Commit Graph

1119 Commits

Author SHA1 Message Date
GalvinYang
6b99075dc8
fix: system default model name length (#4245) (#4246)
Co-authored-by: takatost <takatost@gmail.com>
2024-05-10 18:12:18 +08:00
Yeuoly
8578ee0864
feat: support LLM jinja2 template prompt (#3968)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-05-10 18:08:32 +08:00
Jyong
897e07f639
question classifier prompt optimize (#4262) 2024-05-10 17:22:46 +08:00
LiuVaayne
875249eb00
Feat/vector db pgvector (#3879) 2024-05-10 17:20:30 +08:00
takatost
86a6e6bd04
feat: increase max steps to 50 in workflow (#4252) 2024-05-10 14:50:00 +08:00
takatost
8f3042e5b3
feat: Add draft hash check in workflow (#4251) 2024-05-10 14:48:29 +08:00
takatost
64c3bc070a
version to 0.6.7 (#4208) 2024-05-09 13:58:25 +08:00
sino
4aa21242b6
feat: add volcengine maas model provider (#4142) 2024-05-08 12:45:53 +08:00
Yong723
8ce93faf08
Typo on deepseek.yaml and yi.yaml (#4170) 2024-05-08 10:52:04 +08:00
Su Yang
9f440c11e0
feat: DeepSeek (#4162) 2024-05-08 00:28:16 +08:00
Joshua
58bd5627bf
Add-Deepseek (#4157) 2024-05-07 22:45:38 +08:00
Moonlit
2fdd64c1b5
feat: add proxy configuration for Cohere model (#4152) 2024-05-07 18:12:13 +08:00
Jyong
591b993685
fix dataset segment update api not effect issue (#4151) 2024-05-07 17:47:20 +08:00
VoidIsVoid
543a00e597
feat: update model_provider jina to support custom url and model (#4110)
Co-authored-by: Gimling <huangjl@ruyi.ai>
Co-authored-by: takatost <takatost@gmail.com>
2024-05-07 17:43:24 +08:00
Minamiyama
f361c7004d
feat: support vision models from xinference (#4094)
Co-authored-by: Yeuoly <admin@srmxy.cn>
2024-05-07 17:37:36 +08:00
Tomy
bb7c62777d
Add support for local ai speech to text (#3921)
Co-authored-by: Yeuoly <admin@srmxy.cn>
2024-05-07 17:14:24 +08:00
Yeuoly
d51f52a649
fix: http authorization leakage (#4146) 2024-05-07 16:56:25 +08:00
Jyong
e353809680
question classifier optimize (#4147) 2024-05-07 16:44:27 +08:00
takatost
c2f0f958ef
fix: passing in 0 as a numeric variable will be converted to null (#4148) 2024-05-07 16:38:23 +08:00
Charlie.Wei
087b7a6607
azure_openai add gpt-4-turbo-2024-04-09 model (#4144)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-05-07 15:55:23 +08:00
Patryk Garstecki
6271463240
feat(Languages): 👽 add pl-PL language (#4128) 2024-05-07 15:41:57 +08:00
Weaxs
6f1911533c
bug fix: update minimax model_apis (#4116) 2024-05-07 14:40:24 +08:00
Yeuoly
d5d8b98d82
feat: support openai stream usage (#4140) 2024-05-07 13:49:45 +08:00
Yeuoly
e7fe7ec0f6
feat: support time format (#4138) 2024-05-07 13:02:00 +08:00
Bowen Liang
049abd698f
improve: test CodeExecutor with code templates and extract CodeLanguage enum (#4098) 2024-05-07 12:37:18 +08:00
Yeuoly
76bec6ce7f
feat: add http node max size env (#4137) 2024-05-07 12:07:56 +08:00
S96EA
13cd409575
feat: support aliyun oss auth v4 (#3886)
Co-authored-by: owen <owen@owen.hawk-toad.ts.net>
2024-05-06 11:56:04 +08:00
羊羽
13292ff73e
🦄 refactor(dataset svc): delete check none (#4101)
Co-authored-by: baxiang <baxiang@lixiang.com>
2024-05-06 11:45:26 +08:00
Joshua
51a9e678f0
Leptonai integrate (#4079) 2024-05-05 14:37:47 +08:00
chenx5
ad76ee76a8
Update bedrock.yaml add Region Asia Pacific (Sydney) (#4016) 2024-05-05 10:49:17 +08:00
Yeuoly
b5f101bdac
fix: transform None into correct dest type (#4077) 2024-05-04 16:34:42 +08:00
Pan YANG
5940564d84
feat: add a new built-in tool of Slack Incoming Webhook (#4067) 2024-05-04 16:17:34 +08:00
Yeuoly
67902b5da7
fix: agent log timezone (#4076) 2024-05-04 16:17:15 +08:00
Bowen Liang
44857702ae
test: add integration tests on CodeExecutor with the sandbox service (#4015) 2024-05-03 08:54:40 +08:00
sino
b1399cd5f9
fix: unable to fetch CoT agent runner log (#4052) 2024-05-03 08:54:15 +08:00
Garfield Dai
6f1e4a19a2
fix: workflow avg user interaction. (#4056) 2024-05-02 20:24:40 +08:00
takatost
93393e005e
version to 0.6.6 (#4050) 2024-05-02 16:06:40 +08:00
Bowen Liang
093b5c0e63
fix: typo of jinja2 (#4019) 2024-04-30 18:39:02 +08:00
orangeclk
cbdb861ee4
add glm-3-turbo max_tokens parameter setting (#4017)
Co-authored-by: 陈力坤 <likunchen@caixin.com>
2024-04-30 17:08:04 +08:00
sino
da5a8b9a59
feat: support question classifier node output (#4000) 2024-04-30 17:07:29 +08:00
Weaxs
1e6e8b446d
feat: support minimax abab6.5, abab6.5s (#4012) 2024-04-30 17:02:01 +08:00
Bowen Liang
142814d451
chore: skip deprecated field_schema param in creating payload index on Qdrant (#3903) 2024-04-30 16:16:10 +08:00
crazywoola
704755d005
fix: submitCodeExecutionTask (#4006) 2024-04-30 16:01:03 +08:00
Richards Tu
d1263700c0
Update the description and labels in Judge0ce tool (#3990)
Co-authored-by: crazywoola <427733928@qq.com>
2024-04-30 14:58:29 +08:00
Jyong
338e4669e5
add storage factory (#3922) 2024-04-29 18:22:03 +08:00
Jyong
1d432728ac
add default value for QDRANT_GRPC_PORT (#3976) 2024-04-29 15:28:34 +08:00
Richards Tu
f26ad16af7
Add new tool: Firecrawl (#3819)
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
2024-04-29 14:20:36 +08:00
majian
8f2ae51fe5
feat: add support for request timeout settings in the HTTP request node. (#3854)
Co-authored-by: Yeuoly <admin@srmxy.cn>
2024-04-29 13:59:07 +08:00
Joshua
2f84d00300
fix-nvidia-llama3 (#3973) 2024-04-29 13:41:15 +08:00
takatost
b82a2d97ef
fix: db connections not being released during workflow execution (#3971) 2024-04-29 12:42:09 +08:00