You can now configure Guardrails after you have added them to your Library directly in Deployments > Settings for both input and output, giving you full control over live deployments.

You can now add HTTP and JSON Evaluators and Guardrails under the Evaluator tab and add them to your Deployment or Experiment.

The RAGAS Evaluators are now available, providing specialized tools to evaluate retrieval-augmented generation (RAG) workflows. These evaluators make it easy to set up quality checks when integrating a Knowledge Base into a RAG system and can be used in Experiments and Deployments to ensure responses are accurate, relevant, and safe.

Introducing the new Evaluator Library:

LLM-as-a-Judge Enhancements:
We’ve significantly improved our existing LLM-as-a-Judge feature to provide more robust evaluation capabilities and enforce type-safe outputs.

You can now configure Evaluators after you have added them to your Library directly in Deployments > Settings for both input and output, giving you full control over live deployments.

Cache and reuse your LLM outputs for near-instant responses, reduced costs, and consistent results.

Ensure the model’s responses always stick to your JSON Schema. No more missing fields or incorrect values, making your AI applications more reliable and robust.

Introducing the upgraded Claude 3.5 Sonnet and the new Claude 3.5 Haiku. The enhanced Claude 3.5 Sonnet offers comprehensive improvements, especially in coding and tool use, while maintaining the speed and pricing of the previous model. These upgrades make it an excellent choice for complex, multi-step development and planning tasks.

With the improvements to role-based access control (RBAC), it is much easier to assign and change workspace roles in Orq.