts]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\llama_index\core\embeddings\base.py", line 183, in <listcomp>
    return [self._get_text_embedding(text) for text in texts]
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\embedding.py", line 67, in _get_text_embedding
    return self._get_query_embedding(text)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\autollm\auto\embedding.py", line 41, in _get_query_embedding
    response = lite_embedding(model=self.model, input=[query])
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 3421, in wrapper
    raise e
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 3314, in wrapper
    result = original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\main.py", line 2947, in embedding
    model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(
                                                            ^^^^^^^^^^^^^^^^^
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 6938, in get_llm_provider
    raise e
  File "C:\Python311\Lib\site-packages\litellm\utils.py", line 6915, in get_llm_provider
    raise litellm.exceptions.BadRequestError(  # type: ignore
litellm.exceptions.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=default
 Pass model as E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/starcoder',..)` Learn more: https://docs.litellm.ai/docs/providers

Trying to use huggingface directly gives the following, which is fixed in a later version of litellm (August 2024) and is incompatible:

embed_model="huggingface/intfloat/multilingual-e5-small",
llm_api_base = "https://my-endpoint.huggingface.cloud",

Input should be a valid dictionary or instance of SentenceSimilarityInputsCheck