Skip to content

infer_deployment function broken #32170

Open
@davidADSP

Description

@davidADSP
  • Package Name: azureml-rag[faiss,document_parsing,cognitive_search,hugging_face]
  • Package Version: 0.2.2
  • Operating System: Linux
  • Python Version: 3.10

Describe the bug
A clear and concise description of what the bug is.

The infer_deployment function (from azureml.rag.utils.deployment import infer_deployment) contains reference to Deployment.list which isn't a valid method for the Deployment class from the openai package.

Digging into this a bit more - it's because there is no /deployments route here:

https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2023-07-01-preview/azureopenai.json
or
https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-07-01-preview/inference.json

However, there is a /models route.

So for example,
https://aoairesourcename.openai.azure.com/openai/models?api-version=2023-07-01-preview
will work but
https://aoairesourcename.openai.azure.com/openai/deployments?api-version=2023-07-01-preview
will not.

To Reproduce
Steps to reproduce the behavior:

This will always fail to retrieve any deployments

from azureml.rag.utils.deployment import infer_deployment

aoai_embedding_model_name = "text-embedding-ada-002"
try:
    aoai_embedding_deployment_name = infer_deployment(
        aoai_connection, aoai_embedding_model_name
    )
    print(
        f"Deployment name in AOAI workspace for model '{aoai_embedding_model_name}' is '{aoai_embedding_deployment_name}'"
    )
except Exception as e:
    print(f"Deployment name in AOAI workspace for model '{aoai_embedding_model_name}' is not found.")
    print(
        f"Please create a deployment for this model by following the deploy instructions on the resource page for '{aoai_connection['properties']['target']}' in Azure Portal."
    )

e.g. from here
https://github.com/Azure/azureml-examples/blob/main/sdk/python/generative-ai/rag/notebooks/mlindex_with_testgen_autoprompt.ipynb

Expected behavior
A list of deployments should be retrieved

Screenshots
If applicable, add screenshots to help explain your problem.

Additional context
Add any other context about the problem here.

Metadata

Metadata

Assignees

Labels

ARMClientThis issue points to a problem in the data-plane of the library.Machine LearningService AttentionWorkflow: This issue is responsible by Azure service team.bugThis issue requires a change to an existing behavior in the product in order to be resolved.customer-reportedIssues that are reported by GitHub users external to the Azure organization.needs-team-attentionWorkflow: This issue needs attention from Azure service team or SDK team

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions