components llm_rag_validate_deployments

LLM - Validate Deployments

llm_rag_validate_deployments

Overview

Validates that completion model, embedding model, and Azure Cognitive Search resource deployments is successful and connections works. For default AOAI, it attempts to create the deployments if not valid or present. This validation is done only if customer is using Azure Open AI models or creating an ACS index.

Version: 0.0.50

Tags

Preview

View in Studio: https://ml.azure.com/registries/azureml/components/llm_rag_validate_deployments/version/0.0.50

Inputs

Name	Description	Type	Default	Optional	Enum
llm_config	JSON Configuration for what model to use for question generation. Must contain following keys: 'type' (value must be 'azure_open_ai' or 'azure'), 'model_name' (name of model to use for summary), 'deployment_name' (name of deployment for model), 'temperature' (randomness in response, float from 0 to 1), 'max_tokens' (number of tokens for response).	string	{"type": "azure_open_ai", "model_name": "gpt-35-turbo", "deployment_name": "gpt-35-turbo", "temperature": 0, "max_tokens": 2000}	True
embeddings_model	The model to use to embed data. E.g. 'hugging_face://model/sentence-transformers/all-mpnet-base-v2' or 'azure_open_ai://deployment/{deployment_name}/model/{model_name}'	string		True
check_embeddings	Boolean to inform whether to check the embeddings model deployment or not	string	True		['True', 'False']
check_completion	Boolean to inform whether to check the completion model deployment or not	string	True		['True', 'False']
acs_config	JSON Configuration for the ACS configuration of Azure Search instance to upload embeddings to. Required params: endpoint, index_name	string		True
check_acs	Boolean to inform whether to check the ACS connection associated with acs_config.	string	False	True	['True', 'False']

Outputs

Name	Description	Type
output_data		uri_file

Environment

azureml:llm-rag-embeddings@latest