Skip to content

feat(api): support multimodal structured generation #218

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
svonava wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat(api): support multimodal structured generation #218

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
cd8b684
feat(sdk): add multimodal structured generation
svonava Jul 23, 2026
ed7c8b5
feat(api): support multimodal structured generation
svonava Jul 23, 2026
174a93e
fix(sdk): preserve generate compatibility
svonava Jul 23, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 38 additions & 1 deletion packages/sie_gateway/openapi.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1518,6 +1518,18 @@
"grammar": {
"description": "Optional grammar object accepted by the gateway grammar validator."
},
"images": {
"description": "Optional inline images paired with ``prompt``. When present, the worker\nrenders one user turn through the model's native chat template.",
"items": {
"$ref": "#/components/schemas/NativeGenerateImage"
},
"maxItems": 16,
"minItems": 1,
"type": [
"array",
"null"
]
},
"logit_bias": {
"additionalProperties": {
"format": "double",
Expand Down Expand Up @@ -2268,6 +2280,31 @@
],
"type": "object"
},
"NativeGenerateImage": {
"description": "One inline image on the SIE-native generate surface.",
"properties": {
"data": {
"description": "Canonical standard-base64 encoded image bytes, at most 16 MiB decoded.\nRemote URLs are not accepted.",
"maxLength": 22369624,
"minLength": 1,
"type": "string"
},
"format": {
"description": "Short media-format hint such as ``png`` or ``jpeg``.",
"maxLength": 32,
"minLength": 1,
"pattern": "^[A-Za-z0-9.+-]+$",
"type": [
"string",
"null"
]
}
},
"required": [
"data"
],
"type": "object"
},
"OpenAIEmbeddingDataEntry": {
"properties": {
"embedding": {
Expand Down Expand Up @@ -5853,7 +5890,7 @@
},
"/v1/generate/{model}": {
"post": {
"description": "SIE-native text generation. Omit `stream` or set it to false for a blocking JSON response; set `stream: true` for SIE-native Server-Sent Events terminated by `data: [DONE]`. The model path parameter must use the SIE-safe ID (for example `Qwen__Qwen3-4B-Instruct`); HF-style slashes reject with 400.",
"description": "SIE-native generation with optional bounded inline images. Omit `stream` or set it to false for a blocking JSON response; set `stream: true` for SIE-native Server-Sent Events terminated by `data: [DONE]`. The model path parameter must use the SIE-safe ID (for example `Qwen__Qwen3-4B-Instruct`); HF-style slashes reject with 400.",
"operationId": "proxy_generate",
"parameters": [
{
Expand Down
Loading