yym68686 commited on
Commit
f67c99b
·
1 Parent(s): d6768b9

📖 Docs: Update documentation

Browse files
Files changed (2) hide show
  1. README.md +21 -0
  2. README_CN.md +21 -0
README.md CHANGED
@@ -399,6 +399,27 @@ The channel-level timeout setting has higher priority than the global model time
399
 
400
  By adjusting the model timeout time, you can avoid the error of some channels timing out. If you encounter the error `{'error': '500', 'details': 'fetch_response_stream Read Response Timeout'}`, please try to increase the model timeout time.
401
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
402
  ## ⭐ Star History
403
 
404
  <a href="https://github.com/yym68686/uni-api/stargazers">
 
399
 
400
  By adjusting the model timeout time, you can avoid the error of some channels timing out. If you encounter the error `{'error': '500', 'details': 'fetch_response_stream Read Response Timeout'}`, please try to increase the model timeout time.
401
 
402
+ - How does api_key_rate_limit work? How do I set the same rate limit for multiple models?
403
+
404
+ If you want to set the same frequency limit for the four models gemini-1.5-pro-latest, gemini-1.5-pro, gemini-1.5-pro-001, gemini-1.5-pro-002 simultaneously, you can set it like this:
405
+
406
+ ```yaml
407
+ api_key_rate_limit:
408
+ gemini-1.5-pro: 1000/min
409
+ ```
410
+
411
+ This will match all models containing the gemini-1.5-pro string. The frequency limit for these four models, gemini-1.5-pro-latest, gemini-1.5-pro, gemini-1.5-pro-001, gemini-1.5-pro-002, will all be set to 1000/min. The logic for configuring the api_key_rate_limit field is as follows, here is a sample configuration file:
412
+
413
+ ```yaml
414
+ api_key_rate_limit:
415
+ gemini-1.5-pro: 1000/min
416
+ gemini-1.5-pro-002: 500/min
417
+ ```
418
+
419
+ At this time, if there is a request using the model gemini-1.5-pro-002.
420
+
421
+ First, the uni-api will attempt to precisely match the model in the api_key_rate_limit. If the rate limit for gemini-1.5-pro-002 is set, then the rate limit for gemini-1.5-pro-002 is 500/min. If the requested model at this time is not gemini-1.5-pro-002, but gemini-1.5-pro-latest, since the api_key_rate_limit does not have a rate limit set for gemini-1.5-pro-latest, it will look for any model with the same prefix as gemini-1.5-pro-latest that has been set, thus the rate limit for gemini-1.5-pro-latest will be set to 1000/min.
422
+
423
  ## ⭐ Star History
424
 
425
  <a href="https://github.com/yym68686/uni-api/stargazers">
README_CN.md CHANGED
@@ -399,6 +399,27 @@ api_keys:
399
 
400
  通过调整模型超时时间,可以避免出现某些渠道请求超时报错的情况。如果你遇到 `{'error': '500', 'details': 'fetch_response_stream Read Response Timeout'}` 错误,请尝试增加模型超时时间。
401
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
402
  ## ⭐ Star 历史
403
 
404
  <a href="https://github.com/yym68686/uni-api/stargazers">
 
399
 
400
  通过调整模型超时时间,可以避免出现某些渠道请求超时报错的情况。如果你遇到 `{'error': '500', 'details': 'fetch_response_stream Read Response Timeout'}` 错误,请尝试增加模型超时时间。
401
 
402
+ - api_key_rate_limit 是怎么工作的?我如何给多个模型设置相同的频率限制?
403
+
404
+ 如果你想同时给 gemini-1.5-pro-latest,gemini-1.5-pro,gemini-1.5-pro-001,gemini-1.5-pro-002 这四个模型设置相同的频率限制,可以这样设置:
405
+
406
+ ```yaml
407
+ api_key_rate_limit:
408
+ gemini-1.5-pro: 1000/min
409
+ ```
410
+
411
+ 这会匹配所有含有 gemini-1.5-pro 字符串的模型。gemini-1.5-pro-latest,gemini-1.5-pro,gemini-1.5-pro-001,gemini-1.5-pro-002 这四个模型频率限制都会设置为 1000/min。api_key_rate_limit 字段配置的逻辑如下,这是一个示例配置文件:
412
+
413
+ ```yaml
414
+ api_key_rate_limit:
415
+ gemini-1.5-pro: 1000/min
416
+ gemini-1.5-pro-002: 500/min
417
+ ```
418
+
419
+ 此时如果有一个使用模型 gemini-1.5-pro-002 的请求。
420
+
421
+ 首先,uni-api 会尝试精确匹配 api_key_rate_limit 的模型。如果刚好设置了 gemini-1.5-pro-002 的频率限制,则 gemini-1.5-pro-002 的频率限制则为 500/min,如果此时请求的模型不是 gemini-1.5-pro-002,而是 gemini-1.5-pro-latest,由于 api_key_rate_limit 没有设置 gemini-1.5-pro-latest 的频率限制,因此会寻找有没有前缀和 gemini-1.5-pro-latest 相同的模型被设置了,因此 gemini-1.5-pro-latest 的频率限制会被设置为 1000/min。
422
+
423
  ## ⭐ Star 历史
424
 
425
  <a href="https://github.com/yym68686/uni-api/stargazers">