docs: add Atlas Cloud as an OpenAI-compatible model client#7847
Open
lucaszhu-hue wants to merge 1 commit into
Open
docs: add Atlas Cloud as an OpenAI-compatible model client#7847lucaszhu-hue wants to merge 1 commit into
lucaszhu-hue wants to merge 1 commit into
Conversation
Atlas Cloud (https://www.atlascloud.ai) exposes an OpenAI-compatible API, so it works with the existing OpenAIChatCompletionClient by setting base_url — no new client implementation is needed. - add an "Atlas Cloud (experimental)" section to the Models tutorial (models.ipynb), modeled on the existing Gemini / Llama API examples: base_url + env-var api_key + explicit model_info, with a note about giving reasoning models (e.g. deepseek-ai/deepseek-v4-pro) enough max_tokens - mention Atlas Cloud as an OpenAI-compatible option in the README Extensions API description, linking to the tutorial Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Author
|
@microsoft-github-policy-service agree [company="AtlasCloud"] |
Author
|
@microsoft-github-policy-service agree company="AtlasCloud" |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Atlas Cloud exposes an OpenAI-compatible API, so it works with AutoGen's existing
OpenAIChatCompletionClientsimply by settingbase_url— no new client implementation is required. This PR documents that path.models.ipynb— adds an "Atlas Cloud (experimental)" section to the AgentChat Models tutorial, modeled on the existing Gemini and Llama API examples. It showsbase_url="https://api.atlascloud.ai/v1", an env-varapi_key(ATLAS_CLOUD_API_KEY, no hard-coded secret), and an explicitmodel_info(since Atlas serves third-party models), plus a note to give reasoning models such asdeepseek-ai/deepseek-v4-proenoughmax_tokens.README.md— one factual sentence in the Extensions API description noting OpenAI-compatible endpoints like Atlas Cloud can be used directly viaOpenAIChatCompletionClient, linking back to the tutorial.Docs-only, no code or package version changes. I deliberately kept this to documentation rather than adding a new client, since
OpenAIChatCompletionClientalready covers OpenAI-compatible providers.Validation
autogen_ext.models.openai.OpenAIChatCompletionClient:model="deepseek-ai/deepseek-v4-pro",base_url="https://api.atlascloud.ai/v1"→ response"The capital of France is Paris.",finish_reason=stop.nbformat.validate(valid, 37 cells).🤝 Partnership & contact
This PR comes from the Atlas Cloud team. Beyond the integration above, we'd love to explore a closer collaboration with AutoGen — for example co-marketing or a featured integration.
If that sounds interesting, reach out anytime:
And of course, happy to revise this PR to match your project's conventions — just leave a comment. 🙌