Starstruk Logo MarkStarstruk

25.9.0

NVIDIA/NeMo-Retriever25.9.0Sep 17, 2025by sosahi

AI Summary

The NeMo Retriever extraction 25.09 release adds extensive new hardware and software support, including new GPUs, AI models, and customization capabilities for the extraction pipeline.

Key Highlights

  • Added support for RTX Pro 6000 workstation GPU
  • Added support for DGX B200 system
  • Added support for nemoretriever-ocr-v1 model
  • Added support for llama-3.2-nemoretriever-1b-vlm-embed-v1
  • Added support for Llama Nemotron VLM 8b NIM for image captioning
  • Added custom vector database implementation support
  • Added custom Lambda stages support
  • Added support for multiple VLM running via Helm

New Features

  • RTX Pro 6000 hardware support
  • DGX B200 hardware support
  • nemoretriever-ocr-v1 model integration
  • llama-3.2-nemoretriever-1b-vlm-embed-v1 embedding model
  • Llama Nemotron VLM 8b NIM for image captioning
  • Custom vector database operators
  • Custom Lambda pipeline stages
  • Integer, float, boolean, array metadata support for Milvus
  • Multi-VLM support via Helm deployment
  • Ray Logging configuration documentation
  • Multimodal Embedding documentation
  • Library Mode expanded documentation

Full Release Notes

The NeMo Retriever extraction 25.09 release adds new hardware and software support, and other improvements, including the following:

- Add functional support for [RTX Pro 6000](https://www.nvidia.com/en-us/products/workstations/professional-desktop-gpus/rtx-pro-6000/).
- Add functional support for [DGX B200](https://www.nvidia.com/en-us/data-center/dgx-b200/).
- Add support for [nemoretriever-ocr-v1](https://build.nvidia.com/nvidia/nemoretriever-ocr-v1). For details, refer to [Deploy With Docker Compose (Self-Hosted)](https://docs.nvidia.com/nemo/retriever/latest/extraction/quickstart-guide/) and [NV-Ingest Helm Charts](https://github.com/nkmcalli/nv-ingest/tree/main/helm).
- Add support for [llama-3.2-nemoretriever-1b-vlm-embed-v1](https://build.nvidia.com/nvidia/llama-3_2-nemoretriever-1b-vlm-embed-v1).
- Add support for Llama Nemotron VLM 8b NIM for image captioning. For details, refer to [Extract Captions from Images](https://docs.nvidia.com/nemo/retriever/latest/extraction/nv-ingest-python-api/#extract-captions-from-images).
- Add support for custom vector database implementations. For details, refer to [Build a Custom Vector Database Operator](https://github.com/NVIDIA/nv-ingest/blob/main/examples/building_vdb_operator.ipynb).
- Add support for custom Lambda stages. For details, refer to [Add User-defined Stages to Your NeMo Retriever Extraction Pipeline](https://docs.nvidia.com/nemo/retriever/latest/extraction/user-defined-stages/).
- Expanded documentation for [Library Mode](https://docs.nvidia.com/nemo/retriever/latest/extraction/quickstart-library-mode/).
- New documentation [Configure Ray Logging](https://docs.nvidia.com/nemo/retriever/latest/extraction/ray-logging/).
- New documentation [Use Multimodal Embedding](https://docs.nvidia.com/nemo/retriever/latest/extraction/vlm-embed/).
- Add support for Integer, float, boolean, and array in custom metadata during Milvus entity creation.
- Add support for running more than one VLM at a time by using Helm. For details, refer to [NV-Ingest Helm Charts](https://github.com/nkmcalli/nv-ingest/tree/main/helm).

**Known Issues**

The following are the known issues for this release:

- A10G and L40S are not supported. For details, refer to [Support Matrix](https://docs.nvidia.com/nemo/retriever/latest/extraction/support-matrix/).
- `nemoretriever-parse` is not supported on RTX Pro 6000 or B200. For details, refer to [Support Matrix](https://docs.nvidia.com/nemo/retriever/latest/extraction/support-matrix/).
- The NeMo Retriever extraction pipeline does not support ingestion of batches that include individual files greater than approximately 400MB.