Agentic evaluations Benchmark container

Overview

This image is a container to run benchmarks for Agentic evaluations targets. The NeMo Evaluator microservice uses this container to compute metrics for agentic evaluations. As part of the evaluation, the container downloads a dataset, performs inference, and uploads the results and logs to the datastore.

To get started with NeMo Evaluator, refer to Evaluation Tutorials.

Note: Use, distribution or deployment of this microservice in production requires an NVIDIA AI Enterprise License.

Governing Terms

The software and materials are governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products.