refac
Python CI / Ruff Format (3.11) (push) Has been cancelled
Python CI / Ruff Format (3.12) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true USE_CUDA_VER=cu126 free_disk:true name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true USE_CUDA_VER=cu126 free_disk:true name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:slim suffix:-slim]) (push) Has been cancelled
Create and publish Docker images with specific build args / notify-helm-charts (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (, main) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-cuda, cuda) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-cuda126, cuda126) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-ollama, ollama) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-slim, slim) (push) Has been cancelled
Frontend Build / Format & Build (push) Has been cancelled
Frontend Build / Unit Tests (push) Has been cancelled

This commit is contained in:
Timothy Jaeryang Baek
2026-07-15 02:53:39 -04:00
parent 622767d724
commit 04311d559d
3 changed files with 26 additions and 2 deletions
+10
View File
@@ -313,6 +313,16 @@ async def update_config(
'ollama.api_configs': api_configs,
}
)
await get_all_models.cache.clear()
request.app.state.BASE_MODELS = []
request.app.state.OLLAMA_MODELS = {}
models = getattr(request.app.state, 'MODELS', None)
if hasattr(models, 'clear'):
models.clear()
else:
request.app.state.MODELS = {}
await publish_event(
request,
EVENTS.MODEL_PROVIDER_CONFIG_UPDATED,
+14
View File
@@ -418,6 +418,16 @@ async def update_config(request: Request, form_data: OpenAIConfigForm, user=Depe
'openai.api_configs': api_configs,
}
)
await get_all_models.cache.clear()
request.app.state.BASE_MODELS = []
request.app.state.OPENAI_MODELS = {}
models = getattr(request.app.state, 'MODELS', None)
if hasattr(models, 'clear'):
models.clear()
else:
request.app.state.MODELS = {}
await publish_event(
request,
EVENTS.MODEL_PROVIDER_CONFIG_UPDATED,
@@ -636,6 +646,7 @@ async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
enable_openai_api, api_base_urls, _, api_configs = await get_openai_runtime_config()
if not enable_openai_api:
request.app.state.OPENAI_MODELS = {}
return {'data': []}
responses = await get_all_models_responses(request, user=user)
@@ -1192,6 +1203,9 @@ async def generate_chat_completion(
form_data: dict,
user=Depends(get_verified_user),
):
if not await Config.get('openai.enable'):
raise HTTPException(status_code=503, detail='OpenAI API is disabled')
# NOTE: We intentionally do NOT use Depends(get_async_session) here.
# Database operations (get_model_by_id, AccessGrants.has_access) manage their own short-lived sessions.
# This prevents holding a connection during the entire LLM call (30-60+ seconds),
@@ -38,9 +38,9 @@
</script>
<div
class="my-2 flex w-full items-center gap-3 rounded-3xl bg-gray-100 px-4 py-3 text-gray-800 dark:bg-gray-800 dark:text-gray-100"
class="my-2 flex w-full items-center gap-3 rounded-3xl bg-black/[0.03] px-4 py-3 text-gray-500 dark:bg-white/[0.04] dark:text-gray-400"
>
<Info className="size-5 shrink-0" strokeWidth="2" />
<Info className="size-5 shrink-0 text-gray-400 dark:text-gray-500" strokeWidth="2" />
<div class="min-w-0 self-center break-words text-sm">
{message}