feat: add Eden AI as an LLM provider - #671
Merged
Merged
Conversation
Eden AI is an OpenAI-compatible gateway (https://api.edenai.run/v3) that routes to many providers behind one key; models addressed as <provider>/<model>. Adds a single ProviderSpec to the registry (openai_compat backend, EDENAI_API_KEY), so env vars, config matching and status display all derive from it per the module docs.
pancacake
added a commit
that referenced
this pull request
Jul 24, 2026
… tests Follow-up to #671. The eden_ai/eden-ai spelling variants lived in the spec's keywords tuple, but keywords are only consulted by find_by_model (which excludes gateways) — binding names resolve through PROVIDER_ALIASES. Register the alias there (canonicalization folds eden-ai into eden_ai) and trim keywords to the canonical name. Backfill the four registry-wiring tests the Atlas Cloud addition (#654) established as the pattern: spec fields + alias + base detection, runtime binding resolution, settings provider choices, and the cloud openai_compat native-tools guard.
Collaborator
|
Merged — thanks for the clean, registry-first addition and the live verification notes. Followed up in 75900a5: registered the |
pancacake
added a commit
that referenced
this pull request
Jul 26, 2026
Maintenance release on top of v1.5.4, with two new ways to bring a model. - OpenAI Codex is a first-party OAuth provider (#690): browser sign-in against your own ChatGPT plan replaces the API-key fields, credentials stay in <user-root>/private/openai-codex/ with owner-only permissions, and the managed profile is owner-bound so it is never handed out through grants or made active over an already-configured LLM. - Eden AI joins as the 35th LLM binding (#671), an OpenAI-compatible gateway addressed as <provider>/<model>. - Knowledge bases answer from a real document inventory instead of guessing from retrieval hits: a per-KB inventory rides the system prompt and a new kb_files tool enumerates on demand with glob/substring filters, mounted under rag's gate and deniable per partner. - The rag tool cites the chunks, entities, and reports retrieval actually returned (#694) rather than an echo of its own query; the local LightRAG pipeline still surfaces nothing to cite. - GraphRAG indexing runs on a worker thread with its own asyncio loop (#695), so UVICORN_LOOP=asyncio is no longer needed, and two config faults that broke the first run are fixed (#699). - Assorted: unique optimistic message ids (#698, a v1.5.4 regression that dropped the assistant reply from the visible thread), partner-chat manual scrolling respected (#704), claude-opus-5 recognized as effort-based (#703), Kimi models omit temperature outright, and deeptutor start keeps relaying logs on legacy Windows code pages (#702). - Typing: narrow the loopback callback server to asyncio.Server and gate the msvcrt lock path on sys.platform so it type-checks off Windows. Release notes: assets/releases/ver1-5-5.md
MVS-source
added a commit
to edenai/docs
that referenced
this pull request
Jul 27, 2026
…des (#82) Eden AI shipped as a native provider in all three, merged upstream: Eigenwise/atomic-agents#270, oomol-lab/open-connector#164, HKUDS/DeepTutor#671. Adds v3/integrations/*.mdx pages (AI Frameworks, AI Gateway, Chat UI groups) matching the existing devdoc format.
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
2 participants
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.
What
Adds Eden AI as an LLM provider.
Eden AI is an OpenAI-compatible gateway (
https://api.edenai.run/v3) that routes to many upstream providers behind a single key. Models are addressed as<provider>/<model>, e.g.openai/gpt-5.5ormistral/mistral-large-latest.Changes
A single
ProviderSpecindeeptutor/services/provider_registry.py(per the module's "adding a new provider" note — env vars, config matching and status display all derive from the registry):backend="openai_compat",is_gateway=True,env_key="EDENAI_API_KEY",default_api_base="https://api.edenai.run/v3".Placed among the gateways (after OpenRouter), matching the existing order.
Testing
ruff format --checkandruff checkpass on the changed file.edenairesolves (canonical_provider_name("edenai") -> "edenai").https://api.edenai.run/v3: chat completions return 200 and tool/function calling works foropenai/gpt-5.5andmistral/mistral-large-latest;GET /modelsreturns an OpenAI-style list.Embedding support (Eden AI also exposes
/v3/embeddings) can follow as a separate change toEMBEDDING_PROVIDERSif useful.Targeting
devper CONTRIBUTING.