Skip to content

[integrations][java][python] Apply Azure OpenAI native structured output #930

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
wenjin272 merged 4 commits into from
Aug 4, 2026
Merged

[integrations][java][python] Apply Azure OpenAI native structured output #930

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
57012ab
[integrations][python] Apply Azure OpenAI native structured output
weiqingy Jul 27, 2026
53bb169
[integrations][java] Apply Azure OpenAI native structured output
weiqingy Jul 27, 2026
62c6a1d
[integrations][java][python] Narrow the Azure native structured outpu…
weiqingy Aug 3, 2026
4d60405
[integrations][java][python] Mark the dormant NATIVE silent drop in t…
weiqingy Aug 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
325 changes: 263 additions & 62 deletions ...rg/apache/flink/agents/integrations/chatmodels/openai/AzureOpenAIChatModelConnection.java
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 3 additions & 1 deletion ...ava/org/apache/flink/agents/integrations/chatmodels/openai/AzureOpenAIChatModelSetup.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,9 @@
*
* <p>{@code model} (inherited from {@link BaseChatModelSetup}) is the Azure deployment name, not
* the underlying OpenAI model name. The underlying model name can be supplied via {@code
* model_of_azure_deployment} and is used solely for token-metrics tracking.
* model_of_azure_deployment}. It labels token-usage metrics, and it is also the name that decides
* whether a request can carry a native structured-output schema, since the deployment name carries
* no model information. Leaving it unset keeps requests on the prompt-engineering fallback.
*
* <p>Example usage:
*
Expand Down
Loading
Loading