In AzureAISearch, there seems to be able to customize filterable fields using the metadata_fields, but it seems to be hard coded somehow like the "author" and "director", and then the topic field is a defined data type?
Did I missunderstand wrong or if there could be more example to show how to extract and populate these metadata for a list of Documents? Thank you!
metadata_fields = {
"author": "author",
"theme": ("topic", MetadataIndexFieldType.STRING),
"director": "director",
}
Creating an Azure AI Search Vector Store
vector_store = AzureAISearchVectorStore(
search_or_index_client=index_client,
filterable_metadata_field_keys=metadata_fields,
hidden_field_keys=["embedding"],
index_name=index_name,
index_management=IndexManagement.CREATE_IF_NOT_EXISTS,
id_field_key="id",
chunk_field_key="chunk",
embedding_field_key="embedding",
embedding_dimensionality=1536,
metadata_string_field_key="metadata",
doc_id_field_key="doc_id",
language_analyzer="en.lucene",
vector_algorithm_type="exhaustiveKnn",
semantic_configuration_name="mySemanticConfig",
)
https://docs.llamaindex.ai/en/stable/api_reference/storage/vector_store/azureaisearch/