Commit Graph

585 Commits

Author SHA1 Message Date
Wang Bo
6f222b49f2
refactor: rename task_type to task for jina embeddings v3 (#8488) 2024-09-18 14:53:15 +08:00
-LAN-
8dfe8c773a
chore: Deprecate gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613 models (#8500) 2024-09-18 14:38:09 +08:00
ybalbert001
b6ad7a1e06
Fix: https://github.com/langgenius/dify/issues/8190 (Update Model nam… (#8426)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-14 17:14:18 +08:00
Aaron Ji
6f7625fa47
chore: update Jina embedding model (#8376) 2024-09-14 16:21:17 +08:00
ybalbert001
b613b11422
Fix: Support Bedrock cross region inference #8190 (Update Model name to distinguish between different region groups) (#8402)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-14 11:06:20 +08:00
crazywoola
71b4480c4a
fix: o1-mini 65563 -> 65536 (#8388) 2024-09-14 02:39:58 +08:00
Bowen Liang
5b98acde2f
chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 (#8392) 2024-09-13 23:34:39 +08:00
Bowen Liang
a1104ab97e
chore: refurish python code by applying Pylint linter rules (#8322) 2024-09-13 22:42:08 +08:00
xiandan-erizo
1ab81b4972
support hunyuan-turbo (#8372)
Co-authored-by: sunkesi <sunkesi@hosecloud.com>
2024-09-13 20:21:48 +08:00
takatost
24af4b9313
fix: o1-series model encounters an error when the generate mode is blocking (#8363) 2024-09-13 15:37:54 +08:00
Bowen Liang
6613b8f2e0
chore: fix unnecessary string concatation in single line (#8311) 2024-09-13 14:24:49 +08:00
sino
a45ac6ab98
fix: ark token usage is none (#8351) 2024-09-13 14:19:24 +08:00
takatost
4637ddaa7f
feat: add o1-series models support in Agent App (ReACT only) (#8350) 2024-09-13 13:08:27 +08:00
takatost
e90d3c29ab
feat: add OpenAI o1 series models support (#8328) 2024-09-13 02:15:19 +08:00
Nam Vu
153807f243
fix: response_format label (#8326) 2024-09-12 23:17:29 +08:00
呆萌闷油瓶
02c4b1af71
chore:add Azure openai api version 2024-08-01-preview (#8291) 2024-09-12 20:22:57 +08:00
ybalbert001
d4985fb3aa
Fix: Support Bedrock cross region inference [#8190](https://github.com/langgenius/dify/issues/8190) (#8317) 2024-09-12 19:15:20 +08:00
Bowen Liang
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules (#8296) 2024-09-12 15:50:49 +08:00
Bowen Liang
c69f5b07ba
chore: apply ruff E501 line-too-long linter rule (#8275)
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-12 14:00:36 +08:00
Bowen Liang
0f14873255
chore: cleanup ruff flake8-simplify linter rules (#8286)
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-12 12:55:45 +08:00
Bowen Liang
781d294f49
chore: cleanup pycodestyle E rules (#8269) 2024-09-11 18:55:00 +08:00
yalei
f515af2232
let claude models in bedrock support the response_format parameter (#8220)
Co-authored-by: duyalei <>
2024-09-11 18:24:50 +08:00
crazywoola
4d2cd6703b
chore: remove useless code (#8198) 2024-09-11 18:19:34 +08:00
Bowen Liang
292220c596
chore: apply pep8-naming rules for naming convention (#8261) 2024-09-11 16:40:52 +08:00
HowardChan
53f37a6704
fix:ollama text embedding 500 error (#8252) 2024-09-11 16:23:19 +08:00
Nam Vu
342607f4a4
fix: truthy value (#8208) 2024-09-11 15:44:53 +08:00
HowardChan
82c42b9ec5
fix:error when adding the ollama embedding model (#8236)
Co-authored-by: crazywoola <427733928@qq.com>
2024-09-11 10:25:45 +08:00
Bowen Liang
2cf1187b32
chore(api/core): apply ruff reformatting (#7624) 2024-09-10 17:00:20 +08:00
takatost
dabfd74622
feat: Parallel Execution of Nodes in Workflows (#8192)
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-10 15:23:16 +08:00
Jyong
2d690801d1
nvidia rerank top n missed (#8185) 2024-09-10 13:17:48 +08:00
-LAN-
4313d92e6b
feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. (#8167) 2024-09-10 09:11:31 +08:00
crazywoola
0bec6a037c
update qwen-long (#8157) 2024-09-09 19:09:42 +08:00
AAEE86
fa34b9aed6
Modify model parameters in Spark LLMs and zhipuai LLMs (#8078)
Co-authored-by: Charlie.Wei <luowei@cvte.com>
2024-09-09 15:36:47 +08:00
crazywoola
a27d4d58ec
fix: ollama text embedding 500 error (#8131) 2024-09-09 15:27:49 +08:00
邹成卓
a15791e788
Fix: tongyi code wrapper works not stable (#7871)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-09-09 11:15:17 +08:00
ybalbert001
954580a4af
feat: support more model types and builtin tools on aws/sagemaker (#8061)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-09 10:34:11 +08:00
crazywoola
ab7d79275e
fix: Claude can not validate credientials (#8109) 2024-09-09 10:22:42 +08:00
呆萌闷油瓶
d28446301f
feat:add fishaudio in xinference (#8100) 2024-09-08 23:58:02 +08:00
Nam Vu
2d7954c7da
Fix variable typo (#8084) 2024-09-08 13:14:11 +08:00
AAEE86
0cef25ef8c
Revert "fix: parameter rule" (#8070) 2024-09-07 10:44:56 +08:00
crazywoola
900fd82a92
fix: parameter rule (#8064) 2024-09-06 19:15:24 +08:00
tmuife
89aede80cc
Add OCI(Oracle Cloud Infrastructure) Generative AI Service as a Model Provider (#7775)
Co-authored-by: Walter Jin <jinshuhaicc@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: walter from vm <walter.jin@oracle.com>
2024-09-06 14:15:40 +08:00
Leng Yue
bd0992275c
feat: support fish audio TTS (#7982) 2024-09-05 14:18:39 +08:00
非法操作
3e7597f2bd
feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service (#7648) 2024-09-04 21:56:08 +08:00
wochuideng
f6b9982c23
Concurrent calls to the Wenxin model, and the exception problem when obtaining the token is fixed (#7976)
Co-authored-by: puqs1 <puqs1@lenovo.com>
2024-09-04 21:44:57 +08:00
非法操作
0f72a8e89d
chore: refactor the beichuan model (#7953) 2024-09-04 16:22:31 +08:00
呆萌闷油瓶
83494cb4f5
fix:empty voice occurs when xinference CosyVoice tts model (#7958) 2024-09-04 13:04:31 +08:00
orangeclk
3f2a806abe
fix: glm models prices and max_tokens correction (#7882) 2024-09-02 14:29:09 +08:00
sino
1f56a20b62
feat: support auth by api key for ark provider (#7845) 2024-08-31 10:56:32 +08:00
非法操作
dc015c380a
feat: add zhipu glm_4_plus and glm_4v_plus model (#7824) 2024-08-30 15:08:31 +08:00
hisir
f0273f00e1
Fixed when testing the openai compatible interface model, an error is reported when no object is returned (#7808) 2024-08-29 18:58:19 +08:00
sino
7cfebffbb8
chore: update default endpoint for ark provider (#7741) 2024-08-28 13:56:50 +08:00
crazywoola
da326baa5e
fix: tongyi Error: 'NoneType' object is not subscriptable (#7705) 2024-08-27 16:56:06 +08:00
sino
ee7d5e7206
feat: support Moonshot and GLM models tool call for volc ark provider (#7666) 2024-08-27 14:43:37 +08:00
Hélio Lúcio
7b7576ad55
Add Azure AI Studio as provider (#7549)
Co-authored-by: Hélio Lúcio <canais.hlucio@voegol.com.br>
2024-08-27 09:52:59 +08:00
代君
7c2bb31a55
[fix] openai's tool role dose not support name parameter. (#7659) 2024-08-26 18:52:34 +08:00
Seayon
561a61e7fe
Improve MIME type detection for image URLs (#6531)
Co-authored-by: seayon <zhaoxuyang@shouqianba.com>
2024-08-25 13:36:16 +08:00
sino
efc136cce5
feat: Introduce Ark SDK v3 and ensure compatibility with models of SDK v2 (#7579)
Co-authored-by: crazywoola <427733928@qq.com>
2024-08-24 19:29:45 +08:00
噢哎哟喂
ad13011043
add JSON Mode support for moonshot models (#7568) 2024-08-23 16:24:45 +08:00
Fei He
6025002971
add qwen text-embedding-v3 support. (#7567) 2024-08-23 15:32:38 +08:00
orangeclk
a24717765e
feat: forward zhipu finish_reason (#7560) 2024-08-23 11:15:38 +08:00
orangeclk
f53454f81d
add finish_reason to the LLM node output (#7498) 2024-08-21 17:29:30 +08:00
非法操作
f7af8c7cc7
feat: gpt-4o-mini-2024-07-18 support json schema (#7489) 2024-08-21 15:11:29 +08:00
Xiyuan Chen
4e7b6aec3a
feat: support pinning, including, and excluding for model providers and tools (#7419)
Co-authored-by: GareArc <chen4851@purude.edu>
2024-08-21 11:16:43 +08:00
Nam Vu
6991a243aa
chore: correct _tts_invoke_streaming max length (#7423) 2024-08-20 10:20:04 +08:00
Chengyu Yan
1f944c6eeb
feat(api): support wenxin bge-large and tao embedding model. (#7393) 2024-08-19 22:25:09 +08:00
Xiao Ley
53cf756207
feat: OpenRouter add gpt-4o-2024-08-06 model (#7409) 2024-08-19 19:14:08 +08:00
-LAN-
0087afc2e3
fix(api/core/model_runtime/model_providers/__base/large_language_model.py): Add TEXT type checker (#7407) 2024-08-19 18:45:30 +08:00
SoaringEthan
acd72e3ab2
feat: support xinference's auth system (#7369) 2024-08-19 12:41:56 +08:00
Chengyu Yan
bfd905602f
feat(api): support wenxin text embedding (#7377) 2024-08-19 09:15:19 +08:00
sino
a0a67873aa
chore: optimize ark model parameters (#7378) 2024-08-19 08:44:19 +08:00
噢哎哟喂
baaa3f7f42
add base url for moonshot model (#7360) 2024-08-17 10:28:09 +08:00
Weaxs
3a33062405
feat: support siliconflow rerank (#7337) 2024-08-16 20:21:41 +08:00
Xiyuan Chen
c7df6783df
Revert "feat: support pinning, including, and excluding for Model Providers and Tools" (#7324) 2024-08-15 23:51:00 +08:00
噢哎哟喂
6fdbc7dbf3
fix error when use farui-plus model (#7316)
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2024-08-15 20:14:13 +08:00
Hongbin
d1a6702aa4
Update PerfXCloud Model List (#7212)
Co-authored-by: xhb <466010723@qq.com>
2024-08-15 19:42:15 +08:00
Xiyuan Chen
7619850855
feat: support pinning, including, and excluding for Model Providers and Tools (#7283) 2024-08-15 12:58:38 +08:00
非法操作
6ff7fd80a1
feat: support OPENAI json_schema (#7258) 2024-08-15 11:29:19 +08:00
非法操作
5aa373dc04
feat: add chatgpt-4o-latest (#7289) 2024-08-15 11:19:10 +08:00
Xiyuan Chen
d29b32fce2
fix: typo in upstage/llm/_position.yaml (#7286) 2024-08-15 08:39:35 +08:00
噢哎哟喂
52383d0161
add support for tongyi-farui (#7248)
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2024-08-14 14:09:13 +08:00
Onelevenvy
0f59d76997
fix: add context_size and max_chunks to Tongyi embedding to resolve issue #7189 (#7227) 2024-08-13 16:35:22 +08:00
shAlfred
a12ddc47e7
feat: add support of speech2text function for OpenAI-API-compatible and Siliconflow (#7197) 2024-08-12 21:38:59 +08:00
Weaxs
67b9fdaad7
siliconflow support bge-3 && bce-v1 embedding (#7198) 2024-08-12 19:14:43 +08:00
ybalbert001
f2cb1fb09f
Fix : Workflow "start" paste url not support s3 pre-signed URL (#6855)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-08-11 16:45:15 +08:00
Yanyi Liu
5b32f2e0dd
Feat: Add model provider Text Embedding Inference for embedding and rerank (#7132) 2024-08-09 19:12:13 +08:00
Yanyi Liu
4cbeb6815b
Fix: Wrong cutoff length lead to empty input in openai compatible embedding model. (#7133) 2024-08-09 19:11:57 +08:00
forrestlinfeng
07511dfaf4
update stepfun model (#7118)
Co-authored-by: chenlinfeng <chenlinfeng@step.ai>
Co-authored-by: Tfsh <tianfs_fight@163.com>
2024-08-08 20:40:37 +08:00
小羽
7944ce0594
feat: wenxin add yi-34b-chat (#7117) 2024-08-08 20:01:21 +08:00
orangeclk
83acb53c08
feat: add zhipu embedding-3 (#7100) 2024-08-08 17:08:46 +08:00
shAlfred
a7162240e6
feat: add text-embedding functon and LLM models to Siliconflow (#7090) 2024-08-08 17:08:28 +08:00
小羽
34a9dbe826
Feat/add 360-zhinao provider (#7069) 2024-08-08 14:23:08 +08:00
orangeclk
f288d367ac
Add price info for zhipu models (#7084) 2024-08-08 14:17:05 +08:00
Waffle
5e2fa13126
feat: support glm-4-long (#7070)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-08-08 10:54:39 +08:00
Joe
d7bb422a5c
fix: hunyuan assistant_prompt_message pydantic error (#7062) 2024-08-07 18:31:40 +08:00
majian
99b78dd198
feat: add gpt-4o-2024-08-06 (#7046) 2024-08-07 15:35:57 +08:00
crazywoola
3516989738
fix: typos in wenxin llm (#7021) 2024-08-06 22:33:03 +08:00
Sa Zhang
26991443ed
fix: Fix incorrect context size for jina-reranker-v2 model (#7006) 2024-08-06 21:08:29 +08:00
Yefori
bd3ed89516
feat: add function calling for deepseek models (#6990) 2024-08-06 13:37:27 +08:00
小羽
23ed15d19f
feat:nvidia add nemotron4-340b and microsoft/phi-3 (#6973) 2024-08-06 10:16:41 +08:00
takatost
6da14c2d48
security: fix api image security issues (#6971) 2024-08-05 20:21:08 +08:00
Pedro Gomes
a34285196b
Revise the wrong pricing of certain LLM models. (#6967) 2024-08-05 18:41:44 +08:00
takatost
ea30174057
chore: optimize streaming tts of xinference (#6966) 2024-08-05 18:23:23 +08:00
liuzhenghua
141e4e0276
fix: restore xinference secret field (#6941)
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
2024-08-04 22:32:24 +08:00
Weaxs
5e634a59a2
compatible xinference reranker server (#6927) 2024-08-04 13:49:38 +08:00
JuHyung Son
2e941bb91c
add new provider Solar (#6884) 2024-08-02 20:48:09 +08:00
sino
8166a8caf5
feat: update llama3.1 parameters for openrouter (#6901) 2024-08-02 13:13:34 +08:00
灰灰
56af1a0adf
pref: change ollama embedded api request (#6876) 2024-08-02 12:04:47 +08:00
dufei
f8617db012
fix tongyi tool calls (#6896) 2024-08-02 10:03:43 +08:00
Weaxs
cc4785f094
fix: xinference reranker return_documents (#6888) 2024-08-01 19:57:53 +08:00
chenxu9741
a9cd6df97e
Remove tts (blocking call) (#6869) 2024-08-01 14:50:22 +08:00
呆萌闷油瓶
f31142e758
Azure 4o mini options (#6873) 2024-08-01 14:04:18 +08:00
crazywoola
792f908afb
Revert "feat:Azure gpt4o mini" (#6870) 2024-08-01 13:32:03 +08:00
呆萌闷油瓶
14367ddc09
feat:Azure gpt4o mini (#6866) 2024-08-01 13:03:08 +08:00
Charlie.Wei
cbf7f21ade
Add azure gpt4omini (#6862)
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-08-01 12:57:52 +08:00
Weaxs
f6e8e120a1
support xinference tts (#6746) 2024-08-01 11:59:15 +08:00
Joe
08f922d8c9
fix: anthropic max token NoneType error (#6858) 2024-08-01 11:30:00 +08:00
小羽
56b43f62d1
feat: nvidia add llama3.1 model (#6844) 2024-07-31 21:24:02 +08:00
Giga Group
4b410494b3
Add model parameter enable_enhance for hunyuan llm model (#6847)
Co-authored-by: sun <sun@centen.cn>
2024-07-31 20:04:43 +08:00
Joe
df9bd36cab
fix: claude-3-5-sonnet-20240620 max token error (#6843) 2024-07-31 18:34:44 +08:00
longzhihun
9ce5cea911
feat: bedrock invoke enhancement (#6808) 2024-07-30 21:57:18 +08:00
SiliconFlow, Inc
3e18d32ce5
add deepseek-coder-v2 in siliconflow (#6149) 2024-07-29 18:45:19 +08:00
Charles
94d68b6a08
upgrade deepseek params (#6744) 2024-07-29 18:31:56 +08:00
Giga Group
c9ff0e3961
Add model hunyuan-embedding (#6657)
Co-authored-by: sun <sun@centen.cn>
2024-07-29 18:30:52 +08:00
Bowen Liang
20268708cc
chore: improve position map conversion and tolerate empty position yaml file (#6541) 2024-07-29 10:32:11 +08:00
-LAN-
83af50368f
fix(api/core/model_runtime/model_providers/azure_openai/llm/llm.py): Try to skip if delta.delta is None. (#6727)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-07-27 00:05:21 +08:00
Joe
e4542215cc
fix: tongyi empty tool_calls is not supported in message (#6719) 2024-07-26 18:10:13 +08:00
Jason
3d3677e912
Feat/model provider novita (#6717)
Co-authored-by: takatost <takatost@gmail.com>
2024-07-26 17:37:21 +08:00
chenxu9741
6b50bb0fe6
issues #6655 Open ai tts issues (#6696) 2024-07-26 14:55:49 +08:00
longzhihun
c5ac004f15
[seanguo] fix: unsupported filename in windows & add Mistral Large 2 (#6679) 2024-07-25 19:26:46 +08:00
RookieAgent
78a339a794
modify llama3-1 yaml filename to support Windows pull operations (#6677) 2024-07-25 18:58:55 +08:00
Giga Group
ca696fe94c
Add support of tool-call for model provider "hunyuan" (#6656)
Co-authored-by: sun <sun@centen.cn>
2024-07-25 11:27:58 +08:00
longzhihun
9815aab7a3
[seanguo] feat: add llama 3.1 support in bedrock (#6645) 2024-07-25 11:20:37 +08:00
zhangzhiqiangcs
d4c55748f1
doc: fix about model features (#6619) 2024-07-24 19:12:10 +08:00
dufei
5af2df0cd5
fix: qwen fc error (#6620)
Co-authored-by: dufei <du_fei@venusgroup.com.cn>
2024-07-24 16:56:06 +08:00
takatost
4c85393a1d
feat: add GroqCloud llama3.1 series models support (#6596) 2024-07-24 00:41:58 +08:00
sino
d5c2680fde
feat: support llama3.1 series models for openrouter provider (#6595) 2024-07-24 00:37:48 +08:00
Joe
8123a00e97
feat: update prompt generate (#6516) 2024-07-23 19:52:14 +08:00
Lance Mao
7c55c39085
feat: add tencent asr (#6091) 2024-07-23 16:38:39 +08:00
-LAN-
5e6fc58db3
Feat/environment variables in workflow (#6515)
Co-authored-by: JzoNg <jzongcode@gmail.com>
2024-07-22 15:29:39 +08:00
sino
4f9f175f25
fix: correct gpt-4o-mini max token (#6472)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-07-19 18:24:58 +08:00
sino
9e168f9d1c
feat: support gpt-4o-mini for openrouter provider (#6447) 2024-07-19 13:09:41 +08:00
Weaxs
ea45496a74
update ernie models (#6454) 2024-07-19 13:08:39 +08:00
Richards Tu
8e49146a35
[EMERGENCY] Fix Anthropic header issue (#6445) 2024-07-19 07:38:15 +08:00
takatost
dad3fd2dc1
feat: add gpt-4o-mini (#6442) 2024-07-19 01:53:43 +08:00
ybalbert001
4a026fa352
Enhancement: add model provider - Amazon Sagemaker (#6255)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-07-18 19:32:31 +08:00
themanforfree
ba181197c2
feat: api_key support for xinference (#6417)
Signed-off-by: themanforfree <themanforfree@gmail.com>
2024-07-18 18:58:46 +08:00
forrestlinfeng
3b5b548af3
Add Stepfun LLM Support (#6346) 2024-07-18 07:47:18 +08:00
Richards Tu
4782fb50c4
Support new Claude-3.5 Sonnet max token limit (#6335) 2024-07-18 07:47:06 +08:00
xielong
f3f052ba36
fix: rename model from ernie-4.0-8k-Latest to ernie-4.0-8k-latest (#6383) 2024-07-17 19:07:47 +08:00