update model card, add example

README.md

@@ -20,9 +20,10 @@ tags:
 
 ## **Model Overview**
 
+<!-- 
 ![viz.png](viz.png)
 
-*Preview of the model output on the example image.*
+*Preview of the model output on the example image.* -->
 
 ### **Description**
 
@@ -142,6 +143,18 @@ Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated sys
 
 ### Usage
 
+#### Prerequisites
+
+- **OS**: Linux amd64 with NVIDIA GPU
+- **CUDA**: CUDA Toolkit 12.8 and compatible NVIDIA driver installed (for PyTorch CUDA). Verify with `nvidia-smi`.
+- **Python**: 3.12 (both subpackages require `python = ~3.12`)
+- **Build tools (when building the C++ extension)**:
+  - GCC/G++ with C++17 support
+  - CUDA toolkit headers (for building CUDA kernels)
+  - OpenMP (used by the C++ extension)
+
+
+#### Installation
 The model requires torch, and the custom code available in this repository.
 
 1. Clone the repository
@@ -159,13 +172,61 @@ git clone https://huggingface.co/nvidia/nemoretriever-ocr-v1
 git clone [email protected]:nvidia/nemoretriever-ocr-v1
 ```
 
-2. Install the dependencies
+2. Installation
+
+##### With pip
+
+- Create and activate a Python 3.12 environment (optional)
+
+- Run the following command to install the package:
+
+```bash
+cd nemo-retriever-ocr
+pip install hatchling
+pip install -v .
+```
+
+##### With docker
+
+Run the example end-to-end without installing anything on the host (besides Docker, docker compose, and NVIDIA Container Toolkit):
+
+- Ensure Docker can see your GPU:
+
+```bash
+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 \
+  bash -lc "python example.py ocr-example-input-1.png --merge-level paragraph"
+```
+
+This will:
+- Build an image from the provided `Dockerfile` (based on `nvcr.io/nvidia/pytorch`)
+- Mount the repo at `/workspace`
+- Run `example.py` with model from `checkpoints`
+
+Output is saved next to your input image as `<name>-annotated.<ext>` on the host.
 
-- TODO
 
 3. Run the model using the following code:
 
-- TODO
+```python
+from nemo_retriever_ocr.inference.pipeline import NemoRetrieverOCR
+
+ocr = NemoRetrieverOCR()
+
+predictions = ocr("ocr-example-input-1.png")
+
+for pred in predictions:
+    print(
+        f"  - Text: '{pred['text']}', "
+        f"Confidence: {pred['confidence']:.2f}, "
+        f"Bbox: [left={pred['left']:.4f}, upper={pred['upper']:.4f}, right={pred['right']:.4f}, lower={pred['lower']:.4f}]"
+    )
+```
 
 <!---
 ### Software Integration