Add ApiKey to TEI embedding provider

[YohannZe]

Description

[ What changed? Feel free to be brief. ]

Added the possibility to have an api-key in the tei embedding provider, following what was done for the rerank endpoint.

Checklist

• The relevant docs, if any, have been updated or created
• The relevant tests, if any, have been updated or created

Screenshots

[ For visual changes, include screenshots. ]

Testing instructions

[ For new or modified features, provide step-by-step testing instructions to validate the intended behavior of the change, including any relevant tests to run. ]

[netlify]

✅ Deploy Preview for continuedev ready!

Name	Link
🔨 Latest commit	9ee7190
🔍 Latest deploy log	https://app.netlify.com/sites/continuedev/deploys/67e1533d71eda60008686264
😎 Deploy Preview	https://deploy-preview-4783--continuedev.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[RomneyDa]

@YohannZe I believe this was fixed 2 weeks ago around the same time as your PR was opened on #4581. Sorry for the review delay.

apiKey is added to headers in the this.fetch function that uses our custom @continuedev/fetch package to apply request options to the request. Huggingface was using fetch instead of this.fetch. Your approach would also fix the api key but other request options would still be ignored.

Could you verify that this has been fixed on your end?

[YohannZe]

Hello @RomneyDa , thanks for the reply !
On my side, I don't see any changes with before, and no api key in the request made to the embedding provider. I tried both pre release and release version.

I've read your PR, could it be that in it HuggingFaceTei extends BaseLLM where it should extend openAI ? I'm not familiar with the code so I could be wrong.

Thanks for the review, I remain available if anything.

[RomneyDa]

OpenAI extends BaseLLM and this.fetch is set up on the underlying BaseLLM. If you can debug and step through/into this.fetch you might find the issue.