Python GenAI client v2.13.0 adds custom vocabulary and model selection
sdkaiengineer
feature patch
The Python GenAI client library has been updated to version 2.13.0, introducing a `custom_vocabulary` field for `BidiGenerateContentSetup` and a model selector feature. These enhancements improve customization and control for developers working with generative AI models. The update is available now and impacts users integrating AI capabilities into their Python applications.
- →A new field custom_vocabulary is added to message .google.cloud.aiplatform.v1beta1.BidiGenerateContentSetup
- →Add model selector
- →Add queued status to interaction proto
- →Make ASR fields public in v1main and Interactions
- →Support mTLS in custom client using google auth mtls.get_default_ssl_context
Features (5) ›
- A new field custom_vocabulary is added to message .google.cloud.aiplatform.v1beta1.BidiGenerateContentSetup
- Add model selector
- interaction-api Add queued status to interaction proto
- Make ASR fields public in v1main and Interactions
- Support mTLS in custom client using google auth mtls.get_default_ssl_context
Maintenance (1) ›
- Regenerate docs for 2.11.0 and 2.12.0
Read the original announcement →
https://github.com/googleapis/python-genai/releases/tag/v2.13.0
Related releases
- Vibe-coded schedule app built with Gemini simplifies mornings Gemini Blog ·
- Gemini App Updates: July Drop Gemini Blog ·
- Gemini Spark integrates Chrome for automated web errands Gemini Blog ·
- Gemini Robotics ER 2 Enhances Embodied Reasoning for Robots Gemini Blog ·
- Python GenAI SDK v2.16.0 adds environment resource, Maps tool support Gemini Python SDK Releases ·
- Google Python GenAI SDK Adds Audio Transcription and Enterprise Mode Gemini Python SDK Releases ·