mirror of
https://github.com/JefferyHcool/BiliNote.git
synced 2026-09-05 23:56:59 +08:00
fix(backend): 部署韧性——模型自愈/就绪门禁/全局代理/启动诊断
- whisper: model.bin 截断/损坏时删目录重下重试一次,修「Unable to
open file model.bin」死循环;mlx 同样按 config.json 判完整性
- /generate_note 加就绪门禁:本地转写引擎模型没下好直接拦截,返回
reason=transcriber_model_not_ready,不让任务静默卡在首次下载
- 全局代理:新增 ProxyConfigManager(JSON 配置 + HTTP_PROXY env 兜底)
+ build_openai_client,统一注入代理到 LLM/Groq 客户端;yt-dlp 与
youtube-transcript-api 也走代理
- build_openai_client 校验 api_key 非空,空 key 给「xxx 的 API Key
未配置」而不是天书般的 Illegal header value b'Bearer '
- universal_gpt: 模型拒绝自定义 temperature(o1/o3/gpt-5 系列)时
就地去掉参数重试,不消耗重试预算
- connect_test 改用真实 chat completion 而非 /v1/models 探测
- main.py: lifespan 拆 [startup 1/5..5/5] 分段日志 + 异常清晰定位
- /sys_health 重构为结构化返回 {backend,ffmpeg,db,whisper_model}
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.7
parent
88d25f8cc1
commit
41f17592c2
@@ -1,13 +1,13 @@
|
||||
from typing import Optional, Union
|
||||
|
||||
from openai import OpenAI
|
||||
|
||||
from app.utils.logger import get_logger
|
||||
from app.utils.openai_client import build_openai_client
|
||||
|
||||
logging= get_logger(__name__)
|
||||
class OpenAICompatibleProvider:
|
||||
def __init__(self, api_key: str, base_url: str, model: Union[str, None]=None):
|
||||
self.client = OpenAI(api_key=api_key, base_url=base_url)
|
||||
# build_openai_client:注入全局代理 + 校验 api_key 非空
|
||||
self.client = build_openai_client(api_key, base_url, key_label="模型供应商的 API Key")
|
||||
self.model = model
|
||||
|
||||
@property
|
||||
@@ -15,17 +15,27 @@ class OpenAICompatibleProvider:
|
||||
return self.client
|
||||
|
||||
@staticmethod
|
||||
def test_connection(api_key: str, base_url: str) -> bool:
|
||||
def test_connection(api_key: str, base_url: str, model: str) -> bool:
|
||||
"""发一条最小化 chat completion 验证 key / base_url / model 三方都通。
|
||||
|
||||
为什么不用 client.models.list():
|
||||
- 部分代理 / 自建供应商不实现 /v1/models(如某些 OpenAI 兼容网关)
|
||||
- 部分供应商 key 在没有 inference 权限时 /v1/models 仍返回 200
|
||||
最终用户跑的就是 chat.completions.create,所以直接测它最忠实。
|
||||
max_tokens=1 + temperature=0 让请求开销 < 0.0001 美元、延迟 < 2s。
|
||||
"""
|
||||
try:
|
||||
client = OpenAI(api_key=api_key, base_url=base_url)
|
||||
model = client.models.list()
|
||||
# for segment in model:
|
||||
# print(segment)
|
||||
# print(model)
|
||||
logging.info("连通性测试成功")
|
||||
client = build_openai_client(
|
||||
api_key, base_url, key_label="模型供应商的 API Key", timeout=15.0,
|
||||
)
|
||||
client.chat.completions.create(
|
||||
model=model,
|
||||
messages=[{"role": "user", "content": "ping"}],
|
||||
max_tokens=1,
|
||||
temperature=0,
|
||||
)
|
||||
logging.info(f"连通性测试成功(model={model})")
|
||||
return True
|
||||
except Exception as e:
|
||||
logging.info(f"连通性测试失败:{e}")
|
||||
|
||||
# print(f"Error connecting to OpenAI API: {e}")
|
||||
logging.warning(f"连通性测试失败(model={model}):{e}")
|
||||
return False
|
||||
Reference in New Issue
Block a user