Nemotron Rerank

NVIDIA Nemotron-3.5 Rerank NIM provides GPU-accelerated inference for document reranking in retrieval-augmented generation (RAG) and agentic retrieval applications. It evaluates candidate documents against a text query and returns relevance scores that applications can use to prioritize the most useful context.

Reranking follows an initial retrieval stage performed by an embedding model or search system. By examining query-document pairs in greater detail, the reranker refines the candidate ordering before documents are passed to a downstream application or language model. Depending on the selected model, inputs can include text passages, document-page images, or combined text-and-image content, such as pages containing charts, tables, and infographics.

The NIM packages the inference runtime and serving APIs for deployment on supported NVIDIA GPU systems. Model weights are managed separately from the container and loaded at startup. Supported models, input formats, languages, hardware, precision options, and configuration requirements vary by release.

Getting Started

See the NeMo Retriever Reranking NIM documentation for deployment instructions, configuration, and API examples.

Security Vulnerabilities in Open Source Packages

Please review the Security Scanning tab on NGC to view the latest security scan results.

For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Get Help

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

NVIDIA Developer Community Forum

Get access to community knowledge base articles and support cases (https://forums.developer.nvidia.com/)

Governing Terms

The NIM container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products.

You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.