YeungYeah
|
ee22fba448
|
Merge branch 'main' into main
|
2024-07-17 22:16:30 +08:00 |
Dogtiti
|
b3cfaf1420
|
refator: google
|
2024-07-17 20:05:34 +08:00 |
lloydzhou
|
9b97dca601
|
hotfix: custom comfig for Gemini api. #4944
|
2024-07-12 21:27:30 +08:00 |
|
lloydzhou
|
728c38396a
|
support cloudflare ai gateway
|
2024-07-12 12:00:25 +08:00 |
|
Dogtiti
|
f8c2732fdc
|
Merge pull request #4971 from ConnectAI-E/hotfix/alibaba
change build messages for qwen in client
|
2024-07-11 10:25:39 +08:00 |
|
lloydzhou
|
2299a4156d
|
change build messages for qwen in client
|
2024-07-11 00:50:58 +08:00 |
|
lloydzhou
|
32b82b9cb3
|
change build messages for qwen in client
|
2024-07-11 00:48:58 +08:00 |
|
lloydzhou
|
6885812d21
|
hotfix Gemini finish twice. #4955 #4966
|
2024-07-10 18:59:44 +08:00 |
|
lloydzhou
|
3628d68d9a
|
update
|
2024-07-09 19:56:52 +08:00 |
|
lloydzhou
|
23872086fa
|
merge code
|
2024-07-09 19:37:47 +08:00 |
|
lloydzhou
|
1149d45589
|
remove check vision model
|
2024-07-09 18:06:59 +08:00 |
|
lloydzhou
|
9d7e19cebf
|
display doubao model name when select model
|
2024-07-09 18:05:23 +08:00 |
|
lloydzhou
|
c229d2c3ce
|
merge main
|
2024-07-09 16:53:15 +08:00 |
|
lloydzhou
|
fadd7f6eb4
|
try getAccessToken in app, fixbug to fetch in none stream mode
|
2024-07-09 14:50:40 +08:00 |
|
lloydzhou
|
f68cd2c5c0
|
review code
|
2024-07-09 12:27:44 +08:00 |
|
Dogtiti
|
9bdd37bb63
|
feat: qwen
|
2024-07-07 21:59:56 +08:00 |
|
Dogtiti
|
d726c71141
|
wip: tencent
|
2024-07-07 14:43:28 +08:00 |
|
Dogtiti
|
9b3b4494ba
|
wip: doubao
|
2024-07-06 14:59:37 +08:00 |
|
Dogtiti
|
785d3748e1
|
feat: support baidu model
|
2024-07-06 13:05:09 +08:00 |
|
lloydzhou
|
6dc4844c12
|
using default azure api-version value
|
2024-07-06 00:05:59 +08:00 |
|
Dogtiti
|
14bc1b6aac
|
chore: optimize the code
|
2024-07-05 23:56:10 +08:00 |
|
lloydzhou
|
d9758be3ae
|
fix ts
|
2024-07-05 20:20:21 +08:00 |
|
lloydzhou
|
6b1b530443
|
remove makeAzurePath
|
2024-07-05 20:15:56 +08:00 |
|
lloydzhou
|
1c20137b0e
|
support azure deployment name
|
2024-07-05 19:59:45 +08:00 |
Lloyd Zhou
|
78e2b41e0c
|
Merge pull request #4906 from ConnectAI-E/feature-gemini-streaming
gemini using real sse format response #3677 #3688
|
2024-07-03 10:58:27 +08:00 |
|
lloydzhou
|
c4ad66f745
|
remove console.log
|
2024-07-01 13:27:06 +00:00 |
|
lloydzhou
|
69974d5651
|
gemini using real sse format response #3677 #3688
|
2024-07-01 13:24:01 +00:00 |
|
lloydzhou
|
37e2517dac
|
fix: 1. anthropic client using common getHeaders; 2. always using `Authorization` header send access code
|
2024-07-01 10:24:33 +00:00 |
|
lloydzhou
|
d65ddead11
|
fix: anthropic client using common getHeaders
|
2024-07-01 09:41:01 +00:00 |
|
YeungYeah
|
74986803db
|
feat: add google api safety setting
|
2024-06-15 12:09:58 +08:00 |
|
YeungYeah
|
24bf7950d8
|
chore: set the google safety setting to lowest
|
2024-06-12 21:59:28 +08:00 |
DeanYao
|
d89a12aa05
|
Revert "Chat gpt"
|
2024-05-20 19:02:46 +08:00 |
Hao Jia
|
01c9dbc1fd
|
Merge remote-tracking branch 'origin/main' into gpt-4o
# Conflicts:
# public/apple-touch-icon.png
|
2024-05-16 14:43:10 +08:00 |
Dean-YZG
|
a1493bfb4e
|
feat: bugfix
|
2024-05-06 20:46:53 +08:00 |
|
butterfly
|
b3e856df1d
|
feat: fix 1)the property named 'role' of the first message must be 'user' 2)if default summarize model 'gpt-3.5-turbo' is blocked, use currentModel instead 3)if apiurl&apikey set by location, useCustomConfig would be opened
|
2024-05-06 19:26:39 +08:00 |
|
DeanYao
|
506c17a093
|
Merge pull request #4564 from MrrDrr/gpt4v_remove_max_tokens
remove max_tokens from the official version of gpt4-turbo
|
2024-04-25 13:01:21 +08:00 |
l.tingting
|
dd4648ed9a
|
remove max_tokens from the official version of gpt4-turbo
|
2024-04-24 22:59:14 +08:00 |
黑云白土
|
b7aab3c102
|
Update google.ts
|
2024-04-17 17:16:31 +08:00 |
|
DeanYao
|
9b2cb1e1c3
|
Merge pull request #4525 from ChatGPTNextWeb/chore-fix
Chore fix
|
2024-04-16 14:59:22 +08:00 |
butterfly
|
fb8b8d28da
|
feat: (1) fix issues/4335 and issues/4518
|
2024-04-16 14:50:48 +08:00 |
|
黑云白土
|
5dc5bfb797
|
Merge branch 'main' into main
|
2024-04-11 01:24:34 +08:00 |
|
butterfly
|
9b982b408d
|
feat: fix no max_tokens in payload when calling openai vision model
|
2024-04-08 18:29:08 +08:00 |
|
butterfly
|
63f9063255
|
feat: call claude api not in credential 'include' mode
|
2024-04-08 15:33:27 +08:00 |
|
butterfly
|
6dad353e1c
|
feat: call claude api not in credential 'include' mode
|
2024-04-08 15:33:02 +08:00 |
|
butterfly
|
ef7617d545
|
feat: configs about app client
|
2024-04-08 13:41:02 +08:00 |
|
butterfly
|
0fbb560e90
|
feat: delete returned models in modals function of ClaudeApi instance
|
2024-04-07 20:05:19 +08:00 |
|
butterfly
|
86b5c55855
|
feat: roles must alternate between user and assistant in claude, so add a fake assistant message between two user messages
|
2024-04-07 18:02:31 +08:00 |
|
butterfly
|
768decde93
|
feat: parse response message
|
2024-04-07 15:20:27 +08:00 |
|
butterfly
|
69b079c86e
|
feat: dev done
|
2024-04-07 11:32:57 +08:00 |
|
黑云白土
|
f8b180ac44
|
Update google.ts
|
2024-03-28 15:52:38 +08:00 |
|
DeanYao
|
6b3daec23f
|
Merge pull request #3314 from H0llyW00dzZ/text-moderation-azure
Feat ChatGPT LLM Api [Console Log] [Text Moderation] [Azure]
|
2024-03-28 13:38:56 +08:00 |
kidv
|
29e03b88c7
|
Fix: Handle empty server response in API call
|
2024-03-24 04:07:25 +08:00 |
Fred
|
43e5dc2292
|
fix: fix the method to detect vision model
|
2024-02-28 11:33:43 +08:00 |
fred-bf
|
08fa22749a
|
fix: add max_tokens when using vision model (#4157)
|
2024-02-27 17:28:01 +08:00 |
TheRam_
|
e2da3406d2
|
Add vision support (#4076)
|
2024-02-20 18:04:32 +08:00 |
|
fred-bf
|
d74f636558
|
Fix/gemini app endpoint (#4017)
* fix: support custom api endpoint
* fix: attach api key to google gemini
|
2024-02-07 13:46:52 +08:00 |
|
fred-bf
|
b8f0822214
|
fix: support custom api endpoint (#4016)
|
2024-02-07 13:40:30 +08:00 |
|
fred-bf
|
bca74241e6
|
fix: fix gemini issue when using app (#4013)
* chore: update path
* fix: fix google auth logic
* fix: not using header authorization for google api
* chore: revert to allow stream
|
2024-02-07 13:17:11 +08:00 |
Fred Liang
|
9eaf492d5b
|
chore: low the google safety setting to avoid unexpected blocking
|
2023-12-31 19:49:22 +08:00 |
|
Fred Liang
|
a80502f7db
|
fix: fix gemini pro streaming api duplicated issue (#3721)
* fix: streaming duplicated issue
* chore: remove debug logs
* chore: add types defination
|
2023-12-31 19:08:16 +08:00 |
|
Fred Liang
|
5cf58d9446
|
feat: support streaming for Gemini Pro (#3688)
* feat: support streaming for Gemini Pro
* feat: display texts smoothly
* chore: remove comments
|
2023-12-29 03:42:45 +08:00 |
|
Fred Liang
|
199f29e63c
|
chore: auto concat messages
|
2023-12-25 04:33:47 +08:00 |
|
Fred Liang
|
7c3dfb7bae
|
feat: support custom gemini pro params
|
2023-12-24 17:24:04 +08:00 |
|
Fred Liang
|
75057f9a91
|
chroe: support error reason for gemini pro
|
2023-12-24 04:32:25 +08:00 |
|
Fred Liang
|
ae19a0dc5f
|
chroe: update model name
|
2023-12-24 04:22:12 +08:00 |
|
Fred Liang
|
20f2f61349
|
feat: support set api key from client side
|
2023-12-24 03:44:13 +08:00 |
|
Fred Liang
|
4169431f2c
|
fix: fix add api auth
|
2023-12-24 03:05:23 +08:00 |
|
Fred Liang
|
45798f993d
|
fix: fix type errors
|
2023-12-24 02:39:13 +08:00 |
|
Fred Liang
|
778e88cb56
|
chore: resolve conflict
|
2023-12-24 02:15:30 +08:00 |
H0llyW00dzZ
|
fe0f078353
|
Feat ChatGPT LLM Api [Console Log] [Text Moderation] [Azure]
[+] fix(openai.ts): fix parsing error in ChatGPTApi's message handler
[+] feat(openai.ts): add logging for flagged categories in text moderation
|
2023-11-19 19:49:52 +07:00 |
Yidadaa
|
f2485931d9
|
feat: better animation speed
|
2023-11-19 19:15:11 +08:00 |
|
Yidadaa
|
536ace8e10
|
feat: animate streaming response to make more smooth
|
2023-11-19 18:24:51 +08:00 |
|
Yidadaa
|
b7ffca031e
|
feat: close #935 add azure support
|
2023-11-10 02:43:37 +08:00 |
|
Yifei Zhang
|
fd2f441e02
|
feat: wont send max_tokens
|
2023-11-09 20:45:25 +08:00 |
|
Yidadaa
|
d0a1d910d4
|
fix: #3186 enable max_tokens in chat payload
|
2023-11-09 03:19:13 +08:00 |
|
Yidadaa
|
5610f423d0
|
feat: add multi-model support
|
2023-10-30 02:07:11 +08:00 |
|
Yidadaa
|
ae8226907f
|
feat: close #2621 use better default api url
|
2023-08-14 21:36:29 +08:00 |
7lsu
|
cf625e3542
|
typo fix
|
2023-08-01 10:16:36 +08:00 |
|
Yidadaa
|
15e063e1b5
|
feat: #2330 disable /list/models
|
2023-07-10 23:19:43 +08:00 |
|
Yidadaa
|
28c457730a
|
fix: #2280 auto-detect models from 'list/models'
|
2023-07-09 18:03:06 +08:00 |
guochao
|
6653a31eb7
|
perf: models接口返回数据的容错处理
|
2023-07-06 20:00:30 +08:00 |
|
Yidadaa
|
4131fccbe0
|
feat: close #2192 use /list/models to get model ids
|
2023-07-04 23:16:24 +08:00 |
|
Yidadaa
|
cda074fe24
|
fixup
|
2023-07-04 00:40:57 +08:00 |
|
Yidadaa
|
0140f771c6
|
feat: close #2175 use default api host if endpoint is empty
|
2023-06-28 23:12:35 +08:00 |
|
Yifei Zhang
|
f3ec9f02eb
|
Merge pull request #1807 from AngelLiang/feat/frequency_penalty
feat: Add frequency_penalty request parameter
|
2023-06-18 14:36:55 +08:00 |
|
Yidadaa
|
0d4611052e
|
feat: white url list for openai security
|
2023-06-13 00:39:29 +08:00 |
AngelLiang
|
72cbb156ae
|
feat: Add frequency_penalty request parameter
|
2023-06-04 16:05:35 +08:00 |
|
Yidadaa
|
af497c96ec
|
fix: #1612 infinite loading
|
2023-05-20 19:58:12 +08:00 |
|
Yidadaa
|
a524a60c46
|
fix: #1611 show corret message when can not query usage
|
2023-05-19 00:27:25 +08:00 |
kirk.shan
|
789f3d993c
|
fix content-type = text/event-stream;charset=utf-8
|
2023-05-18 10:25:06 +08:00 |
|
Yidadaa
|
85445c4ef2
|
chore: wont parse finished result
|
2023-05-18 02:09:05 +08:00 |
|
Yidadaa
|
5f2745c32a
|
feat: handle non-stream response
|
2023-05-18 02:04:12 +08:00 |
|
Yidadaa
|
30676d118f
|
fix: #1571 #1578 handle more error code
|
2023-05-18 00:14:29 +08:00 |
ShengYan, Zhang
|
94a2104b55
|
fix: set openWhenHidden to be true
|
2023-05-17 17:20:17 +08:00 |
|
ShengYan, Zhang
|
e00652ce86
|
fix: #1533 handle non-stream type
|
2023-05-17 08:50:50 +08:00 |
PaRaD1SE98
|
8cde6cd4d7
|
Merge pull request #1 from PaRaD1SE98/fix_typo
fix: typo reqestTimeoutId -> requestTimeoutId
|
2023-05-16 10:01:45 +09:00 |
|
PaRaD1SE98
|
06534fa0ae
|
fix: typo reqestTimeoutId -> requestTimeoutId
|
2023-05-16 09:59:30 +09:00 |
|
Yidadaa
|
71cbf86b2c
|
fixup: add more error info
|
2023-05-16 01:58:58 +08:00 |
|
Yidadaa
|
aed6b34950
|
fix: #1498 missing text caused by streaming
|
2023-05-16 01:25:16 +08:00 |
|
Yidadaa
|
8b0cf7d248
|
fix: #1509 openai url split
|
2023-05-16 00:22:11 +08:00 |
|
Yidadaa
|
9e602eb575
|
fixup: decode in stream mode
|
2023-05-15 02:01:50 +08:00 |
|
Yidadaa
|
5979bdd48e
|
fixup
|
2023-05-15 01:55:45 +08:00 |
|
Yidadaa
|
a3de277c43
|
refactor: #1000 #1179 api layer for client-side only mode and local models
|
2023-05-15 01:33:46 +08:00 |
|
Yidadaa
|
bd90caa99d
|
refactor: llm client api
|
2023-05-14 23:00:17 +08:00 |