← Back to changelog

September 1, 2026

Build multi-message prompts and evaluate multi-modal inputs

Tobias Wochinger

Two new capabilities for LLM-as-a-Judge evaluators.

LLM-as-a-Judge evaluators now support two new capabilities:

• LLM-as-a-Judge with multiple prompt messages: Use a System message for the evaluation criteria, a User message for the content to evaluate, and an Assistant message to show an example result.
• LLM-as-a-Judge with multi-modal inputs: Evaluate images, audio, video, PDFs, or text files captured in your observations. The selected LLM-as-a-Judge model and provider must support the media type.

Either capability can be used on its own. Self-hosters can configure media delivery and size limits with the LANGFUSE_EVALUATOR_MEDIA_* environment variables.

Learn more