Commit Graph

364 Commits

Author SHA1 Message Date
Pan, Wen-Ming
b98a1a3303
feat: added Anthropic Claude3 models to Google Cloud Vertex AI (#4870)
Co-authored-by: pwm <pwm@google.com>
2024-06-04 02:52:46 +08:00
takatost
696c5308a9
chore: optimize nvidia nim credential schema and info (#4898) 2024-06-04 02:26:26 +08:00
Joshua
3c8a120e51
add-nvidia-mim (#4882) 2024-06-03 21:10:18 +08:00
Pan, Wen-Ming
cdbc260571
Bugfix: Vertex AI vision model not support image (#4853) 2024-06-02 11:11:09 +08:00
Yash Parmar
e0da0744b5
add: ollama keep alive parameter added. issue #4024 (#4655) 2024-05-31 12:22:02 +08:00
Weaxs
b189faca52
feat: update ernie model (#4756) 2024-05-29 14:57:23 +08:00
xielong
e1cd9aef8f
feat: support baichuan3 turbo, baichuan3 turbo 128k, and baichuan4 (#4762) 2024-05-29 14:46:04 +08:00
crazywoola
705a6e3a8e
Fix/4742 ollama num gpu option not consistent with allowed values (#4751) 2024-05-29 13:33:35 +08:00
xielong
793f0c1dd6
fix: Corrected schema link in model_runtime's README.md (#4757) 2024-05-29 13:03:21 +08:00
xielong
88b4d69278
fix: Correct context size for banchuan2-53b and banchuan2-turbo (#4721) 2024-05-28 16:37:44 +08:00
crazywoola
27dae156db
fix: colon in file mistral.mistral-small-2402-v1:0 (#4673) 2024-05-27 13:15:20 +08:00
Giovanny Gutiérrez
2deb23e00e
fix: Show rerank in system for localai (#4652) 2024-05-27 12:09:51 +08:00
longzhihun
fe9bf5fc4a
[seanguo] add support of amazon titan v2 and modify the price of amazon titan v1 (#4643)
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-05-26 23:30:22 +08:00
miendinh
f804adbff3
feat: Support for Vertex AI - load Default Application Configuration (#4641)
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-05-25 13:40:25 +08:00
Krasus.Chen
f156014daa
update lite8k/speed8k/128k max_token to newest (#4636)
Co-authored-by: Your Name <chen@krasus.red>
2024-05-24 19:33:42 +08:00
Bowen Liang
3fda2245a4
improve: extract method for safe loading yaml file and avoid using PyYaml's FullLoader (#4031) 2024-05-24 12:08:12 +08:00
Patryk Garstecki
296887754f
Support for Vertex AI (#4586) 2024-05-24 12:01:40 +08:00
QuietRocket
9ae72cdcf4
feat: Add Gemini Flash (#4616) 2024-05-24 11:43:06 +08:00
takatost
11642192d1
chore: add https://api.openai.com placeholder in OpenAI api base (#4604) 2024-05-23 12:56:05 +08:00
呆萌闷油瓶
e57bdd4e58
chore:update gpt-3.5-turbo and gpt-4-turbo parameter for azure (#4596) 2024-05-23 11:51:38 +08:00
somethingwentwell
461488e9bf
Add Azure OpenAI API version for GPT4o support (#4569)
Co-authored-by: wwwc <wwwc@outlook.com>
2024-05-22 17:43:16 +08:00
Justin Wu
3ab19be9ea
Fix bedrock claude wrong pricing (#4572)
Co-authored-by: Justin Wu <justin.wu@ringcentral.com>
2024-05-22 14:28:28 +08:00
呆萌闷油瓶
d5a33a0323
feat:add gpt-4o for azure (#4568) 2024-05-22 11:02:43 +08:00
Bowen Liang
e8e213ad1e
chore: apply and fix flake8-bugbear lint rules (#4496) 2024-05-20 16:34:13 +08:00
Ever
4086f5051c
feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294)
Co-authored-by: 老潮 <zhangyongsheng@3vjia.com>
Co-authored-by: takatost <takatost@users.noreply.github.com>
Co-authored-by: takatost <takatost@gmail.com>
2024-05-20 10:15:27 +08:00
fanghongtai
1cca100a48
fix:modify spelling errors: lanuage ->language in schema.md (#4499)
Co-authored-by: wxfanghongtai <wxfanghongtai@gf.com.cn>
2024-05-19 18:31:05 +08:00
Bowen Liang
04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497) 2024-05-19 18:30:45 +08:00
Yeuoly
091fba74cb
enhance: claude stream tool call (#4469) 2024-05-17 12:43:58 +08:00
jiaqianjing
0ac5d621b6
add llm: ernie-character-8k of wenxin (#4448) 2024-05-16 18:31:07 +08:00
sino
6e9066ebf4
feat: support doubao llm and embeding models (#4431) 2024-05-16 11:41:24 +08:00
Yash Parmar
332baca538
FIX: fix the temperature value of ollama model (#4027) 2024-05-15 08:05:54 +08:00
Yeuoly
e8311357ff
feat: gpt-4o (#4346) 2024-05-14 02:52:41 +08:00
orangeclk
ece0f08a2b
add yi models (#4335)
Co-authored-by: 陈力坤 <likunchen@caixin.com>
2024-05-13 17:40:53 +08:00
Weaxs
8cc492721b
fix: minimax streaming function_call message (#4271) 2024-05-11 21:07:22 +08:00
Joshua
a80fe20456
add-some-new-models-hosted-on-nvidia (#4303) 2024-05-11 21:05:31 +08:00
呆萌闷油瓶
4796f9d914
feat:add gpt-4-turbo for azure (#4287) 2024-05-11 13:02:56 +08:00
Sebastian.W
a588df4371
Add rerank model type for LocalAI provider (#3952) 2024-05-11 11:29:28 +08:00
Bowen Liang
228de1f12a
fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224) 2024-05-10 18:14:48 +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
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
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
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
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
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
Weaxs
1e6e8b446d
feat: support minimax abab6.5, abab6.5s (#4012) 2024-04-30 17:02:01 +08:00
Joshua
2f84d00300
fix-nvidia-llama3 (#3973) 2024-04-29 13:41:15 +08:00
longzhihun
43a5ba9415
feat: add support for Bedrock LLAMA3 (#3890) 2024-04-27 13:13:09 +08:00
Garfield Dai
cefe156811
feat: replicate supports default version. (#3884) 2024-04-26 21:16:22 +08:00
Jyong
0ec8b57825
add together ai model setting (#3895) 2024-04-26 20:43:17 +08:00
takatost
a4e4fb4094
fix: credentials validate failed for groqcloud model provider (#3817) 2024-04-25 12:09:44 +08:00
1102
59cba930e5
bedrock llm Model file name change (#3714)
Co-authored-by: heshunchang <shuncanghe@clouditera.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-04-23 18:57:34 +08:00
呆萌闷油瓶
f76ac8bdee
enhance:speedup xinference audio transcription (#3636) 2024-04-23 17:09:30 +08:00
longzhihun
28236147ee
feat: add support for bedrock Mistral AI model (#3676)
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-04-22 17:24:02 +08:00
Chenhe Gu
4969783383
add groq llama3 (#3673) 2024-04-22 15:21:09 +08:00
Joshua
7545e5de6c
add-llama3-for-nvidia-api-catalog (#3631) 2024-04-19 14:51:22 +08:00
Yeuoly
a0c30702c1
feat: moonshot fc (#3629) 2024-04-19 14:04:30 +08:00
jeessy2
646858ea08
feat: Vision switch functionality is provided on OpenRouter (#3564) 2024-04-19 09:13:25 +08:00
Bowen Liang
d9b821cecc
chore: apply ruff rules on tests and app.py (#3605) 2024-04-18 20:24:05 +08:00
Joshua
de3b490f8e
Add mixtral 8x22b (#3606) 2024-04-18 17:44:22 +08:00
aniaan
aa6d2e3035
fix(openai_api_compatible): fixing the error when converting chunk to json (#3570) 2024-04-18 16:54:16 +08:00
呆萌闷油瓶
4365843c20
enhance:speedup xinference embedding & rerank (#3587) 2024-04-18 16:54:00 +08:00
Joshua
b9b28900b1
add-open-mixtral-8x22b (#3591) 2024-04-18 13:48:32 +08:00
Siddharth Jain
8ba95c08a1
added claude 3 opus (#3545) 2024-04-17 20:53:59 +08:00
takatost
b890c11c14
feat: filter empty content messages in llm node (#3547) 2024-04-17 13:30:33 +08:00
takatost
9b8861e3e1
feat: increase read timeout of OpenAI Compatible API, Ollama, Nvidia LLM (#3538) 2024-04-17 09:25:50 +08:00
Yeuoly
fbd3ef8752
fix: add completion mode object check (#3515) 2024-04-16 13:36:02 +08:00
kerlion
200010be19
Add suuport for AWS Bedrock Cohere embedding (#3444) 2024-04-16 13:22:38 +08:00
liuzhenghua
5e02a83b53
fix: the object field is empty string in some openAI api compatible model (#3506) 2024-04-16 12:13:10 +08:00
takatost
5b447d61a6
feat: refactor tongyi models (#3496) 2024-04-15 22:28:32 +08:00
Joshua
fd38e1cf15
nvidia-label-update (#3482) 2024-04-15 13:50:16 +08:00
Yeuoly
8f8e9de601
feat: support configurate openai compatible stream tool call (#3467) 2024-04-14 22:04:45 +08:00
Josh Feng
3e6631312d
Add nvidia codegemma 7b (#3437) 2024-04-13 13:10:32 +08:00
Yash Parmar
dd354bd396
FEAT: cohere rerank 3 model added (#3431) 2024-04-12 22:36:39 +08:00
Yeuoly
a258a90291
feat: gemini pro function call (#3406) 2024-04-12 16:38:02 +08:00
saga.rey
b699945b47
fix: [azure_openai] Error: 'NoneType' object has no attribute 'content' (#3389) 2024-04-12 14:44:17 +08:00
longzhihun
f7a417fdb4
feat: Add support for embed file with AWS Bedrock Titan Model (#3377)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-04-12 00:35:45 +08:00
takatost
36b7dbb8d0
fix: cohere tool call does not support single tool (#3373) 2024-04-11 21:32:18 +08:00
takatost
9a1ea9ac03
fix: image token calc of OpenAI Compatible API (#3368) 2024-04-11 20:29:48 +08:00
Yeuoly
18b855140d
fix/moonshot-function-call (#3339) 2024-04-11 15:42:26 +08:00
crazywoola
7c520b52c1
feat: update aws bedrock (#3326)
Co-authored-by: chenhe <guchenhe@gmail.com>
2024-04-11 15:38:55 +08:00
Eric Wang
e0df7505f6
feat(llm/models): add gemini-1.5-pro (#2925) 2024-04-11 10:58:13 +08:00
takatost
826c422ac4
feat: Add Cohere Command R / R+ model support (#3333) 2024-04-11 01:22:55 +08:00
Kenny
bf63a43bda
feat: support gpt-4-turbo-2024-04-09 model (#3300) 2024-04-10 22:55:46 +08:00
Yeuoly
14bb0b02ac
Feat/Agent-Image-Processing (#3293)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-04-10 14:48:40 +08:00
takatost
97d1e0bbbb
feat: vision parameter support of OpenAI Compatible API (#3272) 2024-04-10 11:13:56 +08:00
Yeuoly
835e547195
feat: gpt-4-turbo (#3263) 2024-04-10 10:28:52 +08:00
crazywoola
f5e65b98a9
feat: remove unregistered-llm-in-debug (#3251) 2024-04-09 20:49:52 +08:00
Chenhe Gu
eb76d7a226
make sure validation flow works for all model providers in bedrock (#3250) 2024-04-09 20:42:18 +08:00
Yeuoly
a2c068d949
feat: moonshot function call (#3227) 2024-04-09 15:30:09 +08:00
Jat
bae0c071cd
Fix: remove unavailable return_preamble parameter in cohere (#3201)
Signed-off-by: Jat <jat@sinosky.org>
2024-04-09 12:11:53 +08:00
takatost
7753ba2d37
FEAT: NEW WORKFLOW ENGINE (#3160)
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Yeuoly <admin@srmxy.cn>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: jyong <jyong@dify.ai>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: jyong <718720800@qq.com>
2024-04-08 18:51:46 +08:00
Yeuoly
25b9ac3df4
feat: claude3 tool call (#3111) 2024-04-05 16:35:59 +09:00
Salem Korayem
6b4c8e76e6
feat (new llm): add support for openrouter (#3042) 2024-04-02 18:38:46 +08:00
呆萌闷油瓶
e215aae39a
feat:xinference audio model support (#3045) 2024-03-31 12:44:11 +08:00
Chenhe Gu
9d962053a2
Fix claude request errors in bedrock (#3015)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-03-29 13:57:45 +08:00
Bowen Liang
08b727833e
generalize helper for loading module from source (#2862) 2024-03-28 11:37:26 +08:00
Weaxs
5becb4c43a
update wenxin llm (#2929) 2024-03-27 11:36:21 +08:00
Kenny
13694293e3
fix: resolve header.uid' length must be less or equal than 32 on Spark V1.5 (#2983) 2024-03-27 09:58:41 +08:00
Ricky
40dbf30784
feat: support new reranker [jina-colbert-v1-en] (#2975) 2024-03-26 11:34:40 +08:00
Weishan-0
a676d4387c
fix: Correct image parameter passing in GLM-4v model API calls (#2948) 2024-03-26 10:43:20 +08:00
orangeclk
4fb9606361
fix: max_token default help info improved (#2951) 2024-03-25 10:07:32 +08:00
orangeclk
c534d95972
fix: yi model price correction (#2946) 2024-03-24 12:10:57 +08:00
orangeclk
6dc62334d6
doc: model schema document fix and wording about the model price parameter (#2944) 2024-03-24 12:06:20 +08:00
Yeuoly
240a94182e
Feat/add triton inference server (#2928) 2024-03-22 15:15:48 +08:00
Su Yang
5a1c29fd8c
chore: change Yi model SDK to OpenAI (#2910) 2024-03-20 16:02:13 +08:00
Joshua
518c1ceb94
Feat/add-NVIDIA-as-a-new-model-provider (#2900) 2024-03-19 21:08:17 +08:00
Su Yang
4419d357c4
chore: update Yi models params (#2895) 2024-03-19 20:54:31 +08:00
takatost
fbbba6db92
feat: optimize ollama model default parameters (#2894) 2024-03-19 18:34:23 +08:00
Su Yang
8133ba16b1
chore: update Qwen model params (#2892) 2024-03-19 18:13:32 +08:00
Su Yang
7e3c59e53e
chore: Update TongYi models prices (#2890) 2024-03-19 16:32:42 +08:00
呆萌闷油瓶
f6314f8e73
feat:support azure openai llm 0125 version (#2889) 2024-03-19 16:32:26 +08:00
Su Yang
3bcfd84fba
chore: use API Key instead of APIKey (#2888) 2024-03-19 16:32:06 +08:00
Su Yang
2dee8a25d5
fix: anthropic system prompt not working (#2885) 2024-03-19 15:50:02 +08:00
Su Yang
507aa6d949
fix: Fix the problem of system not working (#2884) 2024-03-19 13:56:22 +08:00
crazywoola
59f173f2e6
feat: add icons for 01.ai (#2883) 2024-03-19 13:53:21 +08:00
Su Yang
c3790c239c
i18n: update bedrock label (#2879) 2024-03-19 00:57:19 +08:00
Su Yang
45e51e7730
feat: AWS Bedrock Claude3 (#2864)
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-03-18 18:16:36 +08:00
Onelevenvy
cb79a90031
feat: Add tools for open weather search and image generation using the Spark API. (#2845) 2024-03-18 16:22:48 +08:00
Onelevenvy
4502436c47
feat:Embedding models Support for the Aliyun dashscope text-embedding-v1 and text-embedding-v2 (#2874) 2024-03-18 15:21:26 +08:00
orangeclk
e7343cc67c
add max_tokens parameter rule for zhipuai glm4 and glm4v (#2861) 2024-03-18 13:19:36 +08:00
VoidIsVoid
83145486b0
fix: fix unstable function call response arguments missing (#2872) 2024-03-18 13:17:16 +08:00
Su Yang
6fd1795d25
feat: Allow users to specify AWS Bedrock validation models (#2857) 2024-03-18 00:44:09 +08:00
Su Yang
f770232b63
feat: add model for 01.ai, yi-chat-34b series (#2865) 2024-03-17 21:24:01 +08:00
Yeuoly
742be06ea9
Fix/localai (#2840) 2024-03-15 11:41:51 +08:00
Eric Wang
4fe585acc2
feat(llm/models): add claude-3-haiku-20240307 (#2825) 2024-03-14 10:08:24 +08:00
呆萌闷油瓶
e52448b84b
feat:add api-version selection for azure openai APIs (#2821) 2024-03-14 09:14:27 +08:00
Bowen Liang
8b15b742ad
generalize position helper for parsing _position.yaml and sorting objects by name (#2803) 2024-03-13 20:29:38 +08:00
呆萌闷油瓶
8f9125b08a
fix:typo (#2808) 2024-03-13 13:00:46 +08:00
呆萌闷油瓶
e5e97c0a0a
fix:change azure openai api_version default value to 2024-02-15-preview (#2797) 2024-03-12 22:07:06 +08:00
呆萌闷油瓶
f49b1afd6c
feat:support azure tts (#2751) 2024-03-12 12:06:35 +08:00
Jyong
e54c9cd401
Feat/open ai compatible functioncall (#2783)
Co-authored-by: jyong <jyong@dify.ai>
2024-03-11 19:48:21 +08:00
洪朔
60e7e17c86
feat: Add new Azure OpenAI Embedding models (#2758) 2024-03-08 19:04:20 +08:00
Yeuoly
40c646cf7a
Feat/model as tool (#2744) 2024-03-08 15:22:55 +08:00
Yeuoly
3231a8c51c
fix: image tokenizer (#2752) 2024-03-08 14:50:51 +08:00
呆萌闷油瓶
b75ff5fa03
fix:missing import (#2739) 2024-03-07 17:31:30 +08:00
呆萌闷油瓶
9819ad347f
feat:support azure whisper model and fix:rename text-embedidng-ada-002.yaml to text-embedding-ada-002.yaml (#2732) 2024-03-07 16:36:58 +08:00
Yeuoly
8fe83750b7
Fix/jina tokenizer cache (#2735) 2024-03-07 16:32:37 +08:00
Yeuoly
1809f05904
Feat/add groq (#2733) 2024-03-07 16:00:40 +08:00
taokuizu
405a00bb2c
fix:delete the slash at the end of xinference provider server_url (#2730) 2024-03-07 15:37:05 +08:00
Yeuoly
3a3ca8e6a9
fix: max tokens can only up to 2048 (#2734) 2024-03-07 15:35:56 +08:00
Jyong
7f3dec7bee
fix error msg format issue (#2715)
Co-authored-by: jyong <jyong@dify.ai>
2024-03-06 16:45:40 +08:00
Joshua
526c874caa
fix mistralai icon (#2707) 2024-03-06 11:08:22 +08:00