← Back to blog![March 2024 Update](/_next/image?url=%2Fblog%2Fcovers%2Fmarch-2024.webp&w=2048&q=90)
![March 2024 Update](/_next/image?url=%2Fblog%2Fcovers%2Fmarch-2024.webp&w=2048&q=90)
March 2024 Update
Apr 12, 2024.
This month, our focus was on enhancing existing features, particularly evaluations and enterprise-specific functionalities.
Improvements in Prompt Menu
- Enhanced search and sorting capabilities.
Model Additions in Playground
- Introduced Mistral Large, Medium, and all Claude models.
Enhancements in Radars
- Fix issues with Radars not running properly ML models.
- Improved PII and Profanity detection across all languages.
Metadata Tracking
- You can now set and filter by the
metadata
field within the dashboard for better data tracking.
Filters Enhancements
- Reintroduced the feedback filter.
- Significantly improved the Users filter, including a new search feature for managing large user bases.
Private API Keys Update
- Temporarily disabled last month for security reasons, Private API keys are now re-enabled. Access them in your Settings page. Documentation improvements are forthcoming.
Evaluations Enhancements
- Enhanced results table for clearer relationships between results.
- Transitioned from models to "Providers" to allow experimentation with parameters like temperature.
- Implemented a queue system for enhanced performance and to address Anthropic rate limiting.
- Added support for running evaluations on large datasets with multiple models.
- Introduced live progress feedback for lengthy evaluations.
- Improved error handling for failed evaluations.
New for Enterprises
- Deployment made simpler with new Helm Charts for Kubernetes and monolithic Docker images.
- Updated our Role Based Access Control system to allow more granular permission settings.
Fixes
- JS SDK: Resolved issues with OpenAI streaming types.
- Addressed cascading feedback issues from thread messages.
- Fixed display issues with parameters such as
maxTokens
.
Are you building an AI product?
Lunary: open-source GenAI monitoring, prompt management, and magic.