Ecosystem/ai-gateway
5
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
987 Commits 5 Branches 367 Tags 62 MiB
04bb3ef392
Commit Graph

342 Commits

Author SHA1 Message Date
JustSong
cece77e533 fix: fix model list 2024-02-19 22:20:18 +08:00
JustSong
2acc2f5017 feat: support moonshot now (close #804) 2024-02-18 16:17:19 +08:00
JustSong
1aa374ccfb refactor: use adaptor to do relay & test 2024-02-18 00:15:31 +08:00
Laisky.Cai
d548a01c59
feat: Handle errors, validate model names, and calculate quota usage (#978) 
- Improved error handling in various modules for better stability and responsiveness.
- Optimized code in several files for improved efficiency and readability.
- Enhanced user experience by providing more detailed error responses in the controller.
- Strengthened security by ignoring sensitive files in `.gitignore`.
 2024-02-12 21:35:40 +08:00
JustSong
2cd1a78203 chore: update module name 2024-01-28 19:38:58 +08:00
JustSong
b9d3cb0c45 refactor: split RelayTextHelper function 2024-01-28 19:14:46 +08:00
Benny
26e2e646cb
feat: sync models with OpenAI (#971) 
* add new 0125 chat models and embedding-3 models

* refine the step of manually deploying

* add gpt-4-turbo-preview
 2024-01-28 16:09:21 +08:00
JustSong
2d760d4a01
refactor: refactor relay part (#957) 
* refactor: refactor relay part

* refactor: refactor config part
 2024-01-21 23:21:42 +08:00
JustSong
eed9f5fdf0
refactor: refactor relay part (#935) 2024-01-14 19:21:03 +08:00
JustSong
bdd4be562d chore: add theme validation 2024-01-07 18:44:26 +08:00
Buer
48989d4a0b
feat: add new theme berry (#860) 
* feat: add theme berry

* docs: add development notes

* fix: fix blank page

* chore: update implementation

* fix: fix package.json

* chore: update ui copy

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-01-07 14:20:07 +08:00
Tailen
498dea2dbb
feat: add support for davinci-002 and babbage-002 (#888) 2024-01-01 17:06:17 +08:00
Tisfeng
af8908db54
feat: able to change gemini safety setting (#867) 
* perf: adjust gemini safety settings, set BLOCK_NONE by default

* feat: able to adjust by env variable

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2024-01-01 16:42:19 +08:00
JustSong
d8029550f7 fix: do not consume user quota if failed (close #881) 2024-01-01 16:18:50 +08:00
JustSong
1c8922153d feat: support gemini-vision-pro 2023-12-24 18:54:32 +08:00
Laisky.Cai
f3c07e1451
fix: openai response should contains model (#841) 
* fix: openai response should contains `model`

- Update model attributes in `claudeHandler` for `relay-claude.go`
- Implement model type for fullTextResponse in `relay-gemini.go`
- Add new `Model` field to `OpenAITextResponse` struct in `relay.go`

* chore: set model name response for models

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-24 16:58:31 +08:00
moondie
ee9e746520
feat: update ali stream implementation & enable internet search (#856) 
* Update relay-ali.go: 改进stream模式，添加联网搜索能力

通义千问支持stream的增量模式，不需要每次去掉上次的前缀；实测qwen-max联网模式效果不错，添加了联网模式。如果别的模型有问题可以改为单独给qwen-max开放

* 删除"stream参数"

刚发现原来阿里api没有这个参数，上次误加了。

* refactor: only enable search when specified

* fix: remove custom suffix when get model ratio

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-24 16:17:21 +08:00
JustSong
67c64e71c8 fix: fix max_tokens check 2023-12-20 21:45:33 +08:00
JustSong
97030e27f8 fix: fix gemini panic (close #833) 2023-12-17 23:30:45 +08:00
ShinChven ✨
bc6769826b
feat: add condition to validate n value for non-Azure channels (#775) 
- Add a condition to validate the n value only for non-Azure channels, ensuring it falls within the acceptable range.
- Fix Azure compatibility
 2023-12-17 19:49:08 +08:00
Oliver Lee
0fe26cc4bd
feat: update ali relay implementation (#830) 
* 修改通译千问最新接口：1.删除history参数，改用官方推荐的messages参数 2.整理messages参数顺序，补充必要上下文信息 3.用autogen调试测试通过

* chore: update impl

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-17 19:43:23 +08:00
Ghostz
66f06e5d6f
feat: reset image num to 1 when not given (#821) 
* Update relay-image.go

* fix: reset image num to 1 when not given

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-17 18:54:08 +08:00
JustSong
6acb9537a9 fix: try to return a more meaningful error message (close #817) 2023-12-17 18:33:27 +08:00
JustSong
7069c49bdf fix: fix xunfei panic error (close #820) 2023-12-17 18:06:37 +08:00
JustSong
58dee76bf7 fix: fix Gemini stream problem 2023-12-17 16:16:18 +08:00
David Zhuang
5cf23d8698
feat: add Google Gemini Pro support (#826) 
* fest: Add Google Gemini Pro, fix #810

* fest: Add tooling to Gemini; Add OpenAI-like system prompt to Gemini

* refactor: removing unused if statement

* fest: Add dummy model message for system message in gemini model

* chore: update implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-17 12:48:32 +08:00
JustSong
366b82128f fix: remove incorrect logging 2023-12-10 20:44:37 +08:00
Qiying Wang
4c5feee0b6
feat: add image counter for gpt-4 vision (#795) 2023-12-10 19:39:46 +08:00
igophper
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
JustSong
379074f7d0 feat: support plugin for ali channel (close #797) 2023-12-10 17:22:52 +08:00
Tillman Bailee
a3f80a3392
feat: enable channel when test succeed (#771) 
* 增加功能: 渠道 - 测试所有通道; 设置 - 运营设置 - 监控设置 - 成功时自动启用通道

* refactor: update implementation

---------

Co-authored-by: liyujie <29959257@qq.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-03 20:10:57 +08:00
Zhengyi Dong
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 b526006ce0.

* fix: add missing omitempty

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-03 17:43:30 +08:00
ShinChven ✨
b7570d5c77
feat: support dalle for Azure (#754) 
* feat: Add Message-ID to email headers to comply with RFC 5322

- Extract domain from SMTPFrom
- Generate a unique Message-ID
- Add Message-ID to email headers

* chore: check slice length

* feat: Add Azure compatibility for relayImageHelper

- Handle Azure channel requestURL compatibility
- Set api-key header for Azure channel authentication
- Handle Azure channel request body

fixes: https://github.com/songquanpeng/one-api/issues/751

* refactor: update implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-12-03 17:34:59 +08:00
JustSong
0e73418cdf fix: fix log recording & error handling for relay-audio 2023-11-26 12:05:16 +08:00
JustSong
9889377f0e feat: support claude-2.x (close #736) 2023-11-24 21:39:44 +08:00
Ian Li
3347a44023
feat: support Azure's Whisper model (#720) 2023-11-24 21:10:18 +08:00
igophper
d85e356b6e
refactor: remove consumeQuota related logic (#738) 
* feat: 删除relay-text中的consumeQuota变量

该变量始终为true，可以删除

* chore: remove useless code

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-24 20:42:29 +08:00
JustSong
495fc628e4 feat: support gpt-4 with vision (#683, #714) 2023-11-19 18:38:54 +08:00
JustSong
76f9288c34 feat: update request struct (close #708) 2023-11-19 17:50:30 +08:00
Ian Li
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
Buer
54e5f8ecd2
feat: support cloudflare gateway for azure (#666) 
* 🐛 Fix cloudflare gateway request failure

* 🐛 fix channel test url error
 2023-11-19 15:52:35 +08:00
Mikey
34d517cfa2
fix: cloudflare test & expose detailed info about test failures (#715) 
* fix: cloudflare test & expose detailed info about test failures

* fix: cloudflare test & expose detailed info about test failures

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-17 21:45:55 +08:00
ckt1031
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
ckt1031
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
管宜尧
de7b9710a5
fix: fix PaLM not working issue (#667) 
* bugfix for #515 最新版本谷歌PaLM模型无法使用

* update

* chore: remove unrelated file

* chore: add comment

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-17 19:40:59 +08:00
Mikey
9d43ec57d8
feat: sync pricing for new 1106 models (#696) 
* feat: sync pricing for new 1106 models

* chore: change ratio after 2023-12-11

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-10 21:08:23 +08:00
wzxjohn
bc7c9105f4
chore: update quota calc logic (close #599) (#627) 
* fix: change quota calc code (close #599)

Use float64 during calc and do math.Ceil after calc. This will result in the quota being used slightly more than the official standard, but it will be guaranteed that it will not be less.

* chore: remove blank line

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-05 19:15:06 +08:00
wood chen
3fe76c8af7
fix: fix Cloudflare AI Gateway channel test support (#639) 
* 当使用Cloudflare AI Gateway时，支持openai渠道测试

* refactor: change logic

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-11-05 19:08:25 +08:00
papersnake
c70c614018
feat: support chatglm_turbo (#648) 
* feat: support chatglm_turbo

* fix: remove characterglm
 2023-11-05 17:59:38 +08:00
Baksi
0d87de697c
fix: fix typo (#651) 2023-11-02 22:24:22 +08:00
MaricoHan
aec343dc38
feat: support xunfei v3 (#637) 2023-10-29 22:03:01 +08:00
JustSong
89d458b9cf feat: able to set RELAY_TIMEOUT 2023-10-22 20:39:49 +08:00
JustSong
63fafba112 feat: support ERNIE-Bot-4 (close #608) 2023-10-22 18:48:35 +08:00
yiGmMk
57aa637c77
fix: set Accept header if not given (#615) 
* fix: fastgpt调用通义千问问答失败

* refactor: Dockerfile

* Revert "refactor: Dockerfile"

This reverts commit a538c4f28e.

* chore: update implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-10-22 17:56:20 +08:00
vc
3b483639a4
feat: add cloudflare ai gateway support for image & audio (#607) 
* Update channel-test.go

* Update relay-audio.go

* Update relay-image.go

* chore: using a util function

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-10-22 17:50:52 +08:00
JustSong
824444244b feat: able to delete all disabled channels 2023-10-14 17:25:48 +08:00
JustSong
a27a5bcc06 fix: fix array index not checked (close #588) 2023-10-14 16:11:15 +08:00
JustSong
e28d4b1741 feat: support cloudflare AI gateway now (close #565, #598) 2023-10-14 15:26:28 +08:00
JustSong
b4b4acc288 feat: support Tencent's model (close #519) 2023-10-03 14:19:03 +08:00
JustSong
a85ecace2e chore: delete 360's 360GPT_S2_V9.4 2023-10-03 12:51:53 +08:00
JustSong
8d34b7a77e feat: able to delete all manually disabled channels (close #539) 2023-10-02 13:06:27 +08:00
JustSong
47c08c72ce fix: check user quota when pre-consume quota 2023-10-01 12:49:40 +08:00
JustSong
594f06e7b0 perf: lazy initialization for token encoders (close #566) 2023-09-29 17:56:11 +08:00
JustSong
fd98463611 chore: update ali's model name 2023-09-23 22:57:59 +08:00
JustSong
f5a1cd3463 feat: add support for gpt-3.5-turbo-instruct (close #545) 2023-09-23 22:37:11 +08:00
JustSong
159b9e3369 fix: fix unable to set zero value for base url & model mapping 2023-09-18 22:07:17 +08:00
Xyfacai
ecf8a6d875
feat: supprt channel priority now & record channel id in log (#484) 
* feat: 支持设置渠道优先级 & 日志中显示使用的渠道ID

* fix: 设置渠道优先级未更新 ability

* chore: update implementation

---------

Co-authored-by: Xiangyuan Liu <xiangyuan.liu@ui.com>
Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
 2023-09-17 19:18:16 +08:00
igophper
24df3e5f62
feat: support non-stream mode for xunfei (#498) 
* feat:xunfei suport none stream

* fix:join content ignore seq

---------

Co-authored-by: igophper <admin@jialilgu.cn>
 2023-09-17 18:16:12 +08:00
JustSong
328aa68255 feat: able to delete logs now (close #486) 2023-09-17 17:09:56 +08:00
JustSong
42451d9d02 refactor: update logging related logic 2023-09-17 15:39:46 +08:00
JustSong
959bcdef88 chore: update error code 2023-09-17 11:30:20 +08:00
JustSong
39ae8075e4 fix: fix oauth2 state not checking 2023-09-15 00:24:20 +08:00
JustSong
420c375140 perf: only return quota when it's not zero 2023-09-13 22:05:10 +08:00
JustSong
01863d3e44 fix: fix quota not return when error occurred (close #518) 2023-09-13 21:50:45 +08:00
igophper
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
JustSong
a721a5b6f9 chore: add error prompt for Azure 2023-09-03 21:46:07 +08:00
JustSong
621eb91b46 chore: pass through error out 2023-09-03 21:31:58 +08:00
JustSong
04acdb1ccb feat: support aiproxy's library 2023-09-03 12:51:59 +08:00
JustSong
abbf2fded0 perf: preallocate array capacity 2023-08-30 21:15:56 +08:00
JustSong
56b5007379 feat: supper OpenRouter now (close #333, close #340) 2023-08-27 16:16:45 +08:00
JustSong
d09d317459 feat: supper whisper now (close #197) 2023-08-27 15:28:23 +08:00
JustSong
1c4409ae80 Merge branch 'main' of https://github.com/songquanpeng/one-api 2023-08-26 13:36:58 +08:00
JustSong
5ee24e8acf feat: support 360's models (close #331, close #461) 
feat: support 360's models (close #331, close #461)
 2023-08-26 13:36:20 +08:00
shao0222
4f2f911e4d
fix: fix the issue of function_call not working when using model mapping (#462) 2023-08-26 13:10:18 +08:00
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
glzjin
efeb9a16ce
fix: fix xunfei crash (#451) 2023-08-20 22:07:50 +08:00
Benny
05e4f2b439
fix: empty completion issue caused by bad status code from upstream channel (#422) 2023-08-19 17:58:45 +08:00
滔哥
7e058bfb9b
feat: support xunfei's v2 api (#442, close #440) 
* 兼容讯飞v2接口

* Revert "兼容讯飞v2接口"

This reverts commit 21f05d1294.

* fix: fix implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
 2023-08-19 17:50:34 +08:00
glzjin
dfaa0183b7
fix: fix baidu & ali's quota calculation (#444) 
* 修复阿里计费问题

* 修复百度计费问题
 2023-08-19 17:14:39 +08:00
Benny
23b1c63538
fix: claude model ratio (#449) 
* fix: Claude model ratio

* chore: update implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-08-19 16:58:34 +08:00
JustSong
86c2627c24 fix: update cache immediately after cache get 
Co-authored-by: chikasaki <1347283135@qq.com>
Co-authored-by: Cruel <157922018@qq.com>
 2023-08-16 23:40:50 +08:00
JustSong
3da12e99d9 chore: update variable name 2023-08-13 00:50:26 +08:00
igophper
4ef5e2020c
fix: fix baidu's embedding api (#398) 
* fix:judge baidu embeddings input type

* chore: add back update all channels balance

* chore: update default configuration for sql connection

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
 2023-08-13 00:45:04 +08:00
igophper
af20063a8d
feat: able to refresh baidu access token automatically (#400, close #401) 
* feat:baidu channel support apiKey and secretKey

添加百度文心渠道时支持填写secretKey|apiKey或者accessToken，支持自动刷新accessToken

* fix

* fix

* fix

* chore: update implementation

---------

Co-authored-by: JustSong <songquanpeng@foxmail.com>
Co-authored-by: JustSong <39998050+songquanpeng@users.noreply.github.com>
 2023-08-12 23:41:44 +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
JustSong
0e9ff8825e perf: use a goroutine to handle quota post consumption (#364) 2023-08-12 19:36:31 +08:00
JustSong
7bddc73b96 perf: flush response after response handled (close #364) 2023-08-12 18:10:15 +08:00
JustSong
2a527ee436 fix: fix token name too long 2023-08-12 16:58:29 +08:00