58dee76bf7
fix: fix Gemini stream problem
2023-12-17 16:16:18 +08:00
9ba5388367
feat: refactor response parsing logic to support multiple formats ( #782 )
...
* feat: Refactor response parsing logic to support multiple formats
The parsing logic for responses in relay.go and relay-audio.go was refactored to support multiple response formats - 'json', 'text', 'srt', 'verbose_json', and 'vtt'. The existing `WhisperResponse` struct was renamed to `WhisperJsonResponse` and a new struct `WhisperVerboseJsonResponse` was added to support the 'verbose_json' format. Additional parsing functions were added to extract text from these new response types. This change was necessary to make the parsing logic more flexible and extendable for different types of responses.
* chore: update name
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-12-10 18:39:14 +08:00
8f5b83562b
fix: fix "invalidPayload" error when request Azure dall-e-3 api without optional parameter ( #764 )
...
* fix: based on #754 add 'omitempty' in ImageRequest to fit official api reference for relay
* Revert "fix: based on #754 add 'omitempty' in ImageRequest to fit official api reference for relay"
This reverts commit b526006ce0songquanpeng@foxmail.com >
2023-12-03 17:43:30 +08:00
495fc628e4
feat: support gpt-4 with vision ( #683 , #714 )
2023-11-19 18:38:54 +08:00
76f9288c34
feat: update request struct ( close #708 )
2023-11-19 17:50:30 +08:00
969f539777
fix: skip JSON deserialization when accessing transcriptions and translations ( #718 )
...
* fix: Skip JSON deserialization when accessing transcriptions and translations.
* chore: update impl
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-11-19 16:11:39 +08:00
ddcaf95f5f
feat: support tts model ( #713 )
...
* Added support for Text-to-Speech models and
endpoints
* chore: update impl
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-11-17 21:18:51 +08:00
1d15157f7d
feat: keep sync with dall-e updates ( #679 )
...
* Updated ImageRequest struct and OpenAIModels,
added new Dall-E models and size ratios
* Fixed suspect `or`
* Refactored size ratio calculation in
relayImageHelper function
* Updated the format of resolution keys in
DalleSizeRatios map
* Added error handling for unsupported image size in
relayImageHelper function
* Added validation for number of generated images
and defined image generation ratios
* Refactored variable name from
DalleGenerationImageAmountRatios to
DalleGenerationImageAmounts
* Added validation for prompt length in
relayImageHelper function
* Updated model validation and removed size not
supported error in relayImageHelper function
* Refactored image size and model validation in
relayImageHelper function
* chore: discard binary file
* chore: update impl
---------
Co-authored-by: cktsun1031 <65409152+cktsun1031@users.noreply.github.com >
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-11-17 20:03:16 +08:00
42451d9d02
refactor: update logging related logic
2023-09-17 15:39:46 +08:00
d0a0e871e1
fix: support ali's embedding model ( #481 , close #469 )
...
* feat:支持阿里的 embedding 模型
* fix: add to model list
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com >
2023-09-03 22:12:35 +08:00
d09d317459
feat: supper whisper now ( close #197 )
2023-08-27 15:28:23 +08:00
4f2f911e4d
fix: fix the issue of function_call not working when using model mapping ( #462 )
2023-08-26 13:10:18 +08:00
ac7c0f3a76
fix: disable channel when 401 received ( close #467 )
2023-08-26 12:05:18 +08:00
1e16ef3e0d
chore: resolve conflicts
2023-08-12 11:08:52 +08:00
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
150d068e9f
chore: update prompt
2023-08-12 10:20:54 +08:00
3b36608bbd
fix: update no route handler
2023-08-11 19:53:01 +08:00
446337c329
fix: calculate usage if not given in non-stream mode ( #352 )
2023-08-06 17:40:31 +08:00
130e6bfd83
feat: support baidu's embedding model ( close #324 )
2023-07-29 12:15:07 +08:00
0495b9a0d7
fix: using whitelist when disabling channels ( close #292 )
2023-07-22 18:15:30 +08:00
2ff15baf66
feat: support claude now ( close #150 )
2023-07-22 16:18:03 +08:00
35cfebee12
feat: retry on failed ( close #112 )
2023-07-15 19:06:51 +08:00
b520b54625
feat: initial support of Dall-E ( #148 , #266 )
...
* feat: initial support of Dall-E
* fix: fix N not timed
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com >
2023-07-15 12:30:06 +08:00
81c5901123
feat: add support for /v1/engines/text-embedding-ada-002/embeddings ( #224 , close #222 )
2023-07-15 12:03:23 +08:00
abc53cb208
feat: disable channel when account_deactivated received ( close #271 )
2023-07-15 11:49:58 +08:00
0941e294bf
feat: support model remap now
2023-06-27 13:42:45 +08:00
9b178a28a3
feat: support /v1/edits now ( close #196 )
2023-06-25 11:46:23 +08:00
8a4cd403fd
fix: fix http status code ( close #193 )
2023-06-23 22:59:44 +08:00
00151a0124
chore: format logs
2023-06-22 10:59:01 +08:00
33846ce4f6
refactor: rename function
2023-06-19 15:00:22 +08:00
f6fe34676f
refactor: split the relay controller
2023-06-19 10:28:55 +08:00
46c43396d8
feat: add token name to log ( #172 )
...
* add token name to log
* chore: update expression
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-06-17 14:56:03 +08:00
70ed126ccb
feat: return a not found response if requested a wrong API endpoints
2023-06-17 09:46:07 +08:00
0cdab80a6e
feat: record channel's used quota ( close #137 )
2023-06-16 16:02:00 +08:00
760183a970
feat: record used quota & request count ( close #102 , #165 )
2023-06-16 15:20:06 +08:00
58fb18aace
fix: do not record completion ratio anymore
2023-06-16 14:24:16 +08:00
630156dc0a
fix: the prompt field can be array type now ( close #166 , #167 )
...
* fix: the prompt field can be array type now (close #166 )
* fix: fix prompt type
---------
Co-authored-by: JustSong <songquanpeng@foxmail.com >
2023-06-16 14:20:25 +08:00
e87ad1f402
chore: remove -0613 suffix for Azure ( #163 )
2023-06-14 16:33:03 +08:00
38668e7331
chore: update gpt3.5 completion ratio
2023-06-14 09:41:06 +08:00
7c7eb6b7ec
fix: now the input field can be array type now ( close #149 )
2023-06-12 16:11:57 +08:00
077853416d
chore: record ratio detail in log
2023-06-11 11:11:19 +08:00
596446dba4
feat: able to set group ratio now ( close #62 , close #142 )
2023-06-11 11:08:16 +08:00
9d0bec83df
chore: update prompt
2023-06-11 09:55:50 +08:00
f97a9ce597
fix: correct OpenAI error code's type
2023-06-11 09:49:57 +08:00
4339f45f74
feat: support /v1/moderations now ( close #117 )
2023-06-11 09:37:36 +08:00
74f508e847
feat: now user can check its topup & consume history ( close #78 , close #95 )
2023-06-10 16:04:04 +08:00
8901f03864
feat: support set proxy for channel OpenAI ( close #139 )
2023-06-09 18:30:01 +08:00
4b6adaec0b
feat: support /v1/completions ( close #115 )
2023-06-08 14:54:02 +08:00
2ad22e1425
feat: support group now ( close #17 , close #72 , close #85 , close #104 , close #136 )
...
Co-authored-by: quzard <1191890118@qq.com >
2023-06-07 23:26:00 +08:00
d9e39f5906
fix: disable channel with a whitelist
2023-05-21 20:58:00 +08:00
JustSong