components llm_rag_image_embed_index

LLM - Embedding images with Florence

llm_rag_image_embed_index

Overview

Embeds input images and stores it in Azure Cognitive Search index with metadata using Florence embedding resource. MLIndex is stored to output_path.

Version: 0.0.17

Tags

Preview

View in Studio: https://ml.azure.com/registries/azureml/components/llm_rag_image_embed_index/version/0.0.17

Inputs

Name	Description	Type	Default	Optional	Enum
input_path	The input uri_folder containing a set of images and json metadata.	uri_folder		False
embedding_connection_id	The input connection id to the Azure cognitive vision resource for florence embedding.	string		False
acs_connection_id	The input connection id to the Azure Cognitive Search resource.	string		False
search_index_name	The index name for storing the images embeddings and metadata.	string

Outputs

Name	Description	Type
output_path	Where to store the output MLIndex.	uri_folder

Environment

azureml:llm-rag-embeddings@latest