Add Eden AI provider#187
Open
MVS-source wants to merge 1 commit into
Open
Conversation
Add Eden AI (an EU-based, OpenAI-compatible gateway) as a provider, following the aggregator pattern used by openrouter/requesty. A dedicated EdenAIHandler reuses the OpenAI SDK with a fixed base URL (https://api.edenai.run/v3) and the EDENAI_API_KEY env var; models is set to true so any vendor-prefixed id (e.g. openai/gpt-4o-mini) is accepted. Includes the models entry, type unions, handler registry, docs, a changeset and a live manual test. Verified live against the real API.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Thanks for token.js!
All Submissions:
pnpm docs?pnpm lint:fix?pnpm test?pnpm changeset?New Feature Submissions:
This adds Eden AI as a provider. Eden AI is an EU-based, OpenAI-compatible gateway: one API key reaches models from many providers (OpenAI, Anthropic, Google, Mistral, Cohere and more) with ids like
openai/gpt-4o-mini, and it offers EU data residency, zero data retention, a DPA and SOC 2 / ISO 27001.Implementation mirrors the Requesty handler: a dedicated
EdenAIHandlerreuses the OpenAI SDK with a fixed base URL (https://api.edenai.run/v3) and theEDENAI_API_KEYenv var, registered as an aggregator (models: true) so any vendor-prefixed id is accepted, with no new dependency. Added themodelsentry, the type unions, the handler registry entry, the docs (provider page + tables), a changeset, and a live manual test intest/manual/edenai.test.ts.Verified locally:
pnpm build:tsc,pnpm lint:check,pnpm test(118 pass) andpnpm docs:checkare clean, and the live manual test passes against the real Eden AI API (completion and streaming). The manual test asserts only on returned content.Open question for maintainers: I registered Eden AI as an aggregator (
models: true, like openrouter/requesty) since its catalog is large and vendor-prefixed. Happy to switch to a curated model list if you prefer.For transparency: implemented with Claude Code by an Eden AI team member and verified live. We will maintain the provider.