Release Notes for NVIDIA NIM for Table Extraction#

This documentation contains the release notes for NVIDIA NIM for Table Extraction.

Release 1.1.0-rtx (Beta)#

Summary#

This is a public beta release of the NVIDIA NIM for Table Extraction. This release contains the following changes:

  • Added support for GeForce RTX 4090, NVIDIA RTX 6000 Ada Generation, GeForce RTX 5080, and GeForce RTX 5090 for the PaddleOCR NIM.

  • Added the NIM_TRITON_MODEL_BATCH_SIZE environment variable.

Known Issues#

  • The list-model-profiles command incorrectly includes incompatible model profiles. Select the profile that matches your hardware configuration.

Release 1.0.0#

Summary#

This is a General Availability release of the NVIDIA NIM for Table Extraction. This release contains the following changes:

  • Updates the /v1/infer endpoint request and response JSON schemas. The new output schema provides bounding boxes and confidence scores for each text detection. See the API Reference for more details.

Table Detection Model Supported#

  • PaddleOCR

Release 0.2.1#

Summary#

This is an Early Access release of the NVIDIA NIM for Table Extraction. This release contains the following fixes:

  • Fixes bug where NIM_HTTP_TRITON_PORT was not properly setting the port number.

  • Fixes the /v1/manifest API described in the API Reference returning an empty result instead of the manifest file.

  • Returns an emtpy string instead of “nan” when no text is detected in an image

Table Detection Model Supported#

  • PaddleOCR

Release 0.2.0#

Summary#

This is the second Early Access release of the NVIDIA NIM for Table Extraction. This release contains the following changes:

  • Added validation for the base64 decoding format and improved the error message for when the format is incorrect.

  • Improved startup performance of the NIM.

  • Added FP16 optimized TRT engines for A100, H100, A10G, L40S.

Table Detection Model Supported#

  • PaddleOCR

Known Issues#

  • The /v1/manifest API described in the API Reference returns an empty result instead of the manifest file.

Release 0.1.0#

Summary#

This is the first Early Access release of the NVIDIA NIM for Table Extraction.

Table Detection Model Supported#

  • PaddleOCR

Known Issues#

  • If the input image_url does not match the expected format described in the API Reference, the runtime returns an error message, such as {"error": "Incorrect padding"}, indicating what format error occurred.

On this page