mstar.api_server.openai.router

FastAPI routes for the OpenAI-compatible API.

Endpoints stay model-agnostic: each looks up the loaded model’s adapter, checks the surface is supported, and delegates to a serving handler. The native /generate endpoint is unaffected.

Functions

audio_speech(request, raw_request)
chat_completions(request, raw_request)
images_edits(request)
images_generations(request, raw_request)
list_models()
videos_generations(request)

async mstar.api_server.openai.router.audio_speech(request, raw_request)

Parameters:

• request (SpeechRequest)

• raw_request (Request)

async mstar.api_server.openai.router.chat_completions(request, raw_request)

Parameters:

• request (ChatCompletionRequest)

• raw_request (Request)

async mstar.api_server.openai.router.images_edits(request)

Parameters:

request (Request)

async mstar.api_server.openai.router.images_generations(request, raw_request)

Parameters:

• request (ImageGenerationRequest)

• raw_request (Request)

async mstar.api_server.openai.router.list_models()

async mstar.api_server.openai.router.videos_generations(request)

Parameters:

request (VideoGenerationRequest)