Skip to content

Python: Honor injected Foundry embedding clients without endpoint settings #9991

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Eduard van Valkenburg (eavanvalkenburg) merged 3 commits into from
Nov 4, 2026
Merged

Python: Honor injected Foundry embedding clients without endpoint settings #9991

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9342a84
Python: Honor injected Foundry embedding clients without endpoint set…
ZedingZhang Nov 2, 2026
b13fd4a
Python: Honor injected embedding clients over explicit project settings
ZedingZhang Nov 3, 2026
6d11349
Python: Preserve lazy project text embeddings with injected image cli…
ZedingZhang Nov 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 11 additions & 3 deletions python/packages/foundry/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,9 +71,17 @@ The client uses the project for authentication and converts a
`https://<resource>.services.ai.azure.com/api/projects/<project>` endpoint to the documented resource-scoped
`https://<resource>.openai.azure.com/openai/v1/` model route. The existing `FOUNDRY_MODELS_ENDPOINT` and
`FOUNDRY_MODELS_API_KEY` configuration remains available for Foundry Models inference endpoints. A Models endpoint is
required for image embedding models. If both project and Models endpoints are configured only through environment
variables, the Models endpoint is retained for backward compatibility; pass `project_endpoint` explicitly to select
the project OpenAI deployment.
required for image embedding models unless an `ImageEmbeddingsClient` is supplied. If both project and Models
endpoints are configured only through environment variables, the Models endpoint is retained for backward
compatibility; pass `project_endpoint` explicitly to select the project OpenAI deployment.

A preconfigured `EmbeddingsClient` or `ImageEmbeddingsClient` can be passed as `text_client` or `image_client`.
The injected client is the transport for that modality and takes precedence over constructor connection settings,
environment settings, and framework defaults, so no endpoint, API key, credential, or Foundry environment is
required for it. `model` and `image_model` keep their usual explicit-argument, environment, then default
resolution. The other modality is created only when a request needs it and enough settings are available.
For example, an injected `image_client` can be combined with project configuration for text embeddings;
the project text transport is initialized only when a request includes text.

## Evaluations

Expand Down
Loading
Loading