fix: correct GLiNER model name and skip health check#24
Merged
Conversation
- Rename nvidia/nemotron-pii to nvidia/gliner-pii (correct hosted model name) - Add skip_health_check: true (GLiNER health check fails because DD sends unsupported chat params like temperature/top_p) - Remove temperature/top_p/max_tokens from inference_parameters (GLiNER rejects standard chat completion params)
lipikaramaswamy
approved these changes
Mar 6, 2026
Collaborator
lipikaramaswamy
left a comment
lipikaramaswamy
left a comment
There was a problem hiding this comment.
Looks good. To document, we're skipping health checks because data designer automatically passes params like temperature, etc. which are rejected by this model, despite the model config not listing these params.
andreatgretel
changed the title
andreatgretel
changed the title
andreatgretel
added a commit
that referenced
this pull request
Mar 6, 2026
The health check was failing because temperature/top_p/max_tokens were being sent to GLiNER, which rejects them. Now that those params have been removed (#24), the health check passes and skip_health_check is no longer needed.
2 tasks
andreatgretel
added a commit
that referenced
this pull request
Mar 6, 2026
…EADME - Remove skip_health_check: true from GLiNER config — health check passes now that unsupported params were removed in #24 - Fix README: NVIDIA_API_KEY (not NIM_API_KEY) is the correct env var
lipikaramaswamy
added a commit
that referenced
this pull request
Mar 6, 2026
* chore: remove unnecessary skip_health_check, fix API key env var in README - Remove skip_health_check: true from GLiNER config — health check passes now that unsupported params were removed in #24 - Fix README: NVIDIA_API_KEY (not NIM_API_KEY) is the correct env var * fix: update readme code snippets to match api, missed previously * Update README.md --------- Co-authored-by: lipikaramaswamy <31832945+lipikaramaswamy@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
nvidia/nemotron-piitonvidia/gliner-pii(correct model name on build.nvidia.com)skip_health_check: true— GLiNER's health check fails because DD sends standard chat params (temperature,top_p) that GLiNER rejectstemperature/top_p/max_tokensfrom GLiNER inference parameters — these are unsupported by the GLiNER API and cause 422 errorsTest plan
nvidia/gliner-piiresponds correctly onintegrate.api.nvidia.com