JustSong
fdb2cccf65
perf: initialize all token encoder when starting ( close #459 , close $460)
2023-08-26 13:02:02 +08:00
JustSong
a3e267df7e
fix: fix error response ( close #468 )
2023-08-26 12:37:45 +08:00
JustSong
ac7c0f3a76
fix: disable channel when 401 received ( close #467 )
2023-08-26 12:05:18 +08:00
igophper
ca512f6a38
refactor: add set event stream headers func ( #402 )
...
封装流式传输响应头的设置
2023-08-12 21:55:18 +08:00
igophper
476a46ad7e
fix: fix finish_reason fileld not fully compatible with OpenAI ( close #372 , #373 )
...
* optimize:unify finish_reason field
* refactor: use a global stop finish reason
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-08-12 11:04:53 +08:00
JustSong
0495b9a0d7
fix: using whitelist when disabling channels ( close #292 )
2023-07-22 18:15:30 +08:00
JustSong
701aaba191
feat: able to approximate token ( close #207 )
2023-07-04 19:54:13 +08:00
quzard
b09daf5ec1
chore: update countTokenMessages ( #238 )
2023-07-03 09:42:34 +08:00
JustSong
f6fe34676f
refactor: split the relay controller
2023-06-19 10:28:55 +08:00
JustSong
7c7eb6b7ec
fix: now the input field can be array type now ( close #149 )
2023-06-12 16:11:57 +08:00
JustSong
fa79e8b7a3
fix: use gpt-3.5's encoder if not found ( close #110 )
2023-05-21 11:11:19 +08:00
JustSong
3711f4a741
feat: support channel ai.ls now ( close #99 )
2023-05-19 11:07:17 +08:00
quzard
7c6bf3e97b
fix: make the token number calculation more accurate ( #101 )
...
* Make token calculation more accurate.
* fix: make the token number calculation more accurate
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com>
2023-05-19 09:41:26 +08:00
