[Enhancement] Add support for Chat Template params #52
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Outdated suggestions cannot be applied.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.
🚀 Add support for Chat Template params
✨ Summary
This PR adds support for
chat_template_paramsin model configurations and updates the documentation accordingly.The purpose is to enable dynamic parameter injection into chat templates, allowing more flexible control over model behavior (e.g., reasoning effort).
🛠️ Explain the features implemented:
chat_template_paramsfield inmodel_configuration.mdunder Configuration Properties.custom_models.pyto passchat_template_paramsdynamically during request payload creation.get_chat_formatted_text()to accept and apply**chat_template_params.parametersandchat_template_paramscan be overridden in graph YAML files.⚡ Performance impact (if any):
🧪 How to Test the feature
Steps for reviewers to verify functionality:
chat_template_params, for example:chat_template_paramsin graph_config.yaml to override model configuration YAML file. for example:4.▶️ Run a graph YAML that uses this model.
5. 👀 Observe that the model request payloads include the provided chat template parameters and modify output behavior accordingly.
📸 Screenshots (if applicable)
N/A — documentation-only visual updates and backend enhancements.
✅ Checklist
📝 Notes
This change improves extensibility for models using complex prompt templates.
Backward-compatible — existing configurations remain valid without modification.