Menu rel - #4423
Conversation
There was a problem hiding this comment.
maybe agentic_integrations instead of genai_integrations?
There was a problem hiding this comment.
I would go for something more generic. Like "known third party integrations"? So we don't close it for genai/agentic use cases only.
|
|
||
| * [RAG building blocks made easy and affordable with OpenVINO Model Server](https://medium.com/openvino-toolkit/rag-building-blocks-made-easy-and-affordable-with-openvino-model-server-e7b03da5012b) | ||
| **Docker images** (recommended): | ||
| ```bash |
There was a problem hiding this comment.
let's change it to text to not test it in CI
|
|
||
| OpenVINO Model Server demos have been created to showcase the usage of the model server as well as demonstrate it’s capabilities. | ||
| ### Check Out New Generative AI Demos | ||
| OpenVINO Model Server demos have been created to showcase the usage of the model server as well as demonstrate its capabilities. |
There was a problem hiding this comment.
This whole line seem redundant to me. Demos purpose is kind of obvious, so maybe we can just drop it?
|
|
||
| ## What is OVMS? | ||
|
|
||
| OpenVINO Model Server (OVMS) is a production-grade, C++ inference server that exposes ML models over standard network APIs. It serves both **Generative AI** workloads (LLMs, VLMs, image generation, audio) and **classic deep learning** models (object detection, classification, OCR, and more). |
There was a problem hiding this comment.
Maybe explicitly mention agentic?
There was a problem hiding this comment.
Pull request overview
This PR refreshes OVMS’s primary entry points (root README.md and docs/home.md) and restructures the demos documentation navigation to present grouped categories (text generation, classic models, MediaPipe, etc.) instead of a long flat list.
Changes:
- Rewrites the root README and docs homepage with updated positioning, feature breakdown, and quick-start examples.
- Reorganizes demos navigation into category landing pages (new
demos/*_demos.mdpages) and trims per-demo hidden toctrees. - Updates/curates content in several generative demos (notably removing NPU deployment subsections in some pages).
Reviewed changes
Copilot reviewed 10 out of 11 changed files in this pull request and generated 6 comments.
Show a summary per file
| File | Description |
|---|---|
| README.md | New top-level README layout with updated quick starts, features, and links. |
| docs/home.md | Refreshed docs landing page to mirror the new README structure and quick starts. |
| demos/README.md | Replaces the old flat demos toctree with category-level navigation. |
| demos/text_generation.md | Adds a text-generation demos landing page and toctree. |
| demos/classic_models_demos.md | Adds a classic-model demos landing page and toctree. |
| demos/mediapipe_demos.md | Adds a MediaPipe demos landing page and toctree. |
| demos/continuous_batching/README.md | Removes the hidden toctree from the continuous batching demo page. |
| demos/continuous_batching/vlm/README.md | Removes the hidden toctree from the VLM demo page. |
| demos/continuous_batching/structured_output/README.md | Removes NPU-specific tabbed instructions from the structured output demo. |
| demos/continuous_batching/agentic_ai/README.md | Removes NPU-specific deployment instructions from the agentic AI demo. |
| Python Node <ovms_demos_python_node> | ||
| Integrations <ovms_demos_integrations> |
| ## Contributing | ||
|
|
||
| Contributions are welcome! Please open an issue or pull request on GitHub. | ||
| See [security policy](security.md) for responsible disclosure. |
|
|
||
| **Windows (binary package):** | ||
| ```bat | ||
| ovms --model_name resnet --model_path resnet50.xml --mean "[123.675,116.28,103.53]" --scale "[58.395,57.12,57.375]" --layout "NHWC:NCHW" --port 9000 |
| Check how to write the client applications using [generative endpoints](./clients_genai.md). | ||
| **Windows (binary package):** | ||
| ```bat | ||
| ovms --model_name resnet --model_path resnet50.xml --mean "[123.675,116.28,103.53]" --scale "[58.395,57.12,57.375]" --layout "NHWC:NCHW" --port 9000 |
| ovms.exe --source_model OpenVINO/Qwen3-4B-int4-ov --model_repository_path c:\models --rest_port 8000 | ||
| ``` | ||
|
|
||
| **Query the model:** |
| LLM on NPU <ovms_demos_llm_npu> | ||
| Scaling on multi CPU and GPU <ovms_demos_continuous_batching_scaling> | ||
| Loading models in GGUF <ovms_demos_gguf> |
przepeck
left a comment
There was a problem hiding this comment.
Please check the comments from copilot
| ``` | ||
|
|
||
| **Query the model:** | ||
| ```python |
There was a problem hiding this comment.
| ```python | |
| ```console | |
| pip install openai |

🛠 Summary
Refresh main page and menu
https://openvino-doc.iotg.sclab.intel.com/ovms/model-server/ovms_what_is_openvino_model_server.html
🧪 Checklist
``