[Docs] Reformat README, remove duplicated sections (#3018)

## Description
This PR reformats the README and documentation to improve organization,
remove duplication, and enhance clarity.

Preview:
Docs -
https://yatarkan.github.io/openvino.genai/docs/getting-started/installation
README -
https://github.com/yatarkan/openvino.genai/blob/yt/reformat-readme-files/README.md

CVS-169351

## Checklist:
- [x] Tests have been updated or added to cover the new code - N/A
- [ ] This patch fully addresses the ticket.
- [x] I have made corresponding changes to the documentation

Author: yatarkan

README.md

@@ -1,19 +1,39 @@
 ---
-sidebar_position: 3
+sidebar_position: 2
 sidebar_label: Installation
 ---
 
 # Install OpenVINO GenAI
 
-OpenVINO GenAI is available for installation via [Archive](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/), [PyPI](https://pypi.org/project/openvino-genai/)
-and [NPM](https://www.npmjs.com/package/openvino-genai-node) distributions and supports Linux, Windows and macOS platforms.
-
-To install OpenVINO GenAI, refer to the [Install Guide](https://docs.openvino.ai/2025/get-started/install-openvino.html).
+OpenVINO GenAI is available for installation via [PyPI](https://pypi.org/project/openvino-genai/), [Archive](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/)
+and [npm](https://www.npmjs.com/package/openvino-genai-node) distributions and supports Linux, Windows and macOS platforms.
+
+<Tabs>
+    <TabItem value="pypi" label="PyPI" default>
+        ```bash
+        pip install openvino-genai
+        ```
+        :::info Note
+        Some models may require additional dependencies.
+        See the [Model Preparation Guide](/docs/guides/model-preparation/convert-to-openvino) for details.
+        :::
+    </TabItem>
+    <TabItem value="archive" label="Archive">
+        1. Download [OpenVINO GenAI archive](https://storage.openvinotoolkit.org/repositories/openvino_genai/packages/).
+        2. Follow the [Archive Installation instructions](https://docs.openvino.ai/2025/get-started/install-openvino/install-openvino-genai.html#archive-installation).
+    </TabItem>
+    <TabItem value="npm" label="npm">
+        ```bash
+        npm install openvino-genai-node
+        ```
+        See the [Node.js Bindings](/docs/bindings/node-js) for more information.
+    </TabItem>
+</Tabs>
+
+Refer to the [Install Guide](https://docs.openvino.ai/2025/get-started/install-openvino.html) for detailed instructions.
 
 To build OpenVINO GenAI library from source, refer to the [Build Instructions](https://github.com/openvinotoolkit/openvino.genai/blob/master/src/docs/BUILD.md).
 
-To learn more about Node.js bindings, refer to the [Node.js Bindings](/docs/bindings/node-js).
-
 :::info
 Please make sure that you are following the versions compatibility rules, refer to the [OpenVINO GenAI Dependencies](#openvino-genai-dependencies) for more information.
 :::

site/docs/getting-started/installation.mdx

@@ -56,3 +56,14 @@ Compared to Hugging Face Optimum Intel, OpenVINO GenAI offers a smaller footprin
 | Node.js bindings | ✅ | ✅ | ❌ |
 | Pre-built pipelines | ✅ | ❌ | ✅ |
 | Model variety | Medium | High | High |
+
+## Additional Resources
+
+- [OpenVINO Generative AI workflow](https://docs.openvino.ai/2025/openvino-workflow-generative.html)
+- [Optimum Intel and OpenVINO](https://huggingface.co/docs/optimum/intel/openvino/export)
+- [OpenVINO Notebooks with GenAI](https://openvinotoolkit.github.io/openvino_notebooks/?libraries=OpenVINO+GenAI)
+
+Explore blogs to setup your first hands-on experience with OpenVINO GenAI:
+
+- [How to Build OpenVINO™ GenAI APP in C++](https://medium.com/openvino-toolkit/how-to-build-openvino-genai-app-in-c-32dcbe42fa67)
+- [How to run Llama 3.2 locally with OpenVINO™](https://medium.com/openvino-toolkit/how-to-run-llama-3-2-locally-with-openvino-60a0f3674549)

site/docs/getting-started/introduction.mdx

@@ -19,7 +19,7 @@ For downloading pre-converted models, see [Download Pre-Converted OpenVINO Model
 
     :::info Note
     Some models may require additional dependencies.
-    To convert models with `optimum-cli` and to run the examples, install the dependencies from [`./samples/export-requirements.txt`](https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/export-requirements.txt):
+    To convert models with `optimum-cli` and to run the examples, install the dependencies from [`./samples/export-requirements.txt`](https://github.com/openvinotoolkit/openvino.genai/blob/master/samples/export-requirements.txt).
     :::
 
     ```bash

site/docs/guides/model-preparation/convert-to-openvino.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 2
+sidebar_position: 3
 ---
 import OptimumCLI from '@site/src/components/OptimumCLI';
 import ConvertModelSection from '../_shared/_convert_model.mdx';

site/docs/use-cases/image-generation/index.mdx

@@ -16,6 +16,9 @@ int main(int argc, char* argv[]) {
         ov::genai::max_new_tokens(100)
     );
     std::cout << result.texts[0] << std::endl;
+
+    // To input videos frames, use 'ov::genai::videos' property, frames tensor layout = [Frame, H, W, C]
+    // pipe.generate(prompt, ov::genai::videos(std::vector<ov::Tensor>{frames}), ov::genai::max_new_tokens(100));
 }
 `}
 </CodeBlock>

site/docs/use-cases/image-processing/_sections/_run_model/_code_example_cpp.mdx

@@ -23,5 +23,8 @@ images = read_images("./images")
 pipe = ov_genai.VLMPipeline(model_path, "${props.device || 'CPU'}")
 result = pipe.generate(prompt, images=images, max_new_tokens=100)
 print(result.texts[0])
+
+# To input videos frames, use 'videos=', frames tensor layout = [Frame, H, W, C]
+# result = pipe.generate(prompt, videos=[frames], max_new_tokens=100)
 `}
 </CodeBlock>

site/docs/use-cases/image-processing/_sections/_run_model/_code_example_python.mdx

@@ -28,6 +28,8 @@ The prompt can contain `<ov_genai_image_i>` with `i` replaced with an actual zer
 
 Model's native video tag can be used to refer to a video. These tags are:
 1. LLaVa-NeXT-Video: `<video>`
+2. Qwen2-VL: `<|vision_start|><|video_pad|><|vision_end|>`
+2. Qwen2.5-VL: `<|vision_start|><|video_pad|><|vision_end|>`
 
 If the prompt doesn't contain image or video tags, but images or videos are provided, the tags are prepended to the prompt.
 

site/docs/use-cases/image-processing/_sections/_usage_options/index.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 4
+sidebar_position: 2
 ---
 import OptimumCLI from '@site/src/components/OptimumCLI';
 import ConvertModelSection from '../_shared/_convert_model.mdx';

site/docs/use-cases/image-processing/index.mdx

@@ -1,5 +1,5 @@
 ---
-sidebar_position: 7
+sidebar_position: 5
 ---
 import OptimumCLI from '@site/src/components/OptimumCLI';
 import ConvertModelSection from '../_shared/_convert_model.mdx';