Collects documents from Azure Cognitive Search Index, extracts their contents, saves them to a uri folder, and creates an MLIndex yaml file to represent the search index.

Documents collected can then be used in other components without having to query the ACS index again, allowing for a consistent dataset for chunking, data generation, etc.

Version: 0.0.68

Preview

View in Studio: https://ml.azure.com/registries/azureml/components/llm_rag_data_import_acs/version/0.0.68

Name	Description	Type	Default	Optional	Enum
num_docs	Number of documents to import from ACS instance	integer	50
acs_config	Values for connecting to ACS instance. Required keys: 'endpoint', 'endpoint_key_name', 'index_name', 'content_key', 'title_key'. 'content_key' defaults to 'content' and 'title_key' defaults to 'title'	string
use_existing	Use an existing ACS which is already embedded - directly output MLIndex config	string	False		['True', 'False']

Name	Description	Type
output_data	Uri folder containing the documents' content saved as md files	uri_folder
ml_index	Uri folder containing an MLIndex yaml representing the ACS Index. Can be used with azureml-rag package	uri_folder

azureml:llm-rag-embeddings@latest