Skip to content

refresh configuration docs - #4414

Open
dtrawins wants to merge 1 commit into
releases/2026/3from
doc-config-re
Open

refresh configuration docs#4414
dtrawins wants to merge 1 commit into
releases/2026/3from
doc-config-re

Conversation

@dtrawins

Copy link
Copy Markdown
Collaborator

🛠 Summary

JIRA/Issue if applicable.
Describe the changes.

🧪 Checklist

  • Unit tests added.
  • The documentation updated.
  • Change follows security best practices.
    ``

@dtrawins
dtrawins requested review from atobiszei and mzegla July 28, 2026 12:14
```

Traditional AI models perform data analysis in a single inference operation. They can be used over KServe API or TensorFlow API.
Classic models perform data analysis in a single inference operation. They can be served using the KServe API or TensorFlow API.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
Classic models perform data analysis in a single inference operation. They can be served using the KServe API or TensorFlow API.
Classic models perform data analysis in a single inference operation. They can be served using the KServe API.

Comment thread docs/pull_hf_models.md
# OVMS Pull mode {#ovms_docs_pull}

This document describes how to leverage OpenVINO Model Server (OVMS) pull feature to automate deployment configuration with Generative AI models. When pulling from [Hugging Face Hub](https://huggingface.co/) or when pulling GGUF model, no additional steps are required. However, when pulling models in Pytorch format, you have to install additional python dependencies when using baremetal execution so that optimum-cli is available for ovms executable or rely on the docker image `openvino/model_server:latest-py`. In summary you have 3 options:
This document describes how to use the OpenVINO Model Server (OVMS) pull feature to automate deployment configuration for Generative AI models. When pulling models from [Hugging Face Hub](https://huggingface.co/) in IR or GGUF format, no additional setup is required. However, when pulling models in PyTorch format, you need additional Python dependencies on a bare-metal host so that `optimum-cli` is available to the OVMS executable, or you can use the `openvino/model_server:latest-py` Docker image. In summary, you have three options:

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are we ensuring latest-py tag being up to date? In the last release we did not push latest-py.
Last -py image release was for 2026.1.

Comment thread docs/pull_hf_models.md
```

> **Note:** These models aren't tested properly and their accuracy or performance may be low.
> **Note:** These models are tested by OpenVINO team, and their accuracy or performance is not guaranteed.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is that intentional? That would mean that models provided and tested by OV do not come with guaranteed quality. Shouldn't it be are not tested?

Comment thread docs/starting_server.md
```

*Note:* Use relative or absolute paths. `config_path` is relative to the current folder. `model_path` is relative to the config file. With `model_repository_path`, `model_name` represents a folder relative to model repository path.
> **Note:** Use relative or absolute paths. `config_path` is relative to the current folder. `model_path` is relative to the config file. With `model_repository_path`, `model_name` represents a folder relative to the model repository path.

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For model_path I guess it depends if we talk about model path in config.json, or model_path in a single model mode provided from the CLI right? But I guess it's fine if in that section we are talking about add_to_config case.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants