From 58e338d6dc806272ad1c44fefedc33a05336304c Mon Sep 17 00:00:00 2001 From: Karol Blaszczak Date: Mon, 3 Feb 2025 17:23:50 +0100 Subject: [PATCH] [DOCS] ecosystem restructuring 25.0 (#28786) port: https://github.com/openvinotoolkit/openvino/pull/28780 --------- Co-authored-by: sgolebiewski-intel --- docs/articles_en/about-openvino.rst | 27 +-- .../about-openvino/openvino-ecosystem.rst | 142 ++------------ .../openvino-ecosystem/openvino-adoptions.rst | 57 ++++++ .../openvino-integrations.rst | 182 ++++++++++++++++++ .../openvino-ecosystem/openvino-project.rst | 112 +++++++++++ .../{ => openvino-project}/datumaro.rst | 2 +- .../openvino-security-add-on.rst | 6 +- .../openvino-test-drive.rst | 8 +- .../openvino-training-extensions.rst | 4 +- .../assets/images/deploy_encrypted_model.svg | 4 +- docs/articles_en/documentation.rst | 22 ++- .../supported-devices.rst | 1 - .../documentation/openvino-security.rst | 2 +- 13 files changed, 407 insertions(+), 162 deletions(-) create mode 100644 docs/articles_en/about-openvino/openvino-ecosystem/openvino-adoptions.rst create mode 100644 docs/articles_en/about-openvino/openvino-ecosystem/openvino-integrations.rst create mode 100644 docs/articles_en/about-openvino/openvino-ecosystem/openvino-project.rst rename docs/articles_en/about-openvino/openvino-ecosystem/{ => openvino-project}/datumaro.rst (98%) rename docs/articles_en/about-openvino/openvino-ecosystem/{ => openvino-project}/openvino-security-add-on.rst (98%) rename docs/articles_en/about-openvino/openvino-ecosystem/{ => openvino-project}/openvino-test-drive.rst (95%) rename docs/articles_en/about-openvino/openvino-ecosystem/{ => openvino-project}/openvino-training-extensions.rst (94%) diff --git a/docs/articles_en/about-openvino.rst b/docs/articles_en/about-openvino.rst index 8c1552de072500..ec47f6d9f0962e 100644 --- a/docs/articles_en/about-openvino.rst +++ b/docs/articles_en/about-openvino.rst @@ -20,7 +20,6 @@ toolkit designed to optimize, accelerate, and deploy deep learning models for us OpenVINO is actively developed by Intel® to work efficiently on a wide range of Intel® hardware platforms, including CPUs (x86 and Arm), GPUs, and NPUs. - Features ############################################################## @@ -32,23 +31,16 @@ To learn about the main properties of OpenVINO, see the :doc:`Key Features `__ and `core components `__. - -OpenVINO Ecosystem -############################################################## - -Along with the primary components of model optimization and runtime, the toolkit also includes: - -* `Neural Network Compression Framework (NNCF) `__ - a tool for enhanced OpenVINO™ inference to get performance boost with minimal accuracy drop. -* :doc:`Openvino Notebooks `- Jupyter Python notebook, which demonstrate key features of the toolkit. -* `OpenVINO Model Server `__ - a server that enables scalability via a serving microservice. -* :doc:`OpenVINO Training Extensions ` – a convenient environment to train Deep Learning models and convert them using the OpenVINO™ toolkit for optimized inference. -* :doc:`Dataset Management Framework (Datumaro) ` - a tool to build, transform, and analyze datasets. +To learn more about how OpenVINO works, read the Developer documentation on its +`architecture `__ +and +`core components `__. Community ############################################################## -OpenVINO community plays a vital role in the growth and development of the open-sourced toolkit. Users can contribute to OpenVINO and get support using the following channels: +OpenVINO community plays a vital role in the growth and development of the open-sourced toolkit. +Users can contribute to OpenVINO and get support using the following channels: * `OpenVINO GitHub issues, discussions and pull requests `__ * `OpenVINO Blog `__ @@ -59,6 +51,7 @@ OpenVINO community plays a vital role in the growth and development of the open- Case Studies ############################################################## -OpenVINO has been employed in various case studies across a wide range of industries and applications, including healthcare, retail, safety and security, transportation, and more. Read about how OpenVINO enhances efficiency, accuracy, and safety in different sectors on the `success stories page `__. - - +OpenVINO has been employed in various case studies across a wide range of industries and +applications, including healthcare, retail, safety and security, transportation, and more. +Read about how OpenVINO enhances efficiency, accuracy, and safety in different sectors on the +`success stories page `__. diff --git a/docs/articles_en/about-openvino/openvino-ecosystem.rst b/docs/articles_en/about-openvino/openvino-ecosystem.rst index 765a5d87a46c2e..5593ce56af48fe 100644 --- a/docs/articles_en/about-openvino/openvino-ecosystem.rst +++ b/docs/articles_en/about-openvino/openvino-ecosystem.rst @@ -1,136 +1,30 @@ -OpenVINO™ Ecosystem Overview -============================== - +OpenVINO Ecosystem +================== .. meta:: - :description: OpenVINO™ ecosystem offers various resources for developing deep learning - solutions. - + :description: Explore the OpenVINO™ ecosystem of tools and resources for developing deep + learning solutions. .. toctree:: :maxdepth: 1 :hidden: - openvino-ecosystem/openvino-training-extensions - openvino-ecosystem/openvino-test-drive - openvino-ecosystem/datumaro - openvino-ecosystem/openvino-security-add-on - - - -OpenVINO™ is a big project, offering more than just the core runtime. This page will give -you an overview of a whole ecosystem of tools and solutions under the OpenVINO umbrella. - - -| **GenAI** -| :bdg-link-dark:`Github ` - :bdg-link-success:`User Guide ` - -OpenVINO™ GenAI Library aims to simplify running inference of generative AI -models. Check the LLM-powered Chatbot Jupyter notebook to see how GenAI works. -|hr| - - -| **Neural Network Compression Framework** -| :bdg-link-dark:`Github ` - :bdg-link-success:`User Guide ` - -A suite of advanced algorithms for Neural Network inference optimization with minimal accuracy -drop. NNCF applies quantization, filter pruning, binarization, and sparsity algorithms to PyTorch -and TensorFlow models during training. -|hr| - - -| **OpenVINO Model Server** -| :bdg-link-dark:`Github ` - :bdg-link-success:`User Guide ` - -A high-performance system that can be used to access the host models via request to the model -server. -|hr| - - -| **OpenVINO Notebooks** -| :bdg-link-dark:`Github ` - :bdg-link-success:`Jupyter Notebook Collection ` - -A collection of Jupyter notebooks for learning and experimenting with the OpenVINO™ Toolkit. -|hr| - - -| **Hugging Face OpenVINO models** -| :bdg-link-info:`Model Collection ` - -A Hugging Face repository hosting pre-optimized OpenVINO IR models, so that you can use them -without the need to convert. -|hr| - - -| **OpenVINO Training Extensions** -| :bdg-link-dark:`Github ` - :bdg-link-success:`Overview Page ` - -A convenient environment to train Deep Learning models and convert them using the OpenVINO™ -toolkit for optimized inference. -|hr| - - -| **OpenVINO Security Addon** -| :bdg-link-dark:`Github ` - :bdg-link-success:`User Guide ` - -A solution for Model Developers and Independent Software Vendors to use secure packaging and -secure model execution. -|hr| - - -| **Datumaro** -| :bdg-link-dark:`Github ` - :bdg-link-success:`Overview Page ` - -A framework and a CLI tool for building, transforming, and analyzing datasets. -|hr| - - -| **Intel® Geti™** -| :bdg-link-dark:`Github ` - :bdg-link-info:`Official Website ` - -Intel's new software for building computer vision -models in a fraction of the time and with less data. This software eases laborious -data labeling, model training and optimization tasks across the AI model -development process, empowering teams to produce custom AI models at scale. -|hr| - - -| **Intel® Test Drive** -| :bdg-link-dark:`Github ` - -OpenVINO™ Test Drive is cross-platform graphic user interface application that enables running -generative AI and vision models directly on your computer or edge device using OpenVINO™ Runtime. -|hr| - - -| **Tokenizers** -| :bdg-link-dark:`Github ` - :bdg-link-success:`User Guide ` - -OpenVINO Tokenizers add text processing operations to OpenVINO. - -OpenVINO-based AI projects -########################## - -OpenVINO is used in many educational, multimodal, and AI projects in the fields of AI Audio, -Natural Language Processing, AI Computer Vision, Generative AI, operating systems and API extensions. -Examples of such projects are: `OpenVINO AI Plugins for GIMP `__, -`OpenVINO Code `__, and -`NVIDIA GPU Plugin `__. + OpenVINO Integrations + The OpenVINO Project + OpenVINO Adoptions -A detailed listing of OpenVINO-based AI projects is available in the -`Awesome OpenVINO repository `__ +OpenVINO™, as a toolkit should, involves multiple components and integrations that may be used +in various areas of your Deep Learning pipelines. This section will give you an overview of a +whole ecosystem of resources either developed under the OpenVINO umbrella, integrating it with +external solutions, or utilizing its potential. +| :doc:`OpenVINO Integrations <./openvino-ecosystem/openvino-integrations>` +| See what other tools OpenVINO is easily integrated with and how you can benefit from its + performance, without rewriting your software. -.. |hr| raw:: html +| :doc:`The OpenVINO project <./openvino-ecosystem/openvino-project>` +| Check out the most noteworthy components of the OpenVINO project. -
+| :doc:`OpenVINO adoptions <./openvino-ecosystem/openvino-adoptions>` +| Here, you will find information about a selection of software projects utilizing OpenVINO. \ No newline at end of file diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-adoptions.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-adoptions.rst new file mode 100644 index 00000000000000..b83a41837b8a2f --- /dev/null +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-adoptions.rst @@ -0,0 +1,57 @@ +OpenVINO Adoptions +========================== + +OpenVINO has been adopted by multiple AI projects in various areas. For an extensive list of +community-based projects involving OpenVINO, see the +`Awesome OpenVINO repository `__. + +Here is a small selection of adoptions, including proprietary and commercial tools: + +| **DaVinCI Resolve** +| :bdg-link-info:`Official Website ` + +DaVinci resolve is a professional video editing suite by Blackmagic Design. It uses OpenVINO to +run some of its industry-leading AI features. +|hr| + +| **OpenVINO AI Plugins for GIMP** +| :bdg-link-dark:`Official Repository ` + +Gimp is an image editor that has promoted open source values for over two decades. Now, you can +use generative AI directly in the application, thanks to the OpenVINO plugin, just like in the +leading graphics suites. +|hr| + +| **OpenVINO AI Plugins for Audacity** +| :bdg-link-info:`Official Website ` + :bdg-link-dark:`Official Repository ` + +Audacity is a hugely popular audio editing and recording application. Now, it offers AI-based +plugins running on OpenVINO, providing new effects, generators, and analyzers. +|hr| + +| **VisionGuard** +| :bdg-link-dark:`Official Repository ` + +A desktop tool developed within Google Summer of Code. Its aim is to help computer users battle +eye strain, utilizing gaze estimation. +|hr| + +| **OpenVINO Code** +| :bdg-link-dark:`Official Repository ` + +A coding assistant. A community-developed extension for Visual Studio Code, aiming to help +programmers by providing code completion and suggestions. +|hr| + +| **NVIDIA GPU Plugin** +| :bdg-link-dark:`Official Repository ` + +A device plugin for OpenVINO. A community-developed extension, enabling inference using +NVIDIA GPUs. +|hr| + + +.. |hr| raw:: html + +
diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-integrations.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-integrations.rst new file mode 100644 index 00000000000000..16283402a68c31 --- /dev/null +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-integrations.rst @@ -0,0 +1,182 @@ +OpenVINO™ Integrations +============================== + + +.. meta:: + :description: Check a list of integrations between OpenVINO and other Deep Learning solutions. + + + +.. = 1 ======================================================================================== + +**Hugging Face Optimum-Intel** + +|hr| + +.. grid:: 1 1 2 2 + :gutter: 4 + + .. grid-item:: + + | Grab and use models leveraging OpenVINO within the Hugging Face API. + The repository hosts pre-optimized OpenVINO IR models, so that you can use + them in your projects without the need for any adjustments. + | Benefits: + | - Minimize complex coding for Generative AI. + + .. grid-item:: + + * :doc:`Run inference with HuggingFace and Optimum Intel <../../openvino-workflow-generative/inference-with-optimum-intel>` + * `A notebook example: llm-chatbot `__ + * `Hugging Face Inference documentation `__ + * `Hugging Face Compression documentation `__ + * `Hugging Face Reference Documentation `__ + +.. dropdown:: Check example code + :animate: fade-in-slide-down + :color: secondary + + .. code-block:: py + + -from transformers import AutoModelForCausalLM + +from optimum.intel.openvino import OVModelForCausalLM + + from transformers import AutoTokenizer, pipeline + model_id = "togethercomputer/RedPajama-INCITE-Chat-3B-v1" + + -model = AutoModelForCausalLM.from_pretrained(model_id) + +model = OVModelForCausalLM.from_pretrained(model_id, export=True) + + +.. = 2 ======================================================================================== + +**OpenVINO Execution Provider for ONNX Runtime** + +|hr| + +.. grid:: 1 1 2 2 + :gutter: 4 + + .. grid-item:: + + | Utilize OpenVINO as a backend with your existing ONNX Runtime code. + | Benefits: + | - Enhanced inference performance on Intel hardware with minimal code modifications. + + .. grid-item:: + + * A notebook example: YOLOv8 object detection + * `ONNX User documentation `__ + * `Build ONNX RT with OV EP `__ + * `ONNX Examples `__ + + +.. dropdown:: Check example code + :animate: fade-in-slide-down + :color: secondary + + .. code-block:: cpp + + device = `CPU_FP32` + # Set OpenVINO as the Execution provider to infer this model + sess.set_providers([`OpenVINOExecutionProvider`], [{device_type` : device}]) + + +.. = 3 ======================================================================================== + +**Torch.compile with OpenVINO** + +|hr| + +.. grid:: 1 1 2 2 + :gutter: 4 + + .. grid-item:: + + | Use OpenVINO for Python-native applications by JIT-compiling code into optimized kernels. + | Benefits: + | - Enhanced inference performance on Intel hardware with minimal code modifications. + + .. grid-item:: + + * :doc:`PyTorch Deployment via torch.compile <../../openvino-workflow/torch-compile>` + * A notebook example: n.a. + * `torch.compiler documentation `__ + * `torch.compiler API reference `__ + +.. dropdown:: Check example code + :animate: fade-in-slide-down + :color: secondary + + .. code-block:: python + + import openvino.torch + + ... + model = torch.compile(model, backend='openvino') + ... + + + +.. = 4 ======================================================================================== + +**OpenVINO LLMs with LlamaIndex** + +|hr| + +.. grid:: 1 1 2 2 + :gutter: 4 + + .. grid-item:: + + | Build context-augmented GenAI applications with the LlamaIndex framework and enhance + runtime performance with OpenVINO. + | Benefits: + | - Minimize complex coding for Generative AI. + + .. grid-item:: + + * :doc:`LLM inference with Optimum-intel <../../openvino-workflow-generative/inference-with-optimum-intel>` + * `A notebook example: llm-agent-rag `__ + * + * `Inference documentation `__ + * `Rerank documentation `__ + * `Embeddings documentation `__ + * `API Reference `__ + +.. dropdown:: Check example code + :animate: fade-in-slide-down + :color: secondary + + .. code-block:: python + + ov_config = { + "PERFORMANCE_HINT": "LATENCY", + "NUM_STREAMS": "1", + "CACHE_DIR": "", + } + + ov_llm = OpenVINOLLM( + model_id_or_path="HuggingFaceH4/zephyr-7b-beta", + context_window=3900, + max_new_tokens=256, + model_kwargs={"ov_config": ov_config}, + generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95}, + messages_to_prompt=messages_to_prompt, + completion_to_prompt=completion_to_prompt, + device_map="cpu", + ) + + + + + + + + + +.. ============================================================================================ + +.. |hr| raw:: html + +
\ No newline at end of file diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project.rst new file mode 100644 index 00000000000000..2b32c4e54426a5 --- /dev/null +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project.rst @@ -0,0 +1,112 @@ +OpenVINO™ Project Overview +============================== + + +.. meta:: + :description: Check an overview of the most interesting components of the OpenVINO™ project. + + +.. toctree:: + :maxdepth: 1 + :hidden: + + openvino-project/openvino-training-extensions + openvino-project/datumaro + openvino-project/openvino-security-add-on + openvino-project/openvino-test-drive + + +This page provides an overview of the most noteworthy tools and components for AI developers, +hosted in repositories under the OpenVINO project: + +| **GenAI** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +OpenVINO™ GenAI Library simplifies running inference of generative AI +models. Check the LLM-powered Chatbot Jupyter notebook to see how GenAI works. +|hr| + +| **Neural Network Compression Framework** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +A suite of advanced algorithms for Neural Network inference optimization with minimal accuracy +drop. NNCF applies quantization, filter pruning, binarization, and sparsity algorithms to PyTorch +and TensorFlow models during training. +|hr| + +| **OpenVINO Model Server** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +A high-performance system that can be used to access the host models via request to the model +server. +|hr| + +| **OpenVINO Notebooks** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`Jupyter Notebook Collection ` + +A collection of Jupyter notebooks for learning and experimenting with the OpenVINO™ Toolkit. +|hr| + +| **OpenVINO Training Extensions** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`Overview Page ` + +A convenient environment to train Deep Learning models and convert them using the OpenVINO™ +toolkit for optimized inference. +|hr| + +| **OpenVINO Security Addon** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +A solution for Model Developers and Independent Software Vendors to use secure packaging and +secure model execution. +|hr| + +| **OpenVINO Test Drive** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`Overview Page ` + +A cross-platform graphic user interface application for running and testing generative and +vision AI models on computers or edge devices. +|hr| + +| **Datumaro** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`Overview Page ` + +A framework and a CLI tool for building, transforming, and analyzing datasets. +|hr| + +| **Intel® Geti™** +| :bdg-link-dark:`GitHub ` + :bdg-link-info:`Official Website ` + +Intel's new software for building computer vision +models in a fraction of the time and with less data. This software eases laborious +data labeling, model training and optimization tasks across the AI model +development process, empowering teams to produce custom AI models at scale. +|hr| + +| **Tokenizers** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +OpenVINO Tokenizers add text processing operations to OpenVINO. +|hr| + +| **OpenVINO's Open Model Zoo** +| :bdg-link-dark:`GitHub ` + :bdg-link-success:`User Guide ` + +Open Model Zoo includes optimized deep learning models and a set of demos to +expedite development of high-performance deep learning inference applications. + + +.. |hr| raw:: html + +
diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/datumaro.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/datumaro.rst similarity index 98% rename from docs/articles_en/about-openvino/openvino-ecosystem/datumaro.rst rename to docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/datumaro.rst index 36fed2543878fe..0b02d63045f59f 100644 --- a/docs/articles_en/about-openvino/openvino-ecosystem/datumaro.rst +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/datumaro.rst @@ -19,7 +19,7 @@ Plus, enjoy `Jupyter notebooks ` on Intel® architecture. Together, the OpenVINO™ Security Add-on and the OpenVINO™ Model Server provide a way for Model Developers and Independent Software Vendors to use secure packaging and secure model execution to enable access control to the OpenVINO™ models, and for model Users to run inference within assigned limits. +The OpenVINO™ Security Add-on works with the :doc:`OpenVINO™ Model Server <../../../openvino-workflow/model-server/ovms_what_is_openvino_model_server>` on Intel® architecture. Together, the OpenVINO™ Security Add-on and the OpenVINO™ Model Server provide a way for Model Developers and Independent Software Vendors to use secure packaging and secure model execution to enable access control to the OpenVINO™ models, and for model Users to run inference within assigned limits. The OpenVINO™ Security Add-on consists of three components that run in Kernel-based Virtual Machines (KVMs). These components provide a way to run security-sensitive operations in an isolated environment. A brief description of the three components are as follows. Click each triangled line for more information about each. @@ -45,7 +45,7 @@ The OpenVINO™ Security Add-on consists of three components that run in Kernel- **Where the OpenVINO™ Security Add-on Fits into Model Development and Deployment** -.. image:: ../../assets/images/ovsa_diagram.svg +.. image:: ../../../assets/images/ovsa_diagram.svg The binding between SWTPM (vTPM used in guest VM) and HW TPM (TPM on the host) is explained in `this document. `__ @@ -743,7 +743,7 @@ The following figure describes the interactions between the Model Developer, Ind The Model Developer/Independent Software Vendor and User roles are related to virtual machine use and one person might fill the tasks required by multiple roles. In this document the tasks of Model Developer and Independent Software Vendor are combined and use the Guest VM named ``ovsa_isv``. It is possible to have all roles set up on the same Host Machine. -.. image:: ../../assets/images/ovsa_example.svg +.. image:: ../../../assets/images/ovsa_example.svg Model Developer Instructions ++++++++++++++++++++++++++++ diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-test-drive.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-test-drive.rst similarity index 95% rename from docs/articles_en/about-openvino/openvino-ecosystem/openvino-test-drive.rst rename to docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-test-drive.rst index 602a2b8ec24eb2..703bf5f9976350 100644 --- a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-test-drive.rst +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-test-drive.rst @@ -50,20 +50,20 @@ Inference of models from Hugging Face 1. Find a model on `Hugging Face `__ and import it. - .. image:: ../../assets/images/TestDrive_llm_import.gif + .. image:: ../../../assets/images/TestDrive_llm_import.gif :align: center :alt: how to import a model to test drive 2. Chat with LLMs via the `Playground` tab. - .. image:: ../../assets/images/TestDrive_llm_model_chat.gif + .. image:: ../../../assets/images/TestDrive_llm_model_chat.gif :align: center :alt: chatting with llm models in test drive 3. Use the `Performance metrics` tab to get model performance metrics on your computer or an edge device. - .. image:: ../../assets/images/TestDrive_llm_metrics.gif + .. image:: ../../../assets/images/TestDrive_llm_metrics.gif :align: center :alt: verifying llm performance in test drive @@ -74,7 +74,7 @@ Inference of models trained with Intel® Geti™ by Intel® Geti™ (refer to the `Intel® Geti™ documentation `__ for more details). - .. image:: ../../assets/images/TestDrive_geti_download.gif + .. image:: ../../../assets/images/TestDrive_geti_download.gif :align: center :alt: verifying llm performance in test drive diff --git a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-training-extensions.rst b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-training-extensions.rst similarity index 94% rename from docs/articles_en/about-openvino/openvino-ecosystem/openvino-training-extensions.rst rename to docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-training-extensions.rst index 8a5bd91f9c1b7b..ea79aa65884c72 100644 --- a/docs/articles_en/about-openvino/openvino-ecosystem/openvino-training-extensions.rst +++ b/docs/articles_en/about-openvino/openvino-ecosystem/openvino-project/openvino-training-extensions.rst @@ -16,7 +16,7 @@ inference. It allows you to export and convert the models to the needed format. Detailed Workflow ################# -.. image:: ../../assets/images/training_extensions_framework.png +.. image:: ../../../assets/images/training_extensions_framework.png 1. To start working with OpenVINO Training Extensions, prepare and annotate your dataset. For example, on CVAT. @@ -25,7 +25,7 @@ Detailed Workflow .. note:: Prepare a separate dataset or split the dataset you have for more accurate quality evaluation. -3. Having successful evaluation results received, you have an opportunity to deploy your model or continue optimizing it, using NNCF. For more information about these frameworks, go to :doc:`Optimization Guide <../../openvino-workflow/model-optimization>`. +3. Having successful evaluation results received, you have an opportunity to deploy your model or continue optimizing it, using NNCF. For more information about these frameworks, go to :doc:`Optimization Guide <../../../openvino-workflow/model-optimization>`. If the results are unsatisfactory, add datasets and perform the same steps, starting with dataset annotation. diff --git a/docs/articles_en/assets/images/deploy_encrypted_model.svg b/docs/articles_en/assets/images/deploy_encrypted_model.svg index fa897731b54fef..3287667eeb8feb 100644 --- a/docs/articles_en/assets/images/deploy_encrypted_model.svg +++ b/docs/articles_en/assets/images/deploy_encrypted_model.svg @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:454a531a9b2d2883ac9a6beb01ce7ecdd7ec69ea2c68d63b39b65f3780c957fe -size 54772 +oid sha256:02e27919487f371839ec4773fa1cdc1063f59b1a5cdd9875faf9ac75f57181d5 +size 85978 diff --git a/docs/articles_en/documentation.rst b/docs/articles_en/documentation.rst index f1c240066f5f05..f1a229a4bb059e 100644 --- a/docs/articles_en/documentation.rst +++ b/docs/articles_en/documentation.rst @@ -16,20 +16,28 @@ Documentation Compatibility and Support Legacy Features OpenVINO Extensibility - OpenVINO™ Security + OpenVINO Security -This section provides reference documents that guide you through the OpenVINO toolkit workflow, from preparing models, optimizing them, to deploying them in your own deep learning applications. +This section provides reference documents for the OpenVINO toolkit, such as API and Operation +listing. | :doc:`API Reference doc path ` -| A collection of reference articles for OpenVINO C++, C, and Python APIs. +| A collection of reference articles for OpenVINO C++, C, Node.js, and Python APIs, as well as + the Python API for OpenVINO GenAI. -| :doc:`OpenVINO Ecosystem ` -| Apart from the core components, OpenVINO offers tools, plugins, and expansions revolving around it, even if not constituting necessary parts of its workflow. This section gives you an overview of what makes up the OpenVINO toolkit. +| :doc:`OpenVINO IR format ` +| A section describing the OpenVINO IR model format and its opsets. + +| :doc:`Legacy Features ` +| The information on all OpenVINO components that have recently been deprecated or discontinued. | :doc:`OpenVINO Extensibility Mechanism ` -| The Intel® Distribution of OpenVINO™ toolkit supports neural network models trained with various frameworks, including TensorFlow, PyTorch, ONNX, TensorFlow Lite, and PaddlePaddle. Learn how to extend OpenVINO functionality with custom settings. +| The Intel® Distribution of OpenVINO™ toolkit supports neural network models trained with + various frameworks, including TensorFlow, PyTorch, ONNX, TensorFlow Lite, and PaddlePaddle. + Learn how to extend OpenVINO functionality with custom settings. | :doc:`OpenVINO™ Security ` -| Learn how to use OpenVINO securely and protect your data to meet specific security and privacy requirements. +| Learn how to use OpenVINO securely and protect your data to meet specific security and privacy + requirements. diff --git a/docs/articles_en/documentation/compatibility-and-support/supported-devices.rst b/docs/articles_en/documentation/compatibility-and-support/supported-devices.rst index 8708f9f4f81ad3..b249b418634258 100644 --- a/docs/articles_en/documentation/compatibility-and-support/supported-devices.rst +++ b/docs/articles_en/documentation/compatibility-and-support/supported-devices.rst @@ -43,7 +43,6 @@ Feature Support and API Coverage :doc:`Multi-stream execution <../../openvino-workflow/running-inference/optimize-inference/optimizing-throughput>` Yes Yes No :doc:`Model caching <../../openvino-workflow/running-inference/optimize-inference/optimizing-latency/model-caching-overview>` Yes Partial Yes :doc:`Dynamic shapes <../../openvino-workflow/running-inference/dynamic-shapes>` Yes Partial No - :doc:`Import/Export <../../about-openvino/openvino-ecosystem>` Yes Yes Yes :doc:`Preprocessing acceleration <../../openvino-workflow/running-inference/optimize-inference/optimize-preprocessing>` Yes Yes No :doc:`Stateful models <../../openvino-workflow/running-inference/stateful-models>` Yes Yes Yes :doc:`Extensibility <../../documentation/openvino-extensibility>` Yes Yes No diff --git a/docs/articles_en/documentation/openvino-security.rst b/docs/articles_en/documentation/openvino-security.rst index c2b2d2ce04188e..c00d71c20fe657 100644 --- a/docs/articles_en/documentation/openvino-security.rst +++ b/docs/articles_en/documentation/openvino-security.rst @@ -8,7 +8,7 @@ with encryption or other security tools. Actual security and privacy requirements depend on your unique deployment scenario. This section provides general guidance on using OpenVINO tools and libraries securely. The main security measure for OpenVINO is its -:doc:`Security Add-on <../about-openvino/openvino-ecosystem/openvino-security-add-on>`. You can find its description +:doc:`Security Add-on <../about-openvino/openvino-ecosystem/openvino-project/openvino-security-add-on>`. You can find its description in the Ecosystem section. .. _encrypted-models: