Update readme file

README.md

@@ -1,15 +1,22 @@
 # OpenVINO Model API
 
-Model API is a set of wrapper classes for particular tasks and model architectures, simplifying data preprocess and postprocess as well as routine procedures (model loading, asynchronous execution, etc.). It is aimed at simplifying end-to-end model inference for different deployment scenarious, including local execution and serving. The Model API is based on the OpenVINO inference API.
+Model API is a set of wrapper classes for particular tasks and model architectures, simplifying data preprocess and postprocess as well as routine procedures (model loading, asynchronous execution, etc.). It is aimed at simplifying end-to-end model inference for different deployment scenarios, including local execution and serving. The Model API is based on the OpenVINO inference API.
 
 ## How it works
 
 Model API searches for additional information required for model inference, data, pre/postprocessing, label names, etc. directly in OpenVINO Intermediate Representation. This information is used to prepare the inference data, process and output the inference results in a human-readable format.
 
+Currently, ModelAPI supports models trained in [OpenVINO Training Extensions](https://github.com/openvinotoolkit/training_extensions) framework.
+Training Extensions embed all the metadata required for inference into model file. For models coming from other than Training Extensions frameworks metadata generation step is required before using ModelAPI.
+
+## Supported model formats
+
+- [OpenVINO IR](https://docs.openvino.ai/2025/documentation/openvino-ir-format.html)
+- [ONNX](https://onnx.ai)
+
 ## Features
 
 - Python and C++ API
-- Automatic prefetch of public models from [OpenVINO Model Zoo](https://github.com/openvinotoolkit/open_model_zoo) (Python only)
 - Synchronous and asynchronous inference
 - Local inference and serving through the rest API (Python only)
 - Model preprocessing embedding for faster inference
@@ -18,17 +25,15 @@ Model API searches for additional information required for model inference, data
 
 ### Python
 
-- Clone this repository
-- Navigate to `model_api/python` folder
-- Run `pip install .`
+`pip install openvino-model-api`
 
 ### C++
 
 - Install dependencies. For installation on Ubuntu, you can use the following script:
 
   ```bash
-  chmod +x model_api/cpp/install_dependencies.sh
-  sudo model_api/cpp/install_dependencies.sh
+  chmod +x src/cpp/install_dependencies.sh
+  sudo src/cpp/install_dependencies.sh
   ```
 
 - Build library:
@@ -45,44 +50,48 @@ Model API searches for additional information required for model inference, data
   cmake ../model_api/cpp -DOpenCV_DIR=<OpenCV cmake dir> -DOpenVINO_DIR=<OpenVINO cmake dir>
   ```
 
-  - Build:
+`OpenCV` and `OpenVINO` locations are optional. In most cases, system these dependencies are discovered by cmake without extra guidance.
 
-  ```bash
-  cmake --build . -j
-  ```
+- Build:
 
-  - To build a `.tar.gz` package with the library, run:
+```bash
+cmake --build . -j
+```
 
-  ```bash
-  cmake --build . --target package -j
-  ```
+- To build a `.tar.gz` package with the library, run:
+
+```bash
+cmake --build . --target package -j
+```
 
 ## Usage
 
 ### Python
 
 ```python
-from model_api.models import DetectionModel
+from model_api.models import Model
 
-# Create a model (downloaded and cached automatically for OpenVINO Model Zoo models)
-# Use URL to work with served model, e.g. "localhost:9000/models/ssdlite_mobilenet_v2"
-ssd = DetectionModel.create_model("ssdlite_mobilenet_v2")
+# Create a model wrapper from a compatible model generated by OpenVINO Training Extensions
+# Use URL to work with OVMS-served model, e.g. "localhost:9000/models/ssdlite_mobilenet_v2"
+model = Model.create_model("model.xml")
 
 # Run synchronous inference locally
-detections = ssd(image)  # image is numpy.ndarray
+result = model(image)  # image is numpy.ndarray
 
-# Print the list of Detection objects with box coordinates, confidence and label string
-print(f"Detection results: {detections}")
+# Print results in model-specific format
+print(f"Inference result: {result}")
 ```
 
 ### C++
 
+In C++ we have to specify model type in advance, let's set it to detection model.
+
 ```cpp
 #include <models/detection_model.h>
 #include <models/results.h>
 
-// Load the model fetched using Python API
-auto model = DetectionModel::create_model("~/.cache/omz/public/ssdlite_mobilenet_v2/FP16/ssdlite_mobilenet_v2.xml");
+// Load the model
+auto model = Model::create_model("model.xml");
 
 // Run synchronous inference locally
 auto result = model->infer(image); // image is cv::Mat
@@ -125,41 +134,3 @@ auto model = DetectionModel::create_model(adapter);
 ```
 
 For more details please refer to the [examples](https://github.com/openvinotoolkit/model_api/tree/master/examples) of this project.
-
-## Supported models
-
-### Python
-
-- Image Classification:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#classification-models)
-- Object Detection:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#object-detection-models):
-    - SSD-based models (e.g. "ssdlite_mobilenet_v2", etc.)
-    - YOLO-based models (e.g. "yolov3", "yolov4", etc.)
-    - CTPN: "ctpn"
-    - DETR: "detr-resnet50"
-    - CenterNet: "ctdet_coco_dlav0_512"
-    - FaceBoxes: "faceboxes-pytorch"
-    - RetinaFace: "retinaface-resnet50-pytorch"
-    - Ultra Lightweight Face Detection: "ultra-lightweight-face-detection-rfb-320" and "ultra-lightweight-face-detection-slim-320"
-    - NanoDet with ShuffleNetV2: "nanodet-m-1.5x-416"
-    - NanoDet Plus with ShuffleNetV2: "nanodet-plus-m-1.5x-416"
-- Semantic Segmentation:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#semantic-segmentation-models)
-- Instance Segmentation:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#instance-segmentation-models)
-
-### C++
-
-- Image Classification:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#classification-models)
-- Object Detection:
-  - SSD-based models (e.g. "ssdlite_mobilenet_v2", etc.)
-    - YOLO-based models (e.g. "yolov3", "yolov4", etc.)
-    - CenterNet: "ctdet_coco_dlav0_512"
-    - FaceBoxes: "faceboxes-pytorch"
-    - RetinaFace: "retinaface-resnet50-pytorch"
-- Semantic Segmentation:
-  - [OpenVINO Model Zoo models](https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/index.md#semantic-segmentation-models)
-
-[Model configuration](https://github.com/openvinotoolkit/model_api/blob/master/docs/model-configuration.md) discusses possible configurations.

docs/source/conf.py

@@ -10,15 +10,15 @@
 from pathlib import Path
 
 # Define the path to your module using Path
-module_path = Path(__file__).parent.parent / "model_api" / "python"
+module_path = Path(__file__).parent.parent / "src" / "python"
 
 # Insert the path to sys.path
 sys.path.insert(0, str(module_path.resolve()))
 
-project = "InferenceSDK"
-copyright = "2024, Intel OpenVINO"
-author = "Intel OpenVINO"
-release = "2024"
+project = "ModelAPI"
+copyright = "2025, Intel"
+author = "Intel"
+release = "2025"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration

docs/source/cpp/models/anomaly_model.md

@@ -1,6 +1,6 @@
 # Anomaly Model
 
-The `AnomalyModel` is a generic OpenVINO model that aims to provide a single interface for all the exported models based on [Anomalib](https://github.com/openvinotoolkit/anomalib).
+The `AnomalyModel` is a generic OpenVINO model that aims to provide a single interface for all the exported models based on [Anomalib](https://github.com/open-edge-platform/anomalib).
 
 Currently, the `AnomalyModel` supports the following models:
 

docs/source/python/models/anomaly.md

@@ -1,6 +1,6 @@
 # Anomaly
 
-The `AnomalyModel` is a generic OpenVINO model that aims to provide a single interface for all the exported models based on [Anomalib](https://github.com/openvinotoolkit/anomalib).
+The `AnomalyModel` is a generic OpenVINO model that aims to provide a single interface for all the exported models based on [Anomalib](https://github.com/open-edge-platform/anomalib).
 
 Currently, the `AnomalyModel` supports the following models:
 

src/python/docs/visual_prompting.md

@@ -58,5 +58,5 @@ Decoder OV model should have the following named inputs:
 
 ## How to use
 
-See demos: [VPT](https://github.com/openvinotoolkit/model_api/tree/master/examples/python/visual_prompting)
-and [ZSL-VPT](https://github.com/openvinotoolkit/model_api/tree/master/examples/python/zsl_visual_prompting)
+See demos: [VPT](https://github.com/open-edge-platform/model_api/tree/master/examples/python/visual_prompting)
+and [ZSL-VPT](https://github.com/open-edge-platform/model_api/tree/master/examples/python/zsl_visual_prompting)

src/python/pyproject.toml

@@ -63,9 +63,9 @@ build = [
 full = ["openvino_model_api[dependencies, ovms, tests, docs, build]"]
 
 [project.urls]
-Homepage = "https://github.com/openvinotoolkit/model_api"
-Documentation = "https://github.com/openvinotoolkit/model_api/blob/master/README.md"
-Repository = "https://github.com/openvinotoolkit/model_api.git"
+Homepage = "https://github.com/open-edge-platform/model_api"
+Documentation = "https://github.com/open-edge-platform/model_api/blob/master/README.md"
+Repository = "https://github.com/open-edge-platform/model_api.git"
 
 [tool.setuptools.packages.find]
 include = ["model_api*"]