docs(ai-gateway): add "Set up AI Proxy with Eden AI" how-to#5850
Open
MVS-source wants to merge 2 commits into
Open
docs(ai-gateway): add "Set up AI Proxy with Eden AI" how-to#5850MVS-source wants to merge 2 commits into
MVS-source wants to merge 2 commits into
Conversation
Eden AI exposes an OpenAI-compatible API, so it works with the ai-proxy openai provider by pointing upstream_url at Eden AI's endpoint (the same pattern already documented for DeepSeek). This adds a how-to mirroring that pattern, plus the site.edenai vendor name. Eden AI is EU-based and GDPR-compliant and fronts models from many providers behind one key with provider fallback. The upstream contract the guide configures (POST https://api.edenai.run/v3/chat/completions, model openai/gpt-4o-mini, Bearer auth) was verified live; the EU-endpoint note was verified against an EU-hosted model. The API key is a deck env variable and never appears in the config. Signed-off-by: Victor M. SMITH <72023257+MVS-source@users.noreply.github.com>
👷 Deploy request for kongdeveloper pending review.Visit the deploys page to approve it
|
|
|
Contributor
There was a problem hiding this comment.
Pull request overview
Adds a new AI Gateway how-to documenting how to configure the AI Proxy plugin to call Eden AI’s OpenAI-compatible endpoint, and introduces a site.edenai vendor name for consistent branding in docs.
Changes:
- Add
edenai: Eden AItojekyll.ymlfor reuse via{{ site.edenai }}. - Add a new how-to page: Set up AI Proxy with Eden AI under
app/_how-tos/ai-gateway/, including an EU endpoint/data residency note and a validation step.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| jekyll.yml | Adds the Eden AI vendor label (site.edenai) for consistent use in docs templates. |
| app/_how-tos/ai-gateway/set-up-ai-proxy-with-edenai.md | New end-to-end how-to showing AI Proxy configuration for Eden AI (OpenAI-compatible upstream URL + decK variable for API key), plus EU endpoint guidance and validation include. |
Comment on lines
+32
to
+36
| tags: | ||
| - ai | ||
| - openai | ||
| - edenai | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a Set up AI Proxy with Eden AI how-to under
app/_how-tos/ai-gateway/, plus thesite.edenaivendor name.Eden AI exposes an OpenAI-compatible API, so it works with the AI Proxy
openaiprovider by pointingupstream_urlat Eden AI's endpoint — the same "dummy OpenAI-compatible provider" pattern already documented for DeepSeek. The guide mirrors that existing page.What's in the guide
provider: openai,name: openai/gpt-4o-mini,options.upstream_url: https://api.edenai.run/v3/chat/completionsAuthorization: Bearer ${api_key}whereapi_keyis a decK variable sourced from$EDENAI_API_KEY(key is never in the config)https://api.eu.edenai.run/v3endpointWhy it's useful
Eden AI is an EU-based, GDPR-compliant gateway that fronts models from many providers (OpenAI, Anthropic, Mistral, Google, ...) behind a single key with provider fallback — a convenient data-sovereign upstream for AI Proxy users, and a documented answer to the recurring "how do I use an OpenAI-compatible provider" question.
Verification
POST https://api.edenai.run/v3/chat/completionswithmodel: openai/gpt-4o-miniand Bearer auth — was run live and returned a valid chat completion (200).https://api.eu.edenai.run/v3/chat/completionsreturns200with an EU-hosted model (e.g.amazon/mistral.mistral-large-2402-v1:0), and correctly rejects US-only models likeopenai/gpt-4o-mini— the note reflects that.set-up-ai-proxy-with-deepseekpage. I wasn't able to runmake vale/ a local Jekyll build in my environment (missing toolchain), so a style-lint/preview pass on CI would be appreciated.