yumoqing
146ebb2b4a
- wwwroot/v1/video/generations/index.dspy: video generation endpoint Required params: model, llmcatelogid, prompt Supports async task submission via existing inference infrastructure - wwwroot/v1/image/generations/index.dspy: image generation endpoint Required params: model, llmcatelogid, prompt Supports both sync and async models depending on config Both endpoints follow the same pattern as /v1/chat/completions: 1. Validate required params (model + llmcatelogid + prompt) 2. Look up llm via llm_api_map join with catalog type 3. Check customer balance 4. Route to inference (async/sync based on model config)
88 lines
2.4 KiB
Plaintext
88 lines
2.4 KiB
Plaintext
# OpenAI-compatible Video Generation API
|
|
# POST /v1/video/generations
|
|
# Required params: model, llmcatelogid
|
|
# Optional params: prompt, image_url, duration, resolution, n, etc.
|
|
#
|
|
# Example request:
|
|
# {
|
|
# "model": "keling-2.1",
|
|
# "llmcatelogid": "文生视频",
|
|
# "prompt": "A beautiful sunset over the ocean",
|
|
# "duration": "5s",
|
|
# "resolution": "1080p"
|
|
# }
|
|
#
|
|
# Response (async task):
|
|
# {
|
|
# "id": "vid_xxx",
|
|
# "object": "video.generation",
|
|
# "model": "keling-2.1",
|
|
# "status": "submitted",
|
|
# "taskid": "task_xxx",
|
|
# "created": 1234567890
|
|
# }
|
|
|
|
import json
|
|
import time
|
|
from functools import partial
|
|
from appPublic.log import debug
|
|
from appPublic.dictObject import DictObject
|
|
from appPublic.uniqueID import getID
|
|
from appPublic.timeUtils import curDateString, timestampstr
|
|
from sqlor.dbpools import get_sor_context
|
|
|
|
debug(f'{params_kw=}')
|
|
|
|
userid = await get_user()
|
|
userorgid = await get_userorgid()
|
|
if userid is None:
|
|
debug('need login')
|
|
return openai_403()
|
|
|
|
# Validate required parameters
|
|
if not params_kw.model:
|
|
d = return_error('Missing required parameter: model')
|
|
return json_response(d, status=400)
|
|
|
|
if not params_kw.llmcatelogid:
|
|
d = return_error('Missing required parameter: llmcatelogid')
|
|
return json_response(d, status=400)
|
|
|
|
if not params_kw.prompt:
|
|
d = return_error('Missing required parameter: prompt')
|
|
return json_response(d, status=400)
|
|
|
|
lctype = params_kw.llmcatelogid
|
|
|
|
env = request._run_ns
|
|
async with get_sor_context(env, 'llmage') as sor:
|
|
# Look up llm by model name and catalog type through llm_api_map
|
|
sql = """select distinct a.* from llm a
|
|
join llm_api_map m on a.id = m.llmid
|
|
join llmcatelog b on m.llmcatelogid = b.id
|
|
where b.name = ${lctype}$
|
|
and a.model=${model}$"""
|
|
recs = await sor.sqlExe(sql, {
|
|
'lctype': lctype,
|
|
'model': params_kw.model
|
|
})
|
|
if len(recs) == 0:
|
|
debug(f'{params_kw.model=} not found for catalog {lctype}')
|
|
return openai_400()
|
|
params_kw.llmid = recs[0].id
|
|
|
|
debug(f'{params_kw.llmid=}')
|
|
|
|
# Check balance
|
|
f = await checkCustomerBalance(params_kw.llmid, userid, userorgid)
|
|
if not f:
|
|
debug(f'{userid=} balance not enough')
|
|
return openai_429()
|
|
|
|
# Generate task ID and attach to params
|
|
if not params_kw.transno:
|
|
params_kw.transno = getID()
|
|
|
|
# Call inference (video/image generation is typically async via callback)
|
|
return await inference(request, env=env)
|