----> 4 Settings.llm = Gemini()
5 Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")

File c:\Users\Maneesh\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_index\llms\gemini\base.py:141, in Gemini.init(self, api_key, model, temperature, max_tokens, generation_config, safety_settings, callback_manager, api_base, transport, model_name, default_headers, generate_kwargs) 138 # Explicitly passed args take precedence over the generation_config. 139 final_gen_config = {"temperature": temperature, base_gen_config}
--> 141 self._model = genai.GenerativeModel(
142 model_name=model,
143 generation_config=final_gen_config,
144 safety_settings=safety_settings,
145 )
147 self._model_meta = genai.get_model(model)
149 supported_methods = self._model_meta.supported_generation_methods

File c:\Users\Maneesh\AppData\Local\Programs\Python\Python312\Lib\site-packages\pydantic\main.py:837, in BaseModel.setattr(self, name, value)
832 raise AttributeError(
833 f'{name!r} is a ClassVar of {self.__class__.__name__} and cannot be set on an instance. '
834 f'If you want to set a value on the class, use {self.__class__.__name__}.{name} = value.'
835 )
836 elif not _fields.is_valid_field_name(name):
...
826 else:
827 # this is the current error
828 raise AttributeError(f'{type(self).name!r} object has no attribute {item!r}')

AttributeError: 'Gemini' object has no attribute 'pydantic_private'

ValidationError: 1 validation error for ParsingModel[List[llama_cloud.types.pipeline.Pipeline]]
root -> 0 -> eval_parameters -> llm_model
value is not a valid enumeration member; permitted: 'GPT_3_5_TURBO', 'GPT_4', 'GPT_4_TURBO' (type=type_error.enum; enum_values=[<SupportedEvalLlmModelNames.GPT_3_5_TURBO: 'GPT_3_5_TURBO'>, <SupportedEvalLlmModelNames.GPT_4: 'GPT_4'>, <SupportedEvalLlmModelNames.GPT_4_TURBO: 'GPT_4_TURBO'>])

from llama_index.indices.managed.llama_cloud import LlamaCloudIndex
from llama_index.llms.openai import OpenAI

from llama_index.core.vector_stores import (
    MetadataFilter,
    MetadataFilters,
    FilterOperator,
)

index = LlamaCloudIndex(
name="insurance-detail", 
project_name="policy_gpt",
organization_id="a1b3bd00-6958-4b47-bd51-f4c85ad7f8de",
api_key="llx-xxxxxxxxxxxxxi"
)
    
llm = OpenAI(model="gpt-4o-mini")
#  create metadata filter 
filters = MetadataFilters(
    filters=[
        MetadataFilter(
            # key="file_name", operator=FilterOperator.EQ, value="HDFC"
            key="file_name", operator=FilterOperator.EQ, value="HDFC ERGO hospital-daily-cash-rider HDHHLIP21344V02202.pdf"
            
        ),
    ]
)

# configure retriever
retriever = index.as_retriever(
  dense_similarity_top_k=10,
  sparse_similarity_top_k=3,
#   alpha=1.0,
#   llm=llm,
  enable_reranking=True, 
  rerank_top_n=3,
  filters=filters,
)
nodes = retriever.retrieve("what are the excultions in my policy")