1652 Commits

Author SHA1 Message Date
-LAN-
ae254f0a10
fix(http_request): improve parameter initialization and reorganize tests (#10297) 2024-11-05 16:30:23 +08:00
pinsily
5f21d13572
fix: handle KeyError when accessing rules in CleanProcessor.clean (#10258) 2024-11-05 14:47:15 +08:00
非法操作
bf9349c4dc
feat: add xAI model provider (#10272) 2024-11-05 14:42:47 +08:00
Matsuda
4847548779
feat(model_runtime): add new model 'claude-3-5-haiku-20241022' (#10285) 2024-11-05 14:41:39 +08:00
Matsuda
cb245b5435
fix(model_runtime): fix wrong max_tokens for Claude 3.5 Haiku on Amazon Bedrock (#10286) 2024-11-05 14:41:15 +08:00
-LAN-
08c731fd84
fix(node): correct file property name in function switch (#10284) 2024-11-05 14:23:18 +08:00
Novice
d1505b15c4
feat: Iteration node support parallel mode (#9493) 2024-11-05 10:32:49 +08:00
-LAN-
2c4d8dbe9b
feat(document_extractor): support tool file in document extractor (#10217) 2024-11-05 09:49:43 +08:00
Matsuda
9305ad2102
feat: support Claude 3.5 Haiku on Amazon Bedrock (#10265) 2024-11-05 09:42:51 +08:00
-LAN-
7a98dab6a4
refactor(parameter_extractor): implement custom error classes (#10260) 2024-11-05 09:27:51 +08:00
guogeer
971defbbbd
fix: buitin tool aippt (#10234)
Co-authored-by: jinqi.guo <jinqi.guo@ubtrobot.com>
2024-11-04 18:46:39 +08:00
-LAN-
6b0de08157
fix(validation): allow to use 0 in the inputs form (#10255) 2024-11-04 18:34:55 +08:00
方程
2aa171c348
Using a dedicated interface to obtain the token credential for the gitee.ai provider (#10243) 2024-11-04 17:22:02 +08:00
-LAN-
6452342222
feat(workflow): add configurable workflow file upload limit (#10176)
Co-authored-by: JzoNg <jzongcode@gmail.com>
2024-11-04 15:55:34 +08:00
-LAN-
9369cc44e6
refactor(list_operator): replace ValueError with InvalidKeyError (#10222) 2024-11-04 15:23:08 +08:00
-LAN-
38bca6731c
refactor(workflow): introduce specific error handling for LLM nodes (#10221) 2024-11-04 15:22:58 +08:00
-LAN-
2adab7f71a
refactor(http_request): add custom exception handling for HTTP request nodes (#10219) 2024-11-04 15:22:50 +08:00
-LAN-
be96f6e62d
refactor(workflow): introduce specific exceptions for code validation (#10218) 2024-11-04 15:22:41 +08:00
-LAN-
8b5ea39916
chore(llm_node): remove unnecessary type ignore for context assignment (#10216) 2024-11-04 15:22:31 +08:00
Jyong
1024fc623e
fix the ssrf of docx file extractor external images (#10237) 2024-11-04 15:22:07 +08:00
Jiang
0c9e79cd67
Add Lindorm as a VDB choice (#10202)
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
2024-11-04 09:10:26 +08:00
-LAN-
61da0f08dd
refactor(validation): improve input validation logic (#10175) 2024-11-03 11:55:46 +08:00
-LAN-
1432c268a8
chore(list_operator): refine exception handling for error specificity (#10206) 2024-11-03 11:55:19 +08:00
-LAN-
ec6a03afdd
fix(document_extractor): update base exception class (#10208) 2024-11-03 11:55:07 +08:00
Xiao Ley
b28cf68097
chore: enable vision support for models in OpenRouter that should have supported vision (#10191) 2024-11-02 19:45:20 +08:00
-LAN-
53a7cb0e9d
feat(document_extractor): integrate unstructured API for PPTX extraction (#10180) 2024-11-01 23:19:11 +08:00
-LAN-
86739bea8b
fix(tools): suppress RuntimeWarnings in podcast audio generator (#10182) 2024-11-01 20:59:40 +08:00
Lawrence Li
76b0328eb1
feat: add gpustack model provider (#10158) 2024-11-01 17:23:30 +08:00
-LAN-
3c85136279
refactor(tools): Avoid warnings. (#10161) 2024-11-01 17:17:27 +08:00
Jyong
82033af097
clean un-allowed special charters when doing indexing estimate (#10153) 2024-11-01 15:09:22 +08:00
larcane97
8d5456b6d0
Add VESSL AI OpenAI API-compatible model provider and LLM model (#9474)
Co-authored-by: moon <moon@vessl.ai>
2024-11-01 13:38:52 +08:00
Coal Pigeon
4d5546953a
add llm: ernie-4.0-turbo-128k of wenxin (#10135)
Co-authored-by: Pigeon姚宏锋 <pigeon.yhf@galaxyoversea.com>
2024-10-31 21:49:04 +08:00
Shili Cao
b61baa87ec
fix: avoid unexpected error when create knowledge base with baidu vector database and wenxin embedding model (#10130) 2024-10-31 21:34:23 +08:00
llinvokerl
805c701767
fix: bar chart issue with duplicate x-axis labels being incorrectly ignored (#10134)
Co-authored-by: liusurong.lsr <liusurong.lsr@alibaba-inc.com>
2024-10-31 21:25:47 +08:00
Jyong
dad041c49f
fix issue: query is none when doing retrieval (#10129) 2024-10-31 21:25:00 +08:00
omr
11ca1bec0b
fix: optimize unique document filtering with set (#10082) 2024-10-31 16:32:58 +08:00
非法操作
bd6175157c
feat: enhance comfyui workflow (#10085) 2024-10-31 10:00:22 +08:00
Bowen Liang
0bdae34b5e
improve: significantly speed up the server launching time by async preloading tool providers (#9146) 2024-10-31 00:21:01 +08:00
Charlie.Wei
f6fecb957e
fix azure chatgpt o1 parameter error (#10067) 2024-10-30 22:08:56 +08:00
-LAN-
3b53e06e0d
fix(workflow): refine variable type checks in LLMNode (#10051) 2024-10-30 16:23:12 +08:00
zhuhao
92a3898540
fix: resolve the incorrect model name of hunyuan-standard-256k (#10052) 2024-10-30 15:43:29 +08:00
zhuhao
7433095240
chore: use dify_config.TIDB_SPEND_LIMIT instead of constant value (#10038) 2024-10-30 15:43:07 +08:00
zhuhao
0095896051
feat: add YAML type in document extractor node (#9997) 2024-10-30 13:47:19 +08:00
Jyong
9ebd453b87
add rerank check when doing mutil-retrieval (#9998) 2024-10-30 11:17:39 +08:00
非法操作
c7fb8a4f20
fix: conversation variable may not change in the answer node (#10034) 2024-10-30 11:10:31 +08:00
-LAN-
eb87e690ed
fix(llm-node): handle NoneSegment variables properly (#9978) 2024-10-30 08:46:11 +08:00
Hiroshi Fujita
539fc8b760
Fix content-type header case sensitivity (#9961) 2024-10-30 02:11:18 +08:00
powerfool
878d13ef42
Added OceanBase as an option for the vector store in Dify (#10010) 2024-10-29 21:10:18 +08:00
Jyong
5580bcf870
add tidb spend limit config (#9999) 2024-10-29 17:51:13 +08:00
非法操作
12adcf8925
fix: gemini model use some tools raise error (#9993) 2024-10-29 16:09:29 +08:00