remove openai requirement for embedding

[jperez999]

Description

This removes dependency of OpenAI for the text embedder.

Checklist

• I am familiar with the Contributing Guidelines.
• New or existing tests cover these changes.
• The documentation is up to date with these changes.
• If adjusting docker-compose.yaml environment variables have you ensured those are mimicked in the Helm values.yaml file.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[drobison00]

For consistency, this really needs to be a NimClient, so that we're able to use the same configuration process that we do for all the other NIM elements.

[drobison00]

Something like this but, I would imagine much less pre/post processing code.

https://github.com/NVIDIA/nv-ingest/blob/main/api/src/nv_ingest_api/internal/primitives/nim/model_interface/yolox.py#L92

[jperez999]

I am a little confused here, because this is running a NIM client. Its just surrounded by a helper function in order to make it available outside of the NIM classes. https://github.com/NVIDIA/nv-ingest/pull/1101/files#diff-134970881072236d7f90878a5b6a8676c477ff4f6814bd6f9a272b6addd85570R132 NimClient is here.