docs: add Atlas Cloud as an OpenAI-compatible LLM + VLM option#98
Open
lucaszhu-hue wants to merge 1 commit into
Open
docs: add Atlas Cloud as an OpenAI-compatible LLM + VLM option#98lucaszhu-hue wants to merge 1 commit into
lucaszhu-hue wants to merge 1 commit into
Conversation
FireRed-OpenStoryline drives its `[llm]` and `[vlm]` backends through a
standard OpenAI-compatible `chat/completions` endpoint configured in
config.toml. Atlas Cloud exposes the same interface, so a single base_url
+ API key can serve both the text LLM (script planning/scheduling) and
the multimodal VLM (clip understanding).
- docs/source/{en,zh}/api-key.md: add an Atlas Cloud section showing the
config.toml snippet for `[llm]` (deepseek-ai/deepseek-v4-pro) and
`[vlm]` (qwen/qwen3-vl-30b-a3b-instruct) plus the full chat model list.
- README.md / README_zh.md: add a short Atlas Cloud note near the top.
Verified against the live API: chat/completions returns HTTP 200 for both
the LLM model and the VLM model (with an image input).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
FireRed-OpenStoryline already drives its
[llm]and[vlm]backends through a standard OpenAI-compatiblechat/completionsendpoint configured inconfig.toml(vialangchain_openai.ChatOpenAI). This PR documents Atlas Cloud as one such backend — it exposes exactly that interface, so a singlebase_url+ API key can serve both stages:deepseek-ai/deepseek-v4-proqwen/qwen3-vl-30b-a3b-instructNo per-vendor accounts and no code changes — it plugs into the existing custom-model path.
Changes
docs/source/en/api-key.md&docs/source/zh/api-key.md: new Atlas Cloud section with theconfig.tomlsnippet for[llm]/[vlm]and the full chat model list (folded).README.md&README_zh.md: a short note near the top linking to the config doc.assets/atlas-cloud-logo.png: logo used in the README note.Verification
Tested against the live API; both calls return HTTP 200:
POST /v1/chat/completionswithdeepseek-ai/deepseek-v4-pro→ text reply.POST /v1/chat/completionswithqwen/qwen3-vl-30b-a3b-instruct+ an image input → correct visual description.Notes
Docs-only (plus one logo asset). Atlas Cloud is a full-modal, OpenAI-compatible inference platform; beyond the two models above it also serves GLM, Kimi, MiniMax, Claude, Gemini, and image/video generation APIs that could be reused for the AI-transition step. Happy to adjust wording/placement to fit the project's style.
🤖 Generated with Claude Code