March 2024 Update

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.