Rename NeMo Retriever references to Nemotron

Dockerfile

@@ -8,11 +8,11 @@ ENV TORCH_CUDA_ARCH_LIST=${TORCH_CUDA_ARCH_LIST}
 RUN --mount=type=cache,target=/root/.cache/pip \
     pip install -U pip hatchling "setuptools>=68" --root-user-action ignore
 
-COPY nemo-retriever-ocr /workspace/nemo-retriever-ocr
-WORKDIR /workspace/nemo-retriever-ocr
+COPY nemotron-ocr /workspace/nemotron-ocr
+WORKDIR /workspace/nemotron-ocr
 
 # Ensure no prebuilt binaries/artifacts from the host are present
-RUN rm -f src/nemo_retriever_ocr_cpp/*.so || true \
+RUN rm -f src/nemotron_ocr_cpp/*.so || true \
     && rm -rf build/ dist/
 
 RUN --mount=type=cache,target=/root/.cache/pip \

README.md

@@ -16,7 +16,7 @@ tags:
 - ingestion
 ---
 
-# NeMo Retriever OCR v1
+# Nemotron OCR v1
 
 ## **Model Overview**
 
@@ -27,15 +27,15 @@ tags:
 
 ### **Description**
 
-The NeMo Retriever OCR v1 model is a state-of-the-art text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images. It integrates three core neural network modules: a detector for text region localization, a recognizer for transcription of detected regions, and a relational model for layout and structure analysis.
+The Nemotron OCR v1 model is a state-of-the-art text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images. It integrates three core neural network modules: a detector for text region localization, a recognizer for transcription of detected regions, and a relational model for layout and structure analysis.
 
-This model is optimized for a wide variety of OCR tasks, including multi-line, multi-block, and natural scene text, and it supports advanced reading order analysis via its relational model component. NeMo Retriever OCR v1 has been developed to be production-ready and commercially usable, with a focus on speed and accuracy on both document and natural scene images.
+This model is optimized for a wide variety of OCR tasks, including multi-line, multi-block, and natural scene text, and it supports advanced reading order analysis via its relational model component. Nemotron OCR v1 has been developed to be production-ready and commercially usable, with a focus on speed and accuracy on both document and natural scene images.
 
-The NeMo Retriever OCR v1 model is part of the NVIDIA NeMo Retriever collection of NIM microservices, which provides state-of-the-art, commercially-ready models and microservices optimized for the lowest latency and highest throughput. It features a production-ready information retrieval pipeline with enterprise support. The models that form the core of this solution have been trained using responsibly selected, auditable data sources. With multiple pre-trained models available as starting points, developers can readily customize them for domain-specific use cases, such as information technology, human resource help assistants, and research & development research assistants.
+The Nemotron OCR v1 model is part of the NVIDIA NeMo Retriever collection of NIM microservices, which provides state-of-the-art, commercially-ready models and microservices optimized for the lowest latency and highest throughput. It features a production-ready information retrieval pipeline with enterprise support. The models that form the core of this solution have been trained using responsibly selected, auditable data sources. With multiple pre-trained models available as starting points, developers can readily customize them for domain-specific use cases, such as information technology, human resource help assistants, and research & development research assistants.
 
 This model is ready for commercial use.
 
-We are excited to announce the open sourcing of this commercial model. For users interested in deploying this model in production environments, it is also available via the model API in NVIDIA Inference Microservices (NIM) at [nemoretriever-ocr-v1](https://build.nvidia.com/nvidia/nemoretriever-ocr-v1).
+We are excited to announce the open sourcing of this commercial model. For users interested in deploying this model in production environments, it is also available via the model API in NVIDIA Inference Microservices (NIM) at [nemotron-ocr-v1](https://build.nvidia.com/nvidia/nemotron-ocr-v1).
 
 ### **License/Terms of use**
 
@@ -57,11 +57,11 @@ Global
 
 ### Use Case
 
-The **NeMo Retriever OCR v1** model is designed for high-accuracy and high-speed extraction of textual information from images, making it ideal for powering multimodal retrieval systems, Retrieval-Augmented Generation (RAG) pipelines, and agentic applications that require seamless integration of visual and language understanding. Its robust performance and efficiency make it an excellent choice for next-generation AI systems that demand both precision and scalability across diverse real-world content.
+The **Nemotron OCR v1** model is designed for high-accuracy and high-speed extraction of textual information from images, making it ideal for powering multimodal retrieval systems, Retrieval-Augmented Generation (RAG) pipelines, and agentic applications that require seamless integration of visual and language understanding. Its robust performance and efficiency make it an excellent choice for next-generation AI systems that demand both precision and scalability across diverse real-world content.
 
 ### Release Date
 
-10/23/2025 via https://huggingface.co/nvidia/nemoretriever-ocr-v1
+10/23/2025 via https://huggingface.co/nvidia/nemotron-ocr-v1
 
 ### References
 
@@ -71,7 +71,7 @@ The **NeMo Retriever OCR v1** model is designed for high-accuracy and high-speed
 
 **Architecture Type:** Hybrid detector–recognizer with document-level relational modeling
 
-The NeMo Retriever OCR v1 model integrates three specialized neural components:
+The Nemotron OCR v1 model integrates three specialized neural components:
 
 - **Text Detector:** Utilizes a RegNetY-8GF convolutional backbone for high-accuracy localization of text regions within images.
 - **Text Recognizer:** Employs a Transformer-based sequence recognizer to transcribe text from detected regions, supporting variable word and line lengths.
@@ -163,11 +163,11 @@ git lfs install
 ```
 - Using https
 ```
-git clone https://huggingface.co/nvidia/nemoretriever-ocr-v1
+git clone https://huggingface.co/nvidia/nemotron-ocr-v1
 ```
 - Or using ssh
 ```
-git clone git@hf.co:nvidia/nemoretriever-ocr-v1
+git clone git@hf.co:nvidia/nemotron-ocr-v1
 ```
 
 2. Installation
@@ -179,7 +179,7 @@ git clone git@hf.co:nvidia/nemoretriever-ocr-v1
 - Run the following command to install the package:
 
 ```bash
-cd nemo-retriever-ocr
+cd nemotron-ocr
 pip install hatchling
 pip install -v .
 ```
@@ -197,7 +197,7 @@ docker run --rm --gpus all nvcr.io/nvidia/pytorch:25.09-py3 nvidia-smi
 - From the repo root, bring up the service to run the example against the provided image `ocr-example-image.png`:
 
 ```bash
-docker compose run --rm nemo-retriever-ocr \
+docker compose run --rm nemotron-ocr \
   bash -lc "python example.py ocr-example-input-1.png --merge-level paragraph"
 ```
 
@@ -212,7 +212,7 @@ Output is saved next to your input image as `<name>-annotated.<ext>` on the host
 3. Run the model using the following code:
 
 ```python
-from nemo_retriever_ocr.inference.pipeline import NemoRetrieverOCR
+from nemotron_ocr.inference.pipeline import NemoRetrieverOCR
 
 ocr = NemoRetrieverOCR()
 
@@ -230,7 +230,7 @@ for pred in predictions:
 ### Software Integration
 
 **Runtime Engine(s):**
-- **NeMo Retriever Page Elements v3** NIM
+- **NeMo Nemotron OCR V1** NIM
 
 
 **Supported Hardware Microarchitecture Compatibility [List in Alphabetic Order]:**
@@ -247,7 +247,7 @@ This AI model can be embedded as an Application Programming Interface (API) call
 
 ## Model Version(s):
 
-* `nemoretriever-ocr-v1`
+* `nemotron-ocr-v1`
 
 ## **Training and Evaluation Datasets:**
 
@@ -267,7 +267,7 @@ The model is trained on a large-scale, curated mix of public and proprietary OCR
 
 ### **Evaluation Datasets**
 
-The NeMo Retriever OCR v1 model is evaluated on several NVIDIA internal datasets for various tasks, such as pure OCR, table content extraction, and document retrieval.
+The Nemotron OCR v1 model is evaluated on several NVIDIA internal datasets for various tasks, such as pure OCR, table content extraction, and document retrieval.
 
 **Data Collection Method:** Hybrid (Automated, Human, Synthetic)<br>
 **Labeling Method:** Hybrid (Automated, Human, Synthetic)<br>
@@ -275,9 +275,9 @@ The NeMo Retriever OCR v1 model is evaluated on several NVIDIA internal datasets
 
 ### **Evaluation Results**
 
-We benchmarked NeMo Retriever OCR v1 on internal evaluation datasets against PaddleOCR on various tasks, such as pure OCR (Character Error Rate), table content extraction (TEDS), and document retrieval (Recall@5).
+We benchmarked Nemotron OCR v1 on internal evaluation datasets against PaddleOCR on various tasks, such as pure OCR (Character Error Rate), table content extraction (TEDS), and document retrieval (Recall@5).
 
-| Metric                                   | NeMo Retriever OCR v1 | PaddleOCR | Net change |
+| Metric                                   | Nemotron OCR v1 | PaddleOCR | Net change |
 |-------------------------------------------|--------------------|-----------|-----------------|
 | Character Error Rate                      | 0.1633             | 0.2029    | -19.5% ✔️         |
 | Bag-of-character Error Rate               | 0.0453             | 0.0512    | -11.5% ✔️         |

docker-compose.yaml

@@ -1,5 +1,5 @@
 services:
-  nemo-retriever-ocr:
+  nemotron-ocr:
     build:
       context: .
       dockerfile: Dockerfile

example.py

@@ -4,7 +4,7 @@
 
 import argparse
 
-from nemo_retriever_ocr.inference.pipeline import NemoRetrieverOCR
+from nemotron_ocr.inference.pipeline import NemoRetrieverOCR
 
 
 def main(image_path, merge_level, no_visualize, model_dir):