feat: add Eden AI as a provider option - #270
Merged
Merged
Conversation
Eden AI is an EU-based, OpenAI-compatible LLM gateway. Since Atomic Agents delegates model access to Instructor, Eden AI works through instructor.from_openai(OpenAI(base_url=..., api_key=...)), exactly like the existing OpenRouter and MiniMax options. Model ids are vendor-prefixed (e.g. openai/gpt-4o-mini, anthropic/claude-haiku-4-5). Adds the provider to the multi-provider quickstart example, unit tests and live integration tests mirroring the MiniMax ones, and a mention in the README provider list.
Updated compatibility information for APIs supported by Instructor.
Eigenwise
approved these changes
Jul 22, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a provider option, alongside the existing OpenAI, Anthropic, Groq, Ollama, Gemini, OpenRouter and MiniMax choices.
Eden AI is an EU-based, OpenAI-compatible LLM gateway (one API key, one endpoint, many upstream vendors). Because Atomic Agents delegates model access to Instructor, no framework change is needed: Eden AI is used through
instructor.from_openai(OpenAI(base_url="https://api.edenai.run/v3", api_key=...)), exactly like the current OpenRouter and MiniMax options.Eden AI model ids are vendor-prefixed, for example
openai/gpt-4o-mini,anthropic/claude-haiku-4-5,mistral/mistral-small-latest.Changes
atomic-examples/quickstart/quickstart/4_basic_chatbot_different_providers.py: newedenaibranch (option 8) insetup_client()and appended toproviders_list.atomic-agents/tests/agents/test_edenai_provider.py: unit tests mirroringtest_minimax_provider.py(client setup, Instructor wrapping,AgentConfig, agent run/stream/history/system-prompt/params, env var).atomic-agents/tests/agents/test_edenai_integration.py: live integration tests mirroringtest_minimax_integration.py, skipped unlessEDENAI_API_KEYis set.README.md: Eden AI added to the Instructor-supported provider list.Testing
pytest tests/agents/test_edenai_provider.py tests/agents/test_minimax_provider.pypasses (28 tests, no regression on MiniMax).AtomicAgentworks with three upstream vendors (openai/gpt-4o-mini,anthropic/claude-haiku-4-5,mistral/mistral-small-latest), in both InstructorTOOLSandJSONmodes; the example uses the default mode. The integration tests (basic chat, multi-turn memory recall, custom output schema) pass.black --checkandflake8are clean on the changed files.