Skip to content

Remove py image instruction from RAG#4101

Open
rasapala wants to merge 3 commits intomainfrom
clean_demo1
Open

Remove py image instruction from RAG#4101
rasapala wants to merge 3 commits intomainfrom
clean_demo1

Conversation

@rasapala
Copy link
Copy Markdown
Collaborator

@rasapala rasapala commented Mar 31, 2026

🛠 Summary

JIRA CVS-179954

Updates the Continuous Batching RAG demo documentation to remove Docker-based instructions that relied on the Python (latest-py) OVMS image. Also fixes typos in section headings ("HugginFaces" → "Hugging Face") and removes an unnecessary single-item tab-set wrapper in the Advanced usage section.

🧪 Checklist

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

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

This PR updates the Continuous Batching RAG demo documentation to remove Docker-based instructions that relied on the Python (latest-py) OVMS image, aligning the demo setup guidance with the intended distribution approach.

Changes:

  • Removed the “With Docker” model download instructions for OpenVINO-org models.
  • Removed the “With Docker” model download instructions for non-OpenVINO-org (advanced) models that referenced openvino/model_server:latest-py.

@@ -5,21 +5,6 @@
### 1. Download the preconfigured models using ovms --pull option from [HugginFaces Hub OpenVINO organization](https://huggingface.co/OpenVINO) (Simple usage)
Copy link

Copilot AI Mar 31, 2026

Choose a reason for hiding this comment

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

The link text has a typo: "HugginFaces" should be "Hugging Face" (or "Hugging Face Hub") to match the correct project name.

Copilot uses AI. Check for mistakes.
Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

@copilot apply changes based on this feedback

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

Fixed in commit 726003d. Corrected "HugginFaces" → "Hugging Face" in both section headings, and also removed the unnecessary single-item tab-set wrapper in section 2 (Advanced usage).

@@ -57,20 +42,6 @@ ovms --add_to_config --config_path c:\models\config.json --model_name OpenVINO/b
### 2. Download the preconfigured models using ovms --pull option for models outside [HugginFaces Hub OpenVINO organization](https://huggingface.co/OpenVINO) in HuggingFace Hub. (Advanced usage)
Copy link

Copilot AI Mar 31, 2026

Choose a reason for hiding this comment

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

This heading/link text has a typo: "HugginFaces" should be "Hugging Face" (or "Hugging Face Hub") for the correct name.

Copilot uses AI. Check for mistakes.
Comment on lines 43 to 47
::::{tab-set}

:::{tab-item} With Docker
**Required:** Docker Engine installed
```bash
mkdir models
docker run --user $(id -u):$(id -g) -e HF_HOME=/hf_home/cache --rm -v $(pwd)/models:/models:rw -v /opt/home/user/.cache/huggingface/:/hf_home/cache openvino/model_server:latest-py --pull --model_repository_path /models --source_model meta-llama/Meta-Llama-3-8B-Instruct --task text_generation --weight-format int8
docker run --user $(id -u):$(id -g) -e HF_HOME=/hf_home/cache --rm -v $(pwd)/models:/models:rw -v /opt/home/user/.cache/huggingface/:/hf_home/cache openvino/model_server:latest-py --pull --model_repository_path /models --source_model Alibaba-NLP/gte-large-en-v1.5 --task embeddings --weight-format int8
docker run --user $(id -u):$(id -g) -e HF_HOME=/hf_home/cache --rm -v $(pwd)/models:/models:rw -v /opt/home/user/.cache/huggingface/:/hf_home/cache openvino/model_server:latest-py --pull --model_repository_path /models --source_model BAAI/bge-reranker-large --task rerank --weight-format int8

docker run --user $(id -u):$(id -g) --rm -v $(pwd)/models:/models:rw openvino/model_server:latest-py --add_to_config --config_path /models/config.json --model_name meta-llama/Meta-Llama-3-8B-Instruct --model_path meta-llama/Meta-Llama-3-8B-Instruct --weight-format int8
docker run --user $(id -u):$(id -g) --rm -v $(pwd)/models:/models:rw openvino/model_server:latest-py --add_to_config --config_path /models/config.json --model_name Alibaba-NLP/gte-large-en-v1.5 --model_path Alibaba-NLP/gte-large-en-v1.5 --weight-format int8
docker run --user $(id -u):$(id -g) --rm -v $(pwd)/models:/models:rw openvino/model_server:latest-py --add_to_config --config_path /models/config.json --model_name BAAI/bge-reranker-large --model_path BAAI/bge-reranker-large --weight-format int8
```
:::

:::{tab-item} On Baremetal Host
**Required:** OpenVINO Model Server package - see [deployment instructions](../../../docs/deploying_server_baremetal.md) for details.

Copy link

Copilot AI Mar 31, 2026

Choose a reason for hiding this comment

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

This tab-set currently contains only a single tab item ("On Baremetal Host"). Using a tab-set for a single option tends to render as unnecessary UI and adds maintenance overhead; consider removing the ::::{tab-set} / ::{tab-item} wrappers here (or add the missing alternatives if there are meant to be multiple choices).

Copilot uses AI. Check for mistakes.
Copy link
Copy Markdown
Collaborator Author

Choose a reason for hiding this comment

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

@copilot apply changes based on this feedback

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.

4 participants