Compare commits

..
181 Commits
Author SHA1 Message Date
-LAN-andGitHub ca21c285b0 chore: update version to 0.10.0 in packaging and docker configurations (#9534) 2024-10-21 18:51:52 +08:00
5a3eaa85bf chore: translate i18n files (#9528)
Co-authored-by: iamjoel <2120155+iamjoel@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-21 18:49:05 +08:00
非法操作andGitHub a5777683f3 fix: when upload file response 3** will raise error (#9555) 2024-10-21 18:44:25 +08:00
JoeandGitHub 90dd91c6cd fix: TOKEN_EXPIRY_MINUTES (#9557) 2024-10-21 18:14:26 +08:00
-LAN-andGitHub 8d8a8fe295 feat(file-upload): add support for optional file source parameter (#9554) 2024-10-21 17:46:24 +08:00
JoelandGitHub 65e22bb76a fix: input vars not auto rename in list operator (#9550) 2024-10-21 16:48:42 +08:00
非法操作andGitHub f83ed19dfe fix: list filter node some operator raise error (#9539) 2024-10-21 15:33:42 +08:00
非法操作andGitHub 53b14bde4d fix: list filter node url not work (#9540) 2024-10-21 15:32:28 +08:00
JoeandGitHub 7742a5dac2 fix: RESET_PASSWORD_TOKEN_EXPIRY_HOURS error (#9542) 2024-10-21 15:25:35 +08:00
Yi XiaoandGitHub bddcb31fe2 Fix: chatbot retrieval setting save issue (#9536) 2024-10-21 14:35:41 +08:00
-LAN-andGitHub b411a89703 fix(dockerfile): update libsqlite3 package version (#9530) 2024-10-21 10:51:28 +08:00
-LAN-andGitHub e61752bd3a feat/enhance the multi-modal support (#8818) 2024-10-21 10:43:49 +08:00
7a1d6fe509 Feat/attachments (#9526)
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
2024-10-21 10:32:37 +08:00
4fd2743efa Feat/new login (#8120)
Co-authored-by: douxc <douxc512@gmail.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
2024-10-21 10:03:40 +08:00
2c0eaaec3d chore: translate i18n files (#9523)
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-10-21 09:43:12 +08:00
NFishandGitHub 3898fe3311 New Auth Methods (#8119) 2024-10-21 09:23:20 +08:00
非法操作andGitHub 853b0e84cc fix: draft run workflow node with image will raise error (#9406) 2024-10-21 09:05:42 +08:00
42fe208eda refactor wenxin rerank (#9486)
Co-authored-by: cuihz <cuihz@knowbox.cn>
2024-10-21 09:03:25 +08:00
kurokoboandGitHub 444dc01931 fix: ignore all files except for .gitkeep under docker/nginx/ssl by gitignore (#9518) 2024-10-20 22:53:32 +08:00
ice yaoandGitHub 95ce10f23b feat: Add custom username and avatar define in discord tool (#9514) 2024-10-20 22:06:18 +08:00
Ziyu HuangandGitHub 660fc3bb34 Resolve 9508 openai compatible rerank (#9511) 2024-10-20 21:59:58 +08:00
zhuhaoandGitHub c71af7f610 fix: resolve the error of docker-compose startup when the storage is baidu-obs (#9502) 2024-10-19 09:58:50 +08:00
Chenhe GuandGitHub ce476f2e5c refine wording in license (#9505) 2024-10-19 09:58:22 +08:00
ZvenandGitHub a9fc85027d chore: update the description for storage_type (#9492) 2024-10-18 20:22:57 +08:00
ice yaoandGitHub b2aa385942 feat: Add volcengine tos storage test (#9495) 2024-10-18 20:08:41 +08:00
424a7da470 add yuqye(https://www.yuque.com)tools (#8960)
Co-authored-by: 佐井 <chengwu.lcw@alibaba-inc.com>
2024-10-18 18:15:34 +08:00
Tao WangandGitHub b92504bebc Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479) 2024-10-18 18:10:33 +08:00
zhuhaoandGitHub e0846792d2 feat: add yi custom llm intergration (#9482) 2024-10-18 17:23:21 +08:00
zhuhaoandGitHub b9bf60ea23 fix: resolve the error with the db-pool-stat endpoint (#9478) 2024-10-18 12:30:25 +08:00
horochxandGitHub bd27b4c162 fix fetch apps (#9453) 2024-10-18 08:24:07 +08:00
Sergio SacristánandGitHub 28de676956 controller test (#9469) 2024-10-18 08:23:36 +08:00
zhuhaoandGitHub b3cde9900c feat: add parameter top-k for the llm model provided by openrouter and siliconflow (#9455) 2024-10-18 08:21:54 +08:00
ice yaoandGitHub 2155bba5b0 fix: update mismatch vector type (#9462) 2024-10-18 08:21:41 +08:00
ice yaoandGitHub a53fdc7126 fix: add missing vector type to migrate command (#9470) 2024-10-18 08:20:22 +08:00
zhuhaoandGitHub 3fc0ebdd51 feat: add yi-lightning llm model for yi (#9458) 2024-10-18 08:19:58 +08:00
211f416806 feat:add wenxin rerank (#9431)
Co-authored-by: cuihz <cuihz@knowbox.cn>
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-17 19:18:32 +08:00
zhuhaoandGitHub b90ad587c2 refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423) 2024-10-17 19:12:42 +08:00
Kevin9703andGitHub e7aecb89dd fix(workflow): Implement automatic variable addition from opening statement to start node (#9450) 2024-10-17 19:01:50 +08:00
zhuhaoandGitHub a45f8969a0 fix: remove the undefined variable line (#9446) 2024-10-17 17:25:14 +08:00
非法操作andGitHub d3c06a3f76 feat: add the workflow tool of comfyUI (#9447) 2024-10-17 16:48:42 +08:00
Wu TianweiandGitHub f447ee7b9d Fix/firefox overflow error (#9438) 2024-10-17 15:54:04 +08:00
ice yaoandGitHub 3e168ce2ca fix: enable Tencent Cloud Vector integration test (#9441) 2024-10-17 15:30:59 +08:00
zxhlyhandGitHub c64edd2706 revert yarnlock (#9445) 2024-10-17 15:03:38 +08:00
Yi XiaoandGitHub 8a1f106c72 Fix: rerank switch and validation before run (#9416) 2024-10-17 14:26:38 +08:00
HRPandGitHub 4ac99ffe0e Update dify-sandbox version to 0.2.10 (#9439) 2024-10-17 13:41:41 +08:00
fdcf87c70c fix https://github.com/langgenius/dify/issues/9409 (#9433)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-10-17 10:47:56 +08:00
JyongandGitHub 5aabb83f5a update dataset clean rule (#9426) 2024-10-17 10:40:22 +08:00
JyongandGitHub bd678f9ca1 add clean 7 days datasets (#9424) 2024-10-16 22:24:50 +08:00
DDDDD12138andGitHub a87890b3cc fix: resolve overlap issue with API Extension selector and modal (#9407) 2024-10-16 17:40:17 +08:00
zhuhaoandGitHub 86594851cb refactor: update the default values of top-k parameter in vdb to be consistent (#9367) 2024-10-16 16:00:21 +08:00
LeoandGitHub a83ccccffc fix: incorrect webapp image displayed (#9401) 2024-10-16 15:31:47 +08:00
JyongandGitHub 50635e9c15 Fix/economical knowledge retrieval (#9396) 2024-10-16 15:13:45 +08:00
zhuhaoandGitHub 7d3dad3d1d feat: add timezone conversion for time tool (#9393) 2024-10-16 11:17:40 +08:00
ice yaoandGitHub dd22e78515 fix: Deprecated gemma2-9b model in Fireworks AI Provider (#9373) 2024-10-16 10:44:54 +08:00
Hash BrownandGitHub 5df1cb0566 feat: storybook (#9324) 2024-10-16 10:18:48 +08:00
crazywoolaandGitHub 423df67042 fix: use gpt-4o-mini for validating credentials (#9387) 2024-10-16 10:18:06 +08:00
ice yaoandGitHub 568d5c46ed feat: Enable baiduvector intergration test (#9369) 2024-10-16 09:41:28 +08:00
非法操作andGitHub da25b91980 fix: remove the stream option of zhipu and gemini (#9319) 2024-10-15 19:13:43 +08:00
ice yaoandGitHub bc0dad6c1c fix: add missing vikingdb param in docker .env.example (#9334) 2024-10-15 19:12:07 +08:00
Jason TanandGitHub 9b8aa9b75d feat: add minimax abab6.5t support (#9365) 2024-10-15 19:00:05 +08:00
Bowen LiangandGitHub d5bc125617 fix: (#9336 followup) skip poetry preperation in style workflow when no change in api folder (#9362) 2024-10-15 17:56:11 +08:00
非法操作andGitHub 4ffaabcc04 feat: add glm-4-flashx, deprecated chatglm_turbo (#9357) 2024-10-15 17:33:34 +08:00
b597a0d31c fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error (#9326)
Co-authored-by: wwwc <wwwc@outlook.com>
2024-10-15 16:26:44 +08:00
Wei-shun BaoandGitHub fb32e5ca9a fix: In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 (#8791) 2024-10-15 16:24:29 +08:00
zhuhaoandGitHub cd7ab6231f refactor: Add an enumeration type and use the factory pattern to obtain the corresponding class (#9356) 2024-10-15 12:51:13 +08:00
ice yaoandGitHub 5908fd6552 Adapt input type parameter with MiniMax embedding model (#9342) 2024-10-15 09:01:00 +08:00
omrandGitHub 6d2c6caa23 refactor: remove unnecessary 'closing' usage for boto3 client (#9343) 2024-10-15 08:42:39 +08:00
Bowen LiangandGitHub 5eb00502ec chore: clean-up unnecessary annotation on configs with non-null default value (#9323) 2024-10-14 23:47:58 +08:00
ice yaoandGitHub 3f9d6759d4 feat: Add qwen2.5 72B Instruct model in Fireworks AI (#9340) 2024-10-14 23:15:34 +08:00
ice yaoandGitHub aba70207ab feat: Add fireworks custom llm intergration (#9333) 2024-10-14 22:50:31 +08:00
Bowen LiangandGitHub a8134a49c4 fix: poetry installation in CI jobs (#9336) 2024-10-14 22:22:03 +08:00
Hash BrownandGitHub fa47f0c707 chore: disable chat service API passing parent_message_id (#8984) 2024-10-14 19:13:16 +08:00
Summer-GuandGitHub 8501af298f feat: added dataset recall testing API (#9300) 2024-10-14 17:26:04 +08:00
-LAN-andGitHub 5c7b1358d4 chore(release): bump version to 0.9.2 (#9314) 2024-10-14 17:21:58 +08:00
Wu TianweiandGitHub 3938d8863e fix: token refreshing logic issue (#9308) 2024-10-14 16:54:23 +08:00
-LAN-andGitHub 7838f9f3a3 fix: Add new Milvus Lite wheel for manylinux2014_aarch64 (#9316) 2024-10-14 16:27:26 +08:00
de3c5751db chore: add reopen preview btn (#9279)
Co-authored-by: billsyli <billsyli@tencent.com>
2024-10-14 13:32:52 +08:00
5ee7e03c1b chore: Optimize operations in Q&A mode (#9274)
Co-authored-by: billsyli <billsyli@tencent.com>
2024-10-14 13:32:13 +08:00
zhuhaoandGitHub 7a405b86c9 refactor: Refactor the service of retrieval the recommend app (#9302) 2024-10-14 13:26:21 +08:00
非法操作andGitHub ffc3f33670 chore: remove the copied zhipu_ai sdk (#9270) 2024-10-14 10:53:45 +08:00
kurokoboandGitHub 857055b797 fix: remove the latest message from the user that does not have any answer yet (#9297) 2024-10-13 23:25:50 +08:00
ice yaoandGitHub d15ba3939d Add Volcengine VikingDB as new vector provider (#9287) 2024-10-13 21:26:05 +08:00
1ec83e4969 chore: translate i18n files (#9288)
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-13 14:56:26 +08:00
zhuhaoandGitHub 9275760599 chore: add baidu-obs and supabase for .env.example (#9289) 2024-10-13 09:44:53 +08:00
zhuhaoandGitHub d97d3ff5fc chore: add abstract decorator and output log when query embedding fails (#9264) 2024-10-12 23:58:41 +08:00
NFishandGitHub ea6734f550 Feat/new account page (#9236) 2024-10-12 23:49:18 +08:00
-LAN-andGitHub f73751843f Feat/implement-refresh-tokens (#9233) 2024-10-12 23:46:30 +08:00
dbfbc56de7 feat: refresh-token (#9286)
Co-authored-by: NFish <douxc512@gmail.com>
2024-10-12 23:40:38 +08:00
70c5b23089 chore: translate i18n files (#9284)
Co-authored-by: YIXIAO0 <54782454+YIXIAO0@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-10-12 23:27:11 +08:00
Shili CaoandGitHub 2ec6ffe478 feat:support baidu vector db (#9185) 2024-10-12 23:24:17 +08:00
Yi XiaoandGitHub 793205afc5 Feat: rerank model verification in front end (#9271) 2024-10-12 21:24:43 +08:00
Garfield DaiandGitHub c6b74daa0a Fix/s3 iam add region name (#7819) 2024-10-12 18:47:59 +08:00
takatostandGitHub 23ce1fb1ba chore: optimize the trace ops slow queries on node executions. (#9282) 2024-10-12 18:30:46 +08:00
takatostandGitHub 29188e0562 chore: use cache instead of re-querying node record during workflow execution (#9280) 2024-10-12 17:48:59 +08:00
zhuhaoandGitHub d9773c963f chore: fix the misclassification of the opensearch-py package (#9266) 2024-10-12 17:37:01 +08:00
NFishandGitHub 1206b1eb96 fix: add new domain to whitelist (#9265) 2024-10-12 11:32:40 +08:00
crazywoolaandGitHub 93af87a9e0 fix: move exception to debug mode (#9258) 2024-10-12 09:28:45 +08:00
zhuhaoandGitHub 7a6970e570 feat: add supabase object storage (#9229) 2024-10-11 22:48:57 +08:00
Likename HaojieandGitHub ea584e94bd fix: dialog box cannot correctly display LaTeX formulas (#9242) 2024-10-11 22:46:44 +08:00
JyongandGitHub 42b02b3a5f Fix/agent external knowledge retrieval (#9241) 2024-10-11 19:21:03 +08:00
Yi XiaoandGitHub 44f6a536d2 fix: reference issue in external knowledge api (#9240) 2024-10-11 19:17:22 +08:00
AkisAyaandGitHub d7b8e071dd fix:#9222 create or update custum tools error (#9228) 2024-10-11 17:12:30 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
3f1aa1f9e2 chore(deps): bump dompurify from 3.0.5 to 3.1.7 in /web (#9232)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-11 16:57:07 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
82024a65cd chore(deps): bump micromatch from 4.0.5 to 4.0.8 in /web (#9234)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2024-10-11 16:56:32 +08:00
f4ce08211d feat: support csp (#9111)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-10-11 16:14:56 +08:00
Bowen LiangandGitHub 7c6ae96a09 chore: check all dependencies groups in pyproject.toml (#9224) 2024-10-11 16:08:36 +08:00
JyongandGitHub 80b62d50f5 Fix/add es num_candidates (#9225) 2024-10-11 16:04:23 +08:00
d498f4e55e Chore/model icon url (#9218)
Co-authored-by: takatost <takatost@gmail.com>
Co-authored-by: jyong <718720800@qq.com>
2024-10-11 12:33:34 +08:00
Hash BrownandGitHub 1c1e008dcf fix: reduce webapp icon displayed on browser tab flickering when page is loading (#9212) 2024-10-11 12:07:39 +08:00
AAEE86andGitHub fe41e8bc18 feat: add siliconflow custom add model interface (#8745) 2024-10-11 11:56:11 +08:00
ccc6723a8e Update docker-compose.yaml (#9183)
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-11 11:55:16 +08:00
JoeandGitHub 1e7ef46e9c fix: update inner api proxies (#9174) 2024-10-11 11:35:01 +08:00
crazywoolaandGitHub e0c8189f1a feat: add NotFound error for dataset service (#9215) 2024-10-11 11:28:09 +08:00
Wu TianweiandGitHub 8bcad002df fix: add loading to 'delete' button & 'save' button (#9214) 2024-10-11 11:22:59 +08:00
Fei HeandGitHub 5c76131d3d feat: add gte rerank for tongyi (#9153) 2024-10-11 10:35:56 +08:00
cabdb4ef17 fix retrieval resource positon missed (#9155)
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
2024-10-11 10:32:42 +08:00
-LAN-andGitHub a34891851b fix(log list): prevent duplicate data fetch (#9190) 2024-10-11 10:32:27 +08:00
zhuhaoandGitHub 05c1ef75c4 feat: add allow_llm_to_see_data flag for vanna (#9156) 2024-10-10 17:39:26 +08:00
Xiaoguang SunandGitHub be2f1e59f2 improve: Refresh updated_at field of DataSourceOauthBinding model (#9173)
Signed-off-by: Xiaoguang Sun <sunxiaoguang@gmail.com>
2024-10-10 17:21:28 +08:00
Sa ZhangandGitHub 75f0a5e36a fix: Typo Correction in jina.yaml (#9161) 2024-10-10 17:00:34 +08:00
JyongandGitHub 68107fe355 downgrade elastic to 8.14 (#9171) 2024-10-10 16:43:11 +08:00
takatostandGitHub 477beae3bb fix: missing usage of metadata in the chatflow app (#9167) 2024-10-10 16:34:06 +08:00
Yi XiaoandGitHub 6689b592ff fix: delete offline "how to write a good knowledge description" helper (#9165) 2024-10-10 15:48:26 +08:00
Charlie.WeiandGitHub 6b6e94da08 Fix code indentation errors (#9164) 2024-10-10 15:26:38 +08:00
Ziyu HuangandGitHub fc60b554a1 Fixes #9159: Modify to make it works to llama.cpp rerank API (#9160) 2024-10-10 15:18:07 +08:00
daiandGitHub bffb0919cc fix: Twitter to X(Twitter) (#9157) 2024-10-10 14:13:20 +08:00
e947103b6d Feat/add workflow sys params (#9108)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-10-10 11:15:52 +08:00
ronaksingh27andGitHub 62051d5171 Corrected type annotation to "Any" from "any" all files in "model_providers" folder (#9135) 2024-10-10 10:34:25 +08:00
crazywoolaandGitHub 783a6b866b fix: #9076 (#9150) 2024-10-10 10:25:45 +08:00
2024a6c941 fix: vertex ai remote url error(Error: not enough values to unpack) (#9134)
Co-authored-by: hobo.l <hobo.l@binance.com>
2024-10-10 10:16:42 +08:00
-LAN-andGitHub 37d5c166ca fix(migrations): correct parent_message_id for service-api records (#9132) 2024-10-10 10:16:24 +08:00
呆萌闷油瓶andGitHub 060897b25b chore:add azure openai api version 2024-09-01-preview (#9141) 2024-10-10 10:07:49 +08:00
非法操作andGitHub 499cc57082 fix: response_format of model_parameters will not be removed (#9148) 2024-10-10 10:07:21 +08:00
Bowen LiangandGitHub b279d19040 chore: avoid star imports usage (#9123) 2024-10-09 21:12:50 +08:00
非法操作andGitHub cb35e84f51 fix: docker env typo (#9119) 2024-10-09 21:11:13 +08:00
Hash BrownandGitHub 511ffa4698 fix: follow-up (suggested questions) does not refer to the most recen… (#9122) 2024-10-09 21:10:55 +08:00
pinsilyandGitHub 7a1da2409d add generate conversation name error log (#9117) 2024-10-09 21:09:36 +08:00
Yi XiaoandGitHub cbd3ffe056 Fix the margin for the rerank switch in retrieval setting (#9124) 2024-10-09 18:26:38 +08:00
Alter-xyzandGitHub ec0aa32cd4 Add customizable size for chatbot embed with default values (#9115) 2024-10-09 16:56:09 +08:00
55679b4389 azure add o1-mini、o1-preview models (#9088)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-10-09 16:15:03 +08:00
kurokoboandGitHub c0b71f8286 feat: respect x-* headers for redirections (#9054) 2024-10-09 14:42:30 +08:00
Bowen LiangandGitHub 240b66d737 chore: avoid implicit optional in type annotations of method (#8727) 2024-10-09 14:36:43 +08:00
Bowen LiangandGitHub b360feb4c1 refactor: introduce storage factory and speed up api startup by importing storage client on demand (#9086) 2024-10-09 14:15:27 +08:00
zhuhaoandGitHub 5fcd614186 feat: output the execution results of tool should only in debug mode (#9104) 2024-10-09 12:53:55 +08:00
zhuhaoandGitHub 4be1aa516c feat: add tags for vanna tools (#9102) 2024-10-09 12:53:03 +08:00
zhuhaoandGitHub 5e250403d3 chore: add the missing tool names to the _position file (#9099) 2024-10-09 11:04:26 +08:00
SebastjanPrachovskijandGitHub f8af9c6ad0 refactor: Update countries & languages list for SearchApi engines (#9090) 2024-10-09 10:24:09 +08:00
57994e4a24 fix s3 presign url check problem, support two versions(v2,v4) (#9093)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-10-09 10:23:21 +08:00
0540995e5c fix: prompt-editor regex.lastIndex needed to reset (#9097)
Co-authored-by: Chen(MAC) <chenchen404@outlook.com>
2024-10-09 10:22:20 +08:00
crazywoolaandGitHub 3a0734d94c Feat/9081 add support for llamaguard through groq provider (#9083) 2024-10-09 01:00:10 +08:00
zhuhaoandGitHub 5b7de7705e feat: add timestamp conversion and timestamp retrieval for time tool (#9085) 2024-10-08 23:25:11 +08:00
Dongsheng ZhaoandGitHub 7121afdd44 fix: #8969 (#9076) 2024-10-08 19:58:03 +08:00
zhuhaoandGitHub 5213650fed feat: update the xinf tool's API key to optional (#9073) 2024-10-08 19:07:53 +08:00
8204e0e14a fix: Count exception occurs when searching conversations (#8754)
Co-authored-by: zheng.gao <zheng.gao@amh-group.com>
2024-10-08 17:25:33 +08:00
InfinitnetandGitHub e741ee2f45 Correct max_tokens for OpenRouter Sonnet 3.5 (#9068) 2024-10-08 16:06:47 +08:00
Sota OizumiandGitHub 0564e8a284 docs: Add Google Cloud Terraform to README (#9065) 2024-10-08 15:39:47 +08:00
非法操作andGitHub 966e65bb66 fix: zhipu ai web_search not work (#9058) 2024-10-08 15:36:31 +08:00
Bowen LiangandGitHub 896998ef3f chore: refine python dependency list and check dependencies in order (#9061) 2024-10-08 15:11:45 +08:00
NFishandGitHub 4abca8614f fix: Ignore the error toast notification if the status is 401 and isPublicAPI is true (#9062) 2024-10-08 11:48:22 +08:00
Bowen LiangandGitHub 7c0b159a81 chore: removing unused imports in tests (#9049) 2024-10-08 11:13:11 +08:00
Sergio SacristánandGitHub a8b4d1ac2a feat: Improvement- use non root user for Web container (#8928) 2024-10-08 11:12:21 +08:00
Bowen LiangandGitHub b933c9d206 chore: move testing env variables from pyproject.toml to pytest.ini (#9019) 2024-10-08 08:40:29 +08:00
呆萌闷油瓶andGitHub f45042aa8e fix:ddg ratelimit 202 (#9047) 2024-10-07 22:13:41 +08:00
2ab8bc679f fix: Missing model information in llm span of Langfuse #9029 (#9030)
Co-authored-by: corel <corelchen@qq.com>
2024-10-07 18:03:30 +08:00
zhuhaoandGitHub 2571b0c4e3 feat: add baidu obs storage (#9024) 2024-10-07 11:09:27 +08:00
zhuhaoandGitHub 959a81a41b refactor: remove the duplicate definitions across different modules (#9022) 2024-10-07 11:08:06 +08:00
Bowen LiangandGitHub 4480b469a6 chore: fix the yanked dependency vesion aiohappyeyeballs 2.4.2 (#9020) 2024-10-07 11:07:34 +08:00
zg0d233andGitHub fcfa1252a0 fix bug when adding openai or openai-compatible stt model instance (#9006) 2024-10-07 11:06:38 +08:00
zhuhaoandGitHub e1e2d0b364 fix: failed to open links to images generated by QR code tool when using Huawei OBS (#9034) 2024-10-07 11:06:08 +08:00
crazywoolaandGitHub 9815a0911b fix: tools description is missing (#8999) 2024-10-03 21:53:11 +08:00
Giannis KepasandGitHub dc5839b6bb feat: Update AWS Bedrock supported regions (#8992) 2024-10-03 15:17:28 +08:00
4373777871 Update json_in_md_parser.py (#8983)
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-03 10:20:56 +08:00
ice yaoandGitHub 415d27c8bf feat(Tools): add discord incoming webhook for sending messages (#7852) 2024-10-02 13:18:35 +08:00
omrandGitHub 5366820a2f fix: corrected typo (#8979) 2024-10-02 12:54:22 +08:00
Hash BrownandGitHub 5f8a27074e fix: chat API is not bringing the conversation/session history (#8965) 2024-10-01 12:10:36 +08:00
zhuhaoandGitHub 24ba9fdf6c feat: enhance stepfun image generation tool (#8954) 2024-10-01 10:55:54 +08:00
zhuhaoandGitHub 824a0dd63e feat: add qwen2.5-72b and llama3.2 for openrouter (#8956) 2024-10-01 10:55:51 +08:00
ice yaoandGitHub c2d606d587 chore: remove unexecuted scripts to avoid ambiguity (#8946) 2024-10-01 09:15:18 +08:00
omrandGitHub 2deaece7e2 refactor: remove unnecessary comment (#8949) 2024-10-01 09:14:49 +08:00
CXwudiandGitHub 0d84221b2c chore: sort Gemini models (#8951) 2024-10-01 09:14:36 +08:00
CXwudiandGitHub cdd7e55a88 chore: add missing models from Voyage (#8950) 2024-10-01 09:14:21 +08:00
940 changed files with 26174 additions and 13344 deletions
+7 -5
View File
@@ -27,19 +27,18 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4
- name: Install Poetry
uses: abatilo/actions-poetry@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: 'poetry'
cache-dependency-path: |
api/pyproject.toml
api/poetry.lock
- name: Poetry check
- name: Install Poetry
uses: abatilo/actions-poetry@v3
- name: Check Poetry lockfile
run: |
poetry check -C api --lock
poetry show -C api
@@ -47,6 +46,9 @@ jobs:
- name: Install dependencies
run: poetry install -C api --with dev
- name: Check dependencies in pyproject.toml
run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
- name: Run Unit tests
run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
-1
View File
@@ -5,7 +5,6 @@ on:
branches:
- "main"
- "deploy/dev"
- "release/0.10.0-beta"
release:
types: [published]
+3 -4
View File
@@ -23,18 +23,17 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4
- name: Install Poetry
uses: abatilo/actions-poetry@v3
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
cache: 'poetry'
cache-dependency-path: |
api/pyproject.toml
api/poetry.lock
- name: Install Poetry
uses: abatilo/actions-poetry@v3
- name: Install dependencies
run: poetry install -C api
+4 -3
View File
@@ -24,15 +24,16 @@ jobs:
with:
files: api/**
- name: Install Poetry
uses: abatilo/actions-poetry@v3
- name: Set up Python
uses: actions/setup-python@v5
if: steps.changed-files.outputs.any_changed == 'true'
with:
python-version: '3.10'
- name: Install Poetry
if: steps.changed-files.outputs.any_changed == 'true'
uses: abatilo/actions-poetry@v3
- name: Python dependencies
if: steps.changed-files.outputs.any_changed == 'true'
run: poetry install -C api --only lint
+2
View File
@@ -175,6 +175,8 @@ docker/volumes/pgvector/data/*
docker/volumes/pgvecto_rs/data/*
docker/nginx/conf.d/default.conf
docker/nginx/ssl/*
!docker/nginx/ssl/.gitkeep
docker/middleware.env
sdks/python-client/build
+3 -2
View File
@@ -6,8 +6,9 @@ Dify is licensed under the Apache License 2.0, with the following additional con
a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment.
- Tenant Definition: Within the context of Dify, one tenant corresponds to one workspace. The workspace provides a separated area for each tenant's data and configurations.
b. LOGO and copyright information: In the process of using Dify's frontend components, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend components.
b. LOGO and copyright information: In the process of using Dify's frontend, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend.
- Frontend Definition: For the purposes of this license, the "frontend" of Dify includes all components located in the `web/` directory when running Dify from the raw source code, or the "web" image when running Dify with Docker.
Please contact business@dify.ai by email to inquire about licensing matters.
+7 -3
View File
@@ -17,7 +17,7 @@
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
alt="follow on X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -196,10 +196,14 @@ If you'd like to configure a highly-available setup, there are community-contrib
#### Using Terraform for Deployment
Deploy Dify to Cloud Platform with a single click using [terraform](https://www.terraform.io/)
##### Azure Global
Deploy Dify to Azure with a single click using [terraform](https://www.terraform.io/).
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Contributing
For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
@@ -219,7 +223,7 @@ At the same time, please consider supporting Dify by sharing it on social media
* [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
## Star history
+5 -2
View File
@@ -17,7 +17,7 @@
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
alt="follow on X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -179,10 +179,13 @@ docker compose up -d
#### استخدام Terraform للتوزيع
انشر Dify إلى منصة السحابة بنقرة واحدة باستخدام [terraform](https://www.terraform.io/)
##### Azure Global
استخدم [terraform](https://www.terraform.io/) لنشر Dify على Azure بنقرة واحدة.
- [Azure Terraform بواسطة @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## المساهمة
+7 -3
View File
@@ -17,7 +17,7 @@
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
alt="follow on X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,14 @@ docker compose up -d
#### 使用 Terraform 部署
使用 [terraform](https://www.terraform.io/) 一键将 Dify 部署到云平台
##### Azure Global
使用 [terraform](https://www.terraform.io/) 一键部署 Dify 到 Azure。
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
@@ -232,7 +236,7 @@ docker compose up -d
- [GitHub Issues](https://github.com/langgenius/dify/issues)。👉:使用 Dify.AI 时遇到的错误和问题,请参阅[贡献指南](CONTRIBUTING.md)。
- [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉:关于使用 Dify.AI 的问题。
- [Discord](https://discord.gg/FngNHpbcY7)。👉:分享您的应用程序并与社区交流。
- [Twitter](https://twitter.com/dify_ai)。👉:分享您的应用程序并与社区交流。
- [X(Twitter)](https://twitter.com/dify_ai)。👉:分享您的应用程序并与社区交流。
- [商业许可](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)。👉:有关商业用途许可 Dify.AI 的商业咨询。
- [微信]() 👉:扫描下方二维码,添加微信好友,备注 Dify,我们将邀请您加入 Dify 社区。
<img src="./images/wechat.png" alt="wechat" width="100"/>
+6 -3
View File
@@ -17,7 +17,7 @@
alt="chat en Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="seguir en Twitter"></a>
alt="seguir en X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -204,10 +204,13 @@ Si desea configurar una configuración de alta disponibilidad, la comunidad prop
#### Uso de Terraform para el despliegue
Despliega Dify en una plataforma en la nube con un solo clic utilizando [terraform](https://www.terraform.io/)
##### Azure Global
Utiliza [terraform](https://www.terraform.io/) para desplegar Dify en Azure con un solo clic.
- [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Contribuir
@@ -228,7 +231,7 @@ Al mismo tiempo, considera apoyar a Dify compartiéndolo en redes sociales y en
* [Discusión en GitHub](https://github.com/langgenius/dify/discussions). Lo mejor para: compartir comentarios y hacer preguntas.
* [Reporte de problemas en GitHub](https://github.com/langgenius/dify/issues). Lo mejor para: errores que encuentres usando Dify.AI y propuestas de características. Consulta nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
* [Twitter](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
* [X(Twitter)](https://twitter.com/dify_ai). Lo mejor para: compartir tus aplicaciones y pasar el rato con la comunidad.
## Historial de Estrellas
+6 -3
View File
@@ -17,7 +17,7 @@
alt="chat sur Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="suivre sur Twitter"></a>
alt="suivre sur X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,13 @@ Si vous souhaitez configurer une configuration haute disponibilité, la communau
#### Utilisation de Terraform pour le déploiement
Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](https://www.terraform.io/)
##### Azure Global
Utilisez [terraform](https://www.terraform.io/) pour déployer Dify sur Azure en un clic.
- [Azure Terraform par @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Contribuer
@@ -226,7 +229,7 @@ Dans le même temps, veuillez envisager de soutenir Dify en le partageant sur le
* [Discussion GitHub](https://github.com/langgenius/dify/discussions). Meilleur pour: partager des commentaires et poser des questions.
* [Problèmes GitHub](https://github.com/langgenius/dify/issues). Meilleur pour: les bogues que vous rencontrez en utilisant Dify.AI et les propositions de fonctionnalités. Consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Meilleur pour: partager vos applications et passer du temps avec la communauté.
* [Twitter](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
* [X(Twitter)](https://twitter.com/dify_ai). Meilleur pour: partager vos applications et passer du temps avec la communauté.
## Historique des étoiles
+9 -6
View File
@@ -17,7 +17,7 @@
alt="Discordでチャット"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="Twitterでフォロー"></a>
alt="X(Twitter)でフォロー"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -68,7 +68,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
プロンプトの作成、モデルパフォーマンスの比較が行え、チャットベースのアプリに音声合成などの機能も追加できます。
**4. RAGパイプライン**:
ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサーポイントも提供します。
ドキュメントの取り込みから検索までをカバーする広範なRAG機能ができます。ほかにもPDF、PPT、その他の一般的なドキュメントフォーマットからのテキスト抽出のサートも提供します。
**5. エージェント機能**:
LLM Function CallingやReActに基づくエージェントの定義が可能で、AIエージェント用のプリビルトまたはカスタムツールを追加できます。Difyには、Google検索、DALL·E、Stable Diffusion、WolframAlphaなどのAIエージェント用の50以上の組み込みツールが提供します。
@@ -201,10 +201,13 @@ docker compose up -d
#### Terraformを使用したデプロイ
##### Azure Global
[terraform](https://www.terraform.io/) を使用して、AzureにDifyをワンクリックでデプロイします。
- [nikawangのAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
[terraform](https://www.terraform.io/) を使用して、ワンクリックでDifyをクラウドプラットフォームにデプロイします
##### Azure Global
- [@nikawangによるAzure Terraform](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
## 貢献
@@ -225,7 +228,7 @@ docker compose up -d
* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
* [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
* [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
* [Twitter](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。
+8 -5
View File
@@ -17,7 +17,7 @@
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
alt="follow on X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -202,10 +202,13 @@ If you'd like to configure a highly-available setup, there are community-contrib
#### Terraform atorlugu pilersitsineq
##### Azure Global
Atoruk [terraform](https://www.terraform.io/) Dify-mik Azure-mut ataatsikkut ikkussuilluarlugu.
- [Azure Terraform atorlugu @nikawang](https://github.com/nikawang/dify-azure-terraform)
wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/) lo'laH.
##### Azure Global
- [Azure Terraform mung @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Contributing
@@ -228,7 +231,7 @@ At the same time, please consider supporting Dify by sharing it on social media
). Best for: sharing feedback and asking questions.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
* [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
## Star History
+6 -3
View File
@@ -17,7 +17,7 @@
alt="chat on Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="follow on Twitter"></a>
alt="follow on X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -39,7 +39,6 @@
<a href="./README_AR.md"><img alt="README بالعربية" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
<a href="./README_TR.md"><img alt="Türkçe README" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
<a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
</p>
@@ -195,10 +194,14 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
#### Terraform을 사용한 배포
[terraform](https://www.terraform.io/)을 사용하여 단 한 번의 클릭으로 Dify를 클라우드 플랫폼에 배포하십시오
##### Azure Global
[terraform](https://www.terraform.io/)을 사용하여 Azure에 Dify를 원클릭으로 배포하세요.
- [nikawang의 Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
## 기여
코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.
+8 -4
View File
@@ -17,7 +17,7 @@
alt="Discord'da sohbet et"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="Twitter'da takip et"></a>
alt="X(Twitter)'da takip et"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -200,9 +200,13 @@ Yüksek kullanılabilirliğe sahip bir kurulum yapılandırmak isterseniz, Dify'
#### Dağıtım için Terraform Kullanımı
Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.terraform.io/) kullanarak
##### Azure Global
[Terraform](https://www.terraform.io/) kullanarak Dify'ı Azure'a tek tıklamayla dağıtın.
- [@nikawang tarafından Azure Terraform](https://github.com/nikawang/dify-azure-terraform)
- [Azure Terraform tarafından @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Katkıda Bulunma
@@ -222,7 +226,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
* [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
* [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
* [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
* [Twitter](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
## Star history
+7 -3
View File
@@ -17,7 +17,7 @@
alt="chat trên Discord"></a>
<a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
<img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
alt="theo dõi trên Twitter"></a>
alt="theo dõi trên X(Twitter)"></a>
<a href="https://hub.docker.com/u/langgenius" target="_blank">
<img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
<a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -196,10 +196,14 @@ Nếu bạn muốn cấu hình một cài đặt có độ sẵn sàng cao, có
#### Sử dụng Terraform để Triển khai
Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/)
##### Azure Global
Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách sử dụng [terraform](https://www.terraform.io/).
- [Azure Terraform bởi @nikawang](https://github.com/nikawang/dify-azure-terraform)
##### Google Cloud
- [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
## Đóng góp
Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
@@ -219,7 +223,7 @@ Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách s
* [Thảo luận GitHub](https://github.com/langgenius/dify/discussions). Tốt nhất cho: chia sẻ phản hồi và đặt câu hỏi.
* [Vấn đề GitHub](https://github.com/langgenius/dify/issues). Tốt nhất cho: lỗi bạn gặp phải khi sử dụng Dify.AI và đề xuất tính năng. Xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi.
* [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
* [X(Twitter)](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
## Lịch sử Yêu thích
+40 -2
View File
@@ -20,6 +20,9 @@ FILES_URL=http://127.0.0.1:5001
# The time in seconds after the signature is rejected
FILES_ACCESS_TIMEOUT=300
# Access token expiration time in minutes
ACCESS_TOKEN_EXPIRE_MINUTES=60
# celery configuration
CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
@@ -39,7 +42,7 @@ DB_DATABASE=dify
# Storage configuration
# use for store upload files, private keys...
# storage type: local, s3, azure-blob, google-storage, tencent-cos, huawei-obs, volcengine-tos
# storage type: local, s3, aliyun-oss, azure-blob, baidu-obs, google-storage, huawei-obs, oci-storage, tencent-cos, volcengine-tos, supabase
STORAGE_TYPE=local
STORAGE_LOCAL_PATH=storage
S3_USE_AWS_MANAGED_IAM=false
@@ -79,6 +82,12 @@ HUAWEI_OBS_SECRET_KEY=your-secret-key
HUAWEI_OBS_ACCESS_KEY=your-access-key
HUAWEI_OBS_SERVER=your-server-url
# Baidu OBS Storage Configuration
BAIDU_OBS_BUCKET_NAME=your-bucket-name
BAIDU_OBS_SECRET_KEY=your-secret-key
BAIDU_OBS_ACCESS_KEY=your-access-key
BAIDU_OBS_ENDPOINT=your-server-url
# OCI Storage configuration
OCI_ENDPOINT=your-endpoint
OCI_BUCKET_NAME=your-bucket-name
@@ -93,11 +102,16 @@ VOLCENGINE_TOS_ACCESS_KEY=your-access-key
VOLCENGINE_TOS_SECRET_KEY=your-secret-key
VOLCENGINE_TOS_REGION=your-region
# Supabase Storage Configuration
SUPABASE_BUCKET_NAME=your-bucket-name
SUPABASE_API_KEY=your-access-key
SUPABASE_URL=your-server-url
# CORS configuration
WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector
# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb
VECTOR_STORE=weaviate
# Weaviate configuration
@@ -197,6 +211,24 @@ OPENSEARCH_USER=admin
OPENSEARCH_PASSWORD=admin
OPENSEARCH_SECURE=true
# Baidu configuration
BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000
BAIDU_VECTOR_DB_ACCOUNT=root
BAIDU_VECTOR_DB_API_KEY=dify
BAIDU_VECTOR_DB_DATABASE=dify
BAIDU_VECTOR_DB_SHARD=1
BAIDU_VECTOR_DB_REPLICAS=3
# ViKingDB configuration
VIKINGDB_ACCESS_KEY=your-ak
VIKINGDB_SECRET_KEY=your-sk
VIKINGDB_REGION=cn-shanghai
VIKINGDB_HOST=api-vikingdb.xxx.volces.com
VIKINGDB_SCHEMA=http
VIKINGDB_CONNECTION_TIMEOUT=30
VIKINGDB_SOCKET_TIMEOUT=30
# Upload configuration
UPLOAD_FILE_SIZE_LIMIT=15
UPLOAD_FILE_BATCH_LIMIT=5
@@ -267,6 +299,9 @@ HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
# Respect X-* headers to redirect clients
RESPECT_XFORWARD_HEADERS_ENABLED=false
# Log file path
LOG_FILE=
@@ -295,3 +330,6 @@ POSITION_TOOL_EXCLUDES=
POSITION_PROVIDER_PINS=
POSITION_PROVIDER_INCLUDES=
POSITION_PROVIDER_EXCLUDES=
# Reset password token expiry minutes
RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
+1 -1
View File
@@ -55,7 +55,7 @@ RUN apt-get update \
&& echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
&& apt-get update \
# For Security
&& apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
&& apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.1-1 \
&& apt-get autoremove -y \
&& rm -rf /var/lib/apt/lists/*
+1
View File
@@ -85,3 +85,4 @@
cd ../
poetry run -C api bash dev/pytest/pytest_all_tests.sh
```
+4 -203
View File
@@ -10,43 +10,20 @@ if os.environ.get("DEBUG", "false").lower() != "true":
grpc.experimental.gevent.init_gevent()
import json
import logging
import sys
import threading
import time
import warnings
from logging.handlers import RotatingFileHandler
from flask import Flask, Response, request
from flask_cors import CORS
from werkzeug.exceptions import Unauthorized
from flask import Response
import contexts
from commands import register_commands
from configs import dify_config
from app_factory import create_app
# DO NOT REMOVE BELOW
from events import event_handlers
from extensions import (
ext_celery,
ext_code_based_extension,
ext_compress,
ext_database,
ext_hosting_provider,
ext_login,
ext_mail,
ext_migrate,
ext_redis,
ext_sentry,
ext_storage,
)
from events import event_handlers # noqa: F401
from extensions.ext_database import db
from extensions.ext_login import login_manager
from libs.passport import PassportService
# TODO: Find a way to avoid importing models here
from models import account, dataset, model, source, task, tool, tools, web
from services.account_service import AccountService
from models import account, dataset, model, source, task, tool, tools, web # noqa: F401
# DO NOT REMOVE ABOVE
@@ -59,188 +36,12 @@ if hasattr(time, "tzset"):
time.tzset()
class DifyApp(Flask):
pass
# -------------
# Configuration
# -------------
config_type = os.getenv("EDITION", default="SELF_HOSTED") # ce edition first
# ----------------------------
# Application Factory Function
# ----------------------------
def create_flask_app_with_configs() -> Flask:
"""
create a raw flask app
with configs loaded from .env file
"""
dify_app = DifyApp(__name__)
dify_app.config.from_mapping(dify_config.model_dump())
# populate configs into system environment variables
for key, value in dify_app.config.items():
if isinstance(value, str):
os.environ[key] = value
elif isinstance(value, int | float | bool):
os.environ[key] = str(value)
elif value is None:
os.environ[key] = ""
return dify_app
def create_app() -> Flask:
app = create_flask_app_with_configs()
app.secret_key = app.config["SECRET_KEY"]
log_handlers = None
log_file = app.config.get("LOG_FILE")
if log_file:
log_dir = os.path.dirname(log_file)
os.makedirs(log_dir, exist_ok=True)
log_handlers = [
RotatingFileHandler(
filename=log_file,
maxBytes=1024 * 1024 * 1024,
backupCount=5,
),
logging.StreamHandler(sys.stdout),
]
logging.basicConfig(
level=app.config.get("LOG_LEVEL"),
format=app.config["LOG_FORMAT"],
datefmt=app.config.get("LOG_DATEFORMAT"),
handlers=log_handlers,
force=True,
)
log_tz = app.config.get("LOG_TZ")
if log_tz:
from datetime import datetime
import pytz
timezone = pytz.timezone(log_tz)
def time_converter(seconds):
return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
for handler in logging.root.handlers:
assert handler.formatter
handler.formatter.converter = time_converter
initialize_extensions(app)
register_blueprints(app)
register_commands(app)
return app
def initialize_extensions(app):
# Since the application instance is now created, pass it to each Flask
# extension instance to bind it to the Flask application instance (app)
ext_compress.init_app(app)
ext_code_based_extension.init()
ext_database.init_app(app)
ext_migrate.init(app, db)
ext_redis.init_app(app)
ext_storage.init_app(app)
ext_celery.init_app(app)
ext_login.init_app(app)
ext_mail.init_app(app)
ext_hosting_provider.init_app(app)
ext_sentry.init_app(app)
# Flask-Login configuration
@login_manager.request_loader
def load_user_from_request(request_from_flask_login):
"""Load user based on the request."""
if request.blueprint not in {"console", "inner_api"}:
return None
# Check if the user_id contains a dot, indicating the old format
auth_header = request.headers.get("Authorization", "")
if not auth_header:
auth_token = request.args.get("_token")
if not auth_token:
raise Unauthorized("Invalid Authorization token.")
else:
if " " not in auth_header:
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
auth_scheme, auth_token = auth_header.split(None, 1)
auth_scheme = auth_scheme.lower()
if auth_scheme != "bearer":
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
decoded = PassportService().verify(auth_token)
user_id = decoded.get("user_id")
account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
if account:
contexts.tenant_id.set(account.current_tenant_id)
return account
@login_manager.unauthorized_handler
def unauthorized_handler():
"""Handle unauthorized requests."""
return Response(
json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
status=401,
content_type="application/json",
)
# register blueprint routers
def register_blueprints(app):
from controllers.console import bp as console_app_bp
from controllers.files import bp as files_bp
from controllers.inner_api import bp as inner_api_bp
from controllers.service_api import bp as service_api_bp
from controllers.web import bp as web_bp
CORS(
service_api_bp,
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
)
app.register_blueprint(service_api_bp)
CORS(
web_bp,
resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
supports_credentials=True,
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
expose_headers=["X-Version", "X-Env"],
)
app.register_blueprint(web_bp)
CORS(
console_app_bp,
resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
supports_credentials=True,
allow_headers=["Content-Type", "Authorization"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
expose_headers=["X-Version", "X-Env"],
)
app.register_blueprint(console_app_bp)
CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
app.register_blueprint(files_bp)
app.register_blueprint(inner_api_bp)
# create app
app = create_app()
celery = app.extensions["celery"]
+213
View File
@@ -0,0 +1,213 @@
import os
if os.environ.get("DEBUG", "false").lower() != "true":
from gevent import monkey
monkey.patch_all()
import grpc.experimental.gevent
grpc.experimental.gevent.init_gevent()
import json
import logging
import sys
from logging.handlers import RotatingFileHandler
from flask import Flask, Response, request
from flask_cors import CORS
from werkzeug.exceptions import Unauthorized
import contexts
from commands import register_commands
from configs import dify_config
from extensions import (
ext_celery,
ext_code_based_extension,
ext_compress,
ext_database,
ext_hosting_provider,
ext_login,
ext_mail,
ext_migrate,
ext_proxy_fix,
ext_redis,
ext_sentry,
ext_storage,
)
from extensions.ext_database import db
from extensions.ext_login import login_manager
from libs.passport import PassportService
from services.account_service import AccountService
class DifyApp(Flask):
pass
# ----------------------------
# Application Factory Function
# ----------------------------
def create_flask_app_with_configs() -> Flask:
"""
create a raw flask app
with configs loaded from .env file
"""
dify_app = DifyApp(__name__)
dify_app.config.from_mapping(dify_config.model_dump())
# populate configs into system environment variables
for key, value in dify_app.config.items():
if isinstance(value, str):
os.environ[key] = value
elif isinstance(value, int | float | bool):
os.environ[key] = str(value)
elif value is None:
os.environ[key] = ""
return dify_app
def create_app() -> Flask:
app = create_flask_app_with_configs()
app.secret_key = app.config["SECRET_KEY"]
log_handlers = None
log_file = app.config.get("LOG_FILE")
if log_file:
log_dir = os.path.dirname(log_file)
os.makedirs(log_dir, exist_ok=True)
log_handlers = [
RotatingFileHandler(
filename=log_file,
maxBytes=1024 * 1024 * 1024,
backupCount=5,
),
logging.StreamHandler(sys.stdout),
]
logging.basicConfig(
level=app.config.get("LOG_LEVEL"),
format=app.config.get("LOG_FORMAT"),
datefmt=app.config.get("LOG_DATEFORMAT"),
handlers=log_handlers,
force=True,
)
log_tz = app.config.get("LOG_TZ")
if log_tz:
from datetime import datetime
import pytz
timezone = pytz.timezone(log_tz)
def time_converter(seconds):
return datetime.utcfromtimestamp(seconds).astimezone(timezone).timetuple()
for handler in logging.root.handlers:
handler.formatter.converter = time_converter
initialize_extensions(app)
register_blueprints(app)
register_commands(app)
return app
def initialize_extensions(app):
# Since the application instance is now created, pass it to each Flask
# extension instance to bind it to the Flask application instance (app)
ext_compress.init_app(app)
ext_code_based_extension.init()
ext_database.init_app(app)
ext_migrate.init(app, db)
ext_redis.init_app(app)
ext_storage.init_app(app)
ext_celery.init_app(app)
ext_login.init_app(app)
ext_mail.init_app(app)
ext_hosting_provider.init_app(app)
ext_sentry.init_app(app)
ext_proxy_fix.init_app(app)
# Flask-Login configuration
@login_manager.request_loader
def load_user_from_request(request_from_flask_login):
"""Load user based on the request."""
if request.blueprint not in {"console", "inner_api"}:
return None
# Check if the user_id contains a dot, indicating the old format
auth_header = request.headers.get("Authorization", "")
if not auth_header:
auth_token = request.args.get("_token")
if not auth_token:
raise Unauthorized("Invalid Authorization token.")
else:
if " " not in auth_header:
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
auth_scheme, auth_token = auth_header.split(None, 1)
auth_scheme = auth_scheme.lower()
if auth_scheme != "bearer":
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
decoded = PassportService().verify(auth_token)
user_id = decoded.get("user_id")
logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
if logged_in_account:
contexts.tenant_id.set(logged_in_account.current_tenant_id)
return logged_in_account
@login_manager.unauthorized_handler
def unauthorized_handler():
"""Handle unauthorized requests."""
return Response(
json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
status=401,
content_type="application/json",
)
# register blueprint routers
def register_blueprints(app):
from controllers.console import bp as console_app_bp
from controllers.files import bp as files_bp
from controllers.inner_api import bp as inner_api_bp
from controllers.service_api import bp as service_api_bp
from controllers.web import bp as web_bp
CORS(
service_api_bp,
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
)
app.register_blueprint(service_api_bp)
CORS(
web_bp,
resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
supports_credentials=True,
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
expose_headers=["X-Version", "X-Env"],
)
app.register_blueprint(web_bp)
CORS(
console_app_bp,
resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
supports_credentials=True,
allow_headers=["Content-Type", "Authorization"],
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
expose_headers=["X-Version", "X-Env"],
)
app.register_blueprint(console_app_bp)
CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
app.register_blueprint(files_bp)
app.register_blueprint(inner_api_bp)
+25 -48
View File
@@ -259,6 +259,25 @@ def migrate_knowledge_vector_database():
skipped_count = 0
total_count = 0
vector_type = dify_config.VECTOR_STORE
upper_colletion_vector_types = {
VectorType.MILVUS,
VectorType.PGVECTOR,
VectorType.RELYT,
VectorType.WEAVIATE,
VectorType.ORACLE,
VectorType.ELASTICSEARCH,
}
lower_colletion_vector_types = {
VectorType.ANALYTICDB,
VectorType.CHROMA,
VectorType.MYSCALE,
VectorType.PGVECTO_RS,
VectorType.TIDB_VECTOR,
VectorType.OPENSEARCH,
VectorType.TENCENT,
VectorType.BAIDU,
VectorType.VIKINGDB,
}
page = 1
while True:
try:
@@ -284,11 +303,9 @@ def migrate_knowledge_vector_database():
skipped_count = skipped_count + 1
continue
collection_name = ""
if vector_type == VectorType.WEAVIATE:
dataset_id = dataset.id
dataset_id = dataset.id
if vector_type in upper_colletion_vector_types:
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.QDRANT:
if dataset.collection_binding_id:
dataset_collection_binding = (
@@ -301,55 +318,15 @@ def migrate_knowledge_vector_database():
else:
raise ValueError("Dataset Collection Binding not found")
else:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.MILVUS:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.RELYT:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.TENCENT:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.PGVECTOR:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.OPENSEARCH:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {
"type": VectorType.OPENSEARCH,
"vector_store": {"class_prefix": collection_name},
}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.ANALYTICDB:
dataset_id = dataset.id
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {
"type": VectorType.ANALYTICDB,
"vector_store": {"class_prefix": collection_name},
}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type == VectorType.ELASTICSEARCH:
dataset_id = dataset.id
index_name = Dataset.gen_collection_name_by_id(dataset_id)
index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
dataset.index_struct = json.dumps(index_struct_dict)
elif vector_type in lower_colletion_vector_types:
collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
else:
raise ValueError(f"Vector store {vector_type} is not supported.")
index_struct_dict = {"type": vector_type, "vector_store": {"class_prefix": collection_name}}
dataset.index_struct = json.dumps(index_struct_dict)
vector = Vector(dataset)
click.echo(f"Migrating dataset {dataset.id}.")
+69 -11
View File
@@ -1,6 +1,15 @@
from typing import Annotated, Literal, Optional
from pydantic import AliasChoices, Field, HttpUrl, NegativeInt, NonNegativeInt, PositiveInt, computed_field
from pydantic import (
AliasChoices,
Field,
HttpUrl,
NegativeInt,
NonNegativeInt,
PositiveFloat,
PositiveInt,
computed_field,
)
from pydantic_settings import BaseSettings
from configs.feature.hosted_service import HostedServiceConfig
@@ -18,9 +27,9 @@ class SecurityConfig(BaseSettings):
default="",
)
RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
description="Duration in hours for which a password reset token remains valid",
default=24,
RESET_PASSWORD_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
description="Duration in minutes for which a password reset token remains valid",
default=5,
)
@@ -257,6 +266,12 @@ class HttpConfig(BaseSettings):
default=None,
)
RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
" to respect X-* headers to redirect clients",
default=False,
)
class InnerAPIConfig(BaseSettings):
"""
@@ -364,9 +379,9 @@ class WorkflowConfig(BaseSettings):
)
class OAuthConfig(BaseSettings):
class AuthConfig(BaseSettings):
"""
Configuration for OAuth authentication
Configuration for authentication and OAuth
"""
OAUTH_REDIRECT_PATH: str = Field(
@@ -375,7 +390,7 @@ class OAuthConfig(BaseSettings):
)
GITHUB_CLIENT_ID: Optional[str] = Field(
description="GitHub OAuth client secret",
description="GitHub OAuth client ID",
default=None,
)
@@ -394,6 +409,11 @@ class OAuthConfig(BaseSettings):
default=None,
)
ACCESS_TOKEN_EXPIRE_MINUTES: PositiveInt = Field(
description="Expiration time for access tokens in minutes",
default=60,
)
class ModerationConfig(BaseSettings):
"""
@@ -472,6 +492,11 @@ class MailConfig(BaseSettings):
default=False,
)
EMAIL_SEND_IP_LIMIT_PER_MINUTE: PositiveInt = Field(
description="Maximum number of emails allowed to be sent from the same IP address in a minute",
default=50,
)
class RagEtlConfig(BaseSettings):
"""
@@ -506,11 +531,16 @@ class DataSetConfig(BaseSettings):
Configuration for dataset management
"""
CLEAN_DAY_SETTING: PositiveInt = Field(
description="Interval in days for dataset cleanup operations",
PLAN_SANDBOX_CLEAN_DAY_SETTING: PositiveInt = Field(
description="Interval in days for dataset cleanup operations - plan: sandbox",
default=30,
)
PLAN_PRO_CLEAN_DAY_SETTING: PositiveInt = Field(
description="Interval in days for dataset cleanup operations - plan: pro and team",
default=7,
)
DATASET_OPERATOR_ENABLED: bool = Field(
description="Enable or disable dataset operator functionality",
default=False,
@@ -609,9 +639,37 @@ class PositionConfig(BaseSettings):
return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
class LoginConfig(BaseSettings):
ENABLE_EMAIL_CODE_LOGIN: bool = Field(
description="whether to enable email code login",
default=False,
)
ENABLE_EMAIL_PASSWORD_LOGIN: bool = Field(
description="whether to enable email password login",
default=True,
)
ENABLE_SOCIAL_OAUTH_LOGIN: bool = Field(
description="whether to enable github/google oauth login",
default=False,
)
EMAIL_CODE_LOGIN_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
description="expiry time in minutes for email code login token",
default=5,
)
ALLOW_REGISTER: bool = Field(
description="whether to enable register",
default=False,
)
ALLOW_CREATE_WORKSPACE: bool = Field(
description="whether to enable create workspace",
default=False,
)
class FeatureConfig(
# place the configs in alphabet order
AppExecutionConfig,
AuthConfig, # Changed from OAuthConfig to AuthConfig
BillingConfig,
CodeExecutionSandboxConfig,
DataSetConfig,
@@ -626,14 +684,14 @@ class FeatureConfig(
MailConfig,
ModelLoadBalanceConfig,
ModerationConfig,
OAuthConfig,
PositionConfig,
RagEtlConfig,
SecurityConfig,
ToolConfig,
UpdateConfig,
WorkflowConfig,
WorkspaceConfig,
PositionConfig,
LoginConfig,
# hosted services config
HostedServiceConfig,
CeleryBeatConfig,
+28 -4
View File
@@ -8,9 +8,11 @@ from configs.middleware.cache.redis_config import RedisConfig
from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageConfig
from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
from configs.middleware.storage.oci_storage_config import OCIStorageConfig
from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
@@ -26,13 +28,15 @@ from configs.middleware.vdb.qdrant_config import QdrantConfig
from configs.middleware.vdb.relyt_config import RelytConfig
from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
from configs.middleware.vdb.vikingdb_config import VikingDBConfig
from configs.middleware.vdb.weaviate_config import WeaviateConfig
class StorageConfig(BaseSettings):
STORAGE_TYPE: str = Field(
description="Type of storage to use."
" Options: 'local', 's3', 'azure-blob', 'aliyun-oss', 'google-storage'. Default is 'local'.",
" Options: 'local', 's3', 'aliyun-oss', 'azure-blob', 'baidu-obs', 'google-storage', 'huawei-obs', "
"'oci-storage', 'tencent-cos', 'volcengine-tos', 'supabase'. Default is 'local'.",
default="local",
)
@@ -190,6 +194,22 @@ class CeleryConfig(DatabaseConfig):
return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False
class InternalTestConfig(BaseSettings):
"""
Configuration settings for Internal Test
"""
AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
description="Internal test AWS secret access key",
default=None,
)
AWS_ACCESS_KEY_ID: Optional[str] = Field(
description="Internal test AWS access key ID",
default=None,
)
class MiddlewareConfig(
# place the configs in alphabet order
CeleryConfig,
@@ -200,12 +220,14 @@ class MiddlewareConfig(
StorageConfig,
AliyunOSSStorageConfig,
AzureBlobStorageConfig,
BaiduOBSStorageConfig,
GoogleCloudStorageConfig,
TencentCloudCOSStorageConfig,
HuaweiCloudOBSStorageConfig,
VolcengineTOSStorageConfig,
S3StorageConfig,
OCIStorageConfig,
S3StorageConfig,
SupabaseStorageConfig,
TencentCloudCOSStorageConfig,
VolcengineTOSStorageConfig,
# configs of vdb and vdb providers
VectorStoreConfig,
AnalyticdbConfig,
@@ -222,5 +244,7 @@ class MiddlewareConfig(
TiDBVectorConfig,
WeaviateConfig,
ElasticsearchConfig,
InternalTestConfig,
VikingDBConfig,
):
pass
@@ -0,0 +1,29 @@
from typing import Optional
from pydantic import BaseModel, Field
class BaiduOBSStorageConfig(BaseModel):
"""
Configuration settings for Baidu Object Storage Service (OBS)
"""
BAIDU_OBS_BUCKET_NAME: Optional[str] = Field(
description="Name of the Baidu OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
default=None,
)
BAIDU_OBS_ACCESS_KEY: Optional[str] = Field(
description="Access Key ID for authenticating with Baidu OBS",
default=None,
)
BAIDU_OBS_SECRET_KEY: Optional[str] = Field(
description="Secret Access Key for authenticating with Baidu OBS",
default=None,
)
BAIDU_OBS_ENDPOINT: Optional[str] = Field(
description="URL of the Baidu OSS endpoint for your chosen region (e.g., 'https://.bj.bcebos.com')",
default=None,
)
@@ -0,0 +1,24 @@
from typing import Optional
from pydantic import BaseModel, Field
class SupabaseStorageConfig(BaseModel):
"""
Configuration settings for Supabase Object Storage Service
"""
SUPABASE_BUCKET_NAME: Optional[str] = Field(
description="Name of the Supabase bucket to store and retrieve objects (e.g., 'dify-bucket')",
default=None,
)
SUPABASE_API_KEY: Optional[str] = Field(
description="API KEY for authenticating with Supabase",
default=None,
)
SUPABASE_URL: Optional[str] = Field(
description="URL of the Supabase",
default=None,
)
@@ -0,0 +1,45 @@
from typing import Optional
from pydantic import Field, NonNegativeInt, PositiveInt
from pydantic_settings import BaseSettings
class BaiduVectorDBConfig(BaseSettings):
"""
Configuration settings for Baidu Vector Database
"""
BAIDU_VECTOR_DB_ENDPOINT: Optional[str] = Field(
description="URL of the Baidu Vector Database service (e.g., 'http://vdb.bj.baidubce.com')",
default=None,
)
BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS: PositiveInt = Field(
description="Timeout in milliseconds for Baidu Vector Database operations (default is 30000 milliseconds)",
default=30000,
)
BAIDU_VECTOR_DB_ACCOUNT: Optional[str] = Field(
description="Account for authenticating with the Baidu Vector Database",
default=None,
)
BAIDU_VECTOR_DB_API_KEY: Optional[str] = Field(
description="API key for authenticating with the Baidu Vector Database service",
default=None,
)
BAIDU_VECTOR_DB_DATABASE: Optional[str] = Field(
description="Name of the specific Baidu Vector Database to connect to",
default=None,
)
BAIDU_VECTOR_DB_SHARD: PositiveInt = Field(
description="Number of shards for the Baidu Vector Database (default is 1)",
default=1,
)
BAIDU_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
description="Number of replicas for the Baidu Vector Database (default is 3)",
default=3,
)
+1 -1
View File
@@ -14,7 +14,7 @@ class OracleConfig(BaseSettings):
default=None,
)
ORACLE_PORT: Optional[PositiveInt] = Field(
ORACLE_PORT: PositiveInt = Field(
description="Port number on which the Oracle database server is listening (default is 1521)",
default=1521,
)
@@ -14,7 +14,7 @@ class PGVectorConfig(BaseSettings):
default=None,
)
PGVECTOR_PORT: Optional[PositiveInt] = Field(
PGVECTOR_PORT: PositiveInt = Field(
description="Port number on which the PostgreSQL server is listening (default is 5433)",
default=5433,
)
@@ -14,7 +14,7 @@ class PGVectoRSConfig(BaseSettings):
default=None,
)
PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
PGVECTO_RS_PORT: PositiveInt = Field(
description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
default=5431,
)
@@ -0,0 +1,49 @@
from typing import Optional
from pydantic import BaseModel, Field
class VikingDBConfig(BaseModel):
"""
Configuration for connecting to Volcengine VikingDB.
Refer to the following documentation for details on obtaining credentials:
https://www.volcengine.com/docs/6291/65568
"""
VIKINGDB_ACCESS_KEY: Optional[str] = Field(
description="The Access Key provided by Volcengine VikingDB for API authentication."
"Refer to the following documentation for details on obtaining credentials:"
"https://www.volcengine.com/docs/6291/65568",
default=None,
)
VIKINGDB_SECRET_KEY: Optional[str] = Field(
description="The Secret Key provided by Volcengine VikingDB for API authentication.",
default=None,
)
VIKINGDB_REGION: str = Field(
description="The region of the Volcengine VikingDB service.(e.g., 'cn-shanghai', 'cn-beijing').",
default="cn-shanghai",
)
VIKINGDB_HOST: str = Field(
description="The host of the Volcengine VikingDB service.(e.g., 'api-vikingdb.volces.com', \
'api-vikingdb.mlp.cn-shanghai.volces.com')",
default="api-vikingdb.mlp.cn-shanghai.volces.com",
)
VIKINGDB_SCHEME: str = Field(
description="The scheme of the Volcengine VikingDB service.(e.g., 'http', 'https').",
default="http",
)
VIKINGDB_CONNECTION_TIMEOUT: int = Field(
description="The connection timeout of the Volcengine VikingDB service.",
default=30,
)
VIKINGDB_SOCKET_TIMEOUT: int = Field(
description="The socket timeout of the Volcengine VikingDB service.",
default=30,
)
+1 -1
View File
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="0.10.0-beta2",
default="0.10.0",
)
COMMIT_SHA: str = Field(
+3 -2
View File
@@ -12,10 +12,11 @@ VIDEO_EXTENSIONS.extend([ext.upper() for ext in VIDEO_EXTENSIONS])
AUDIO_EXTENSIONS = ["mp3", "m4a", "wav", "webm", "amr"]
AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
if dify_config.ETL_TYPE == "Unstructured":
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "ppt", "xml", "epub"))
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
else:
DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
@@ -189,6 +189,7 @@ class ChatConversationApi(Resource):
subquery.c.from_end_user_session_id.ilike(keyword_filter),
),
)
.group_by(Conversation.id)
)
account = current_user
@@ -10,10 +10,10 @@ from controllers.console import api
from controllers.console.app.wraps import get_app_model
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from enums import WorkflowRunTriggeredFrom
from extensions.ext_database import db
from libs.helper import DatetimeString
from libs.login import login_required
from models.enums import WorkflowRunTriggeredFrom
from models.model import AppMode
+19 -19
View File
@@ -1,17 +1,15 @@
import base64
import datetime
import secrets
from flask import request
from flask_restful import Resource, reqparse
from constants.languages import supported_language
from controllers.console import api
from controllers.console.error import AlreadyActivateError
from extensions.ext_database import db
from libs.helper import StrLen, email, timezone
from libs.password import hash_password, valid_password
from models.account import AccountStatus
from services.account_service import RegisterService
from libs.helper import StrLen, email, extract_remote_ip, timezone
from models.account import AccountStatus, Tenant
from services.account_service import AccountService, RegisterService
class ActivateCheckApi(Resource):
@@ -27,8 +25,18 @@ class ActivateCheckApi(Resource):
token = args["token"]
invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
return {"is_valid": invitation is not None, "workspace_name": invitation["tenant"].name if invitation else None}
if invitation:
data = invitation.get("data", {})
tenant: Tenant = invitation.get("tenant", None)
workspace_name = tenant.name if tenant else None
workspace_id = tenant.id if tenant else None
invitee_email = data.get("email") if data else None
return {
"is_valid": invitation is not None,
"data": {"workspace_name": workspace_name, "workspace_id": workspace_id, "email": invitee_email},
}
else:
return {"is_valid": False}
class ActivateApi(Resource):
@@ -38,7 +46,6 @@ class ActivateApi(Resource):
parser.add_argument("email", type=email, required=False, nullable=True, location="json")
parser.add_argument("token", type=str, required=True, nullable=False, location="json")
parser.add_argument("name", type=StrLen(30), required=True, nullable=False, location="json")
parser.add_argument("password", type=valid_password, required=True, nullable=False, location="json")
parser.add_argument(
"interface_language", type=supported_language, required=True, nullable=False, location="json"
)
@@ -54,15 +61,6 @@ class ActivateApi(Resource):
account = invitation["account"]
account.name = args["name"]
# generate password salt
salt = secrets.token_bytes(16)
base64_salt = base64.b64encode(salt).decode()
# encrypt password with salt
password_hashed = hash_password(args["password"], salt)
base64_password_hashed = base64.b64encode(password_hashed).decode()
account.password = base64_password_hashed
account.password_salt = base64_salt
account.interface_language = args["interface_language"]
account.timezone = args["timezone"]
account.interface_theme = "light"
@@ -70,7 +68,9 @@ class ActivateApi(Resource):
account.initialized_at = datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
db.session.commit()
return {"result": "success"}
token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
return {"result": "success", "data": token_pair.model_dump()}
api.add_resource(ActivateCheckApi, "/activate/check")
+25 -1
View File
@@ -27,5 +27,29 @@ class InvalidTokenError(BaseHTTPException):
class PasswordResetRateLimitExceededError(BaseHTTPException):
error_code = "password_reset_rate_limit_exceeded"
description = "Password reset rate limit exceeded. Try again later."
description = "Too many password reset emails have been sent. Please try again in 1 minutes."
code = 429
class EmailCodeError(BaseHTTPException):
error_code = "email_code_error"
description = "Email code is invalid or expired."
code = 400
class EmailOrPasswordMismatchError(BaseHTTPException):
error_code = "email_or_password_mismatch"
description = "The email or password is mismatched."
code = 400
class EmailPasswordLoginLimitError(BaseHTTPException):
error_code = "email_code_login_limit"
description = "Too many incorrect password attempts. Please try again later."
code = 429
class EmailCodeLoginRateLimitExceededError(BaseHTTPException):
error_code = "email_code_login_rate_limit_exceeded"
description = "Too many login emails have been sent. Please try again in 5 minutes."
code = 429
+64 -30
View File
@@ -1,65 +1,82 @@
import base64
import logging
import secrets
from flask import request
from flask_restful import Resource, reqparse
from constants.languages import languages
from controllers.console import api
from controllers.console.auth.error import (
EmailCodeError,
InvalidEmailError,
InvalidTokenError,
PasswordMismatchError,
PasswordResetRateLimitExceededError,
)
from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
from controllers.console.setup import setup_required
from events.tenant_event import tenant_was_created
from extensions.ext_database import db
from libs.helper import email as email_validate
from libs.helper import email, extract_remote_ip
from libs.password import hash_password, valid_password
from models import Account
from services.account_service import AccountService
from services.errors.account import RateLimitExceededError
from models.account import Account
from services.account_service import AccountService, TenantService
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.feature_service import FeatureService
class ForgotPasswordSendEmailApi(Resource):
@setup_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=str, required=True, location="json")
parser.add_argument("email", type=email, required=True, location="json")
parser.add_argument("language", type=str, required=False, location="json")
args = parser.parse_args()
email = args["email"]
ip_address = extract_remote_ip(request)
if AccountService.is_email_send_ip_limit(ip_address):
raise EmailSendIpLimitError()
if not email_validate(email):
raise InvalidEmailError()
account = Account.query.filter_by(email=email).first()
if account:
try:
AccountService.send_reset_password_email(account=account)
except RateLimitExceededError:
logging.warning(f"Rate limit exceeded for email: {account.email}")
raise PasswordResetRateLimitExceededError()
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
# Return success to avoid revealing email registration status
logging.warning(f"Attempt to reset password for unregistered email: {email}")
language = "en-US"
return {"result": "success"}
account = Account.query.filter_by(email=args["email"]).first()
token = None
if account is None:
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_reset_password_email(email=args["email"], language=language)
return {"result": "fail", "data": token, "code": "account_not_found"}
else:
raise NotAllowedRegister()
else:
token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
return {"result": "success", "data": token}
class ForgotPasswordCheckApi(Resource):
@setup_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=str, required=True, location="json")
parser.add_argument("code", type=str, required=True, location="json")
parser.add_argument("token", type=str, required=True, nullable=False, location="json")
args = parser.parse_args()
token = args["token"]
reset_data = AccountService.get_reset_password_data(token)
user_email = args["email"]
if reset_data is None:
return {"is_valid": False, "email": None}
return {"is_valid": True, "email": reset_data.get("email")}
token_data = AccountService.get_reset_password_data(args["token"])
if token_data is None:
raise InvalidTokenError()
if user_email != token_data.get("email"):
raise InvalidEmailError()
if args["code"] != token_data.get("code"):
raise EmailCodeError()
return {"is_valid": True, "email": token_data.get("email")}
class ForgotPasswordResetApi(Resource):
@@ -92,9 +109,26 @@ class ForgotPasswordResetApi(Resource):
base64_password_hashed = base64.b64encode(password_hashed).decode()
account = Account.query.filter_by(email=reset_data.get("email")).first()
account.password = base64_password_hashed
account.password_salt = base64_salt
db.session.commit()
if account:
account.password = base64_password_hashed
account.password_salt = base64_salt
db.session.commit()
tenant = TenantService.get_join_tenants(account)
if not tenant and not FeatureService.get_system_features().is_allow_create_workspace:
tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(tenant, account, role="owner")
account.current_tenant = tenant
tenant_was_created.send(tenant)
else:
try:
account = AccountService.create_account_and_tenant(
email=reset_data.get("email"),
name=reset_data.get("email"),
password=password_confirm,
interface_language=languages[0],
)
except WorkSpaceNotAllowedCreateError:
pass
return {"result": "success"}
+171 -55
View File
@@ -1,16 +1,34 @@
from typing import cast
import flask_login
from flask import request
from flask import redirect, request
from flask_restful import Resource, reqparse
import services
from configs import dify_config
from constants.languages import languages
from controllers.console import api
from controllers.console.auth.error import (
EmailCodeError,
EmailOrPasswordMismatchError,
EmailPasswordLoginLimitError,
InvalidEmailError,
InvalidTokenError,
)
from controllers.console.error import (
AccountBannedError,
EmailSendIpLimitError,
NotAllowedCreateWorkspace,
NotAllowedRegister,
)
from controllers.console.setup import setup_required
from libs.helper import email, get_remote_ip
from events.tenant_event import tenant_was_created
from libs.helper import email, extract_remote_ip
from libs.password import valid_password
from models import Account
from services.account_service import AccountService, TenantService
from models.account import Account
from services.account_service import AccountService, RegisterService, TenantService
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.feature_service import FeatureService
class LoginApi(Resource):
@@ -23,15 +41,43 @@ class LoginApi(Resource):
parser.add_argument("email", type=email, required=True, location="json")
parser.add_argument("password", type=valid_password, required=True, location="json")
parser.add_argument("remember_me", type=bool, required=False, default=False, location="json")
parser.add_argument("invite_token", type=str, required=False, default=None, location="json")
parser.add_argument("language", type=str, required=False, default="en-US", location="json")
args = parser.parse_args()
# todo: Verify the recaptcha
is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
if is_login_error_rate_limit:
raise EmailPasswordLoginLimitError()
invitation = args["invite_token"]
if invitation:
invitation = RegisterService.get_invitation_if_token_valid(None, args["email"], invitation)
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
language = "en-US"
try:
account = AccountService.authenticate(args["email"], args["password"])
except services.errors.account.AccountLoginError as e:
return {"code": "unauthorized", "message": str(e)}, 401
if invitation:
data = invitation.get("data", {})
invitee_email = data.get("email") if data else None
if invitee_email != args["email"]:
raise InvalidEmailError()
account = AccountService.authenticate(args["email"], args["password"], args["invite_token"])
else:
account = AccountService.authenticate(args["email"], args["password"])
except services.errors.account.AccountLoginError:
raise AccountBannedError()
except services.errors.account.AccountPasswordError:
AccountService.add_login_error_rate_limit(args["email"])
raise EmailOrPasswordMismatchError()
except services.errors.account.AccountNotFoundError:
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_reset_password_email(email=args["email"], language=language)
return {"result": "fail", "data": token, "code": "account_not_found"}
else:
raise NotAllowedRegister()
# SELF_HOSTED only have one workspace
tenants = TenantService.get_join_tenants(account)
if len(tenants) == 0:
@@ -40,71 +86,141 @@ class LoginApi(Resource):
"data": "workspace not found, please contact system admin to invite you to join in a workspace",
}
token = AccountService.login(account, ip_address=get_remote_ip(request))
return {"result": "success", "data": token}
token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
AccountService.reset_login_error_rate_limit(args["email"])
return {"result": "success", "data": token_pair.model_dump()}
class LogoutApi(Resource):
@setup_required
def get(self):
account = cast(Account, flask_login.current_user)
token = request.headers.get("Authorization", "").split(" ")[1]
AccountService.logout(account=account, token=token)
if isinstance(account, flask_login.AnonymousUserMixin):
return {"result": "success"}
AccountService.logout(account=account)
flask_login.logout_user()
return {"result": "success"}
class ResetPasswordApi(Resource):
class ResetPasswordSendEmailApi(Resource):
@setup_required
def get(self):
# parser = reqparse.RequestParser()
# parser.add_argument('email', type=email, required=True, location='json')
# args = parser.parse_args()
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
parser.add_argument("language", type=str, required=False, location="json")
args = parser.parse_args()
# import mailchimp_transactional as MailchimpTransactional
# from mailchimp_transactional.api_client import ApiClientError
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
language = "en-US"
# account = {'email': args['email']}
# account = AccountService.get_by_email(args['email'])
# if account is None:
# raise ValueError('Email not found')
# new_password = AccountService.generate_password()
# AccountService.update_password(account, new_password)
account = AccountService.get_user_through_email(args["email"])
if account is None:
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_reset_password_email(email=args["email"], language=language)
else:
raise NotAllowedRegister()
else:
token = AccountService.send_reset_password_email(account=account, language=language)
# todo: Send email
# MAILCHIMP_API_KEY = dify_config.MAILCHIMP_TRANSACTIONAL_API_KEY
# mailchimp = MailchimpTransactional(MAILCHIMP_API_KEY)
return {"result": "success", "data": token}
# message = {
# 'from_email': 'noreply@example.com',
# 'to': [{'email': account['email']}],
# 'subject': 'Reset your Dify password',
# 'html': """
# <p>Dear User,</p>
# <p>The Dify team has generated a new password for you, details as follows:</p>
# <p><strong>{new_password}</strong></p>
# <p>Please change your password to log in as soon as possible.</p>
# <p>Regards,</p>
# <p>The Dify Team</p>
# """
# }
# response = mailchimp.messages.send({
# 'message': message,
# # required for transactional email
# ' settings': {
# 'sandbox_mode': dify_config.MAILCHIMP_SANDBOX_MODE,
# },
# })
class EmailCodeLoginSendEmailApi(Resource):
@setup_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
parser.add_argument("language", type=str, required=False, location="json")
args = parser.parse_args()
# Check if MSG was sent
# if response.status_code != 200:
# # handle error
# pass
ip_address = extract_remote_ip(request)
if AccountService.is_email_send_ip_limit(ip_address):
raise EmailSendIpLimitError()
return {"result": "success"}
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
language = "en-US"
account = AccountService.get_user_through_email(args["email"])
if account is None:
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_email_code_login_email(email=args["email"], language=language)
else:
raise NotAllowedRegister()
else:
token = AccountService.send_email_code_login_email(account=account, language=language)
return {"result": "success", "data": token}
class EmailCodeLoginApi(Resource):
@setup_required
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=str, required=True, location="json")
parser.add_argument("code", type=str, required=True, location="json")
parser.add_argument("token", type=str, required=True, location="json")
args = parser.parse_args()
user_email = args["email"]
token_data = AccountService.get_email_code_login_data(args["token"])
if token_data is None:
raise InvalidTokenError()
if token_data["email"] != args["email"]:
raise InvalidEmailError()
if token_data["code"] != args["code"]:
raise EmailCodeError()
AccountService.revoke_email_code_login_token(args["token"])
account = AccountService.get_user_through_email(user_email)
if account:
tenant = TenantService.get_join_tenants(account)
if not tenant:
if not FeatureService.get_system_features().is_allow_create_workspace:
raise NotAllowedCreateWorkspace()
else:
tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(tenant, account, role="owner")
account.current_tenant = tenant
tenant_was_created.send(tenant)
if account is None:
try:
account = AccountService.create_account_and_tenant(
email=user_email, name=user_email, interface_language=languages[0]
)
except WorkSpaceNotAllowedCreateError:
return redirect(
f"{dify_config.CONSOLE_WEB_URL}/signin"
"?message=Workspace not found, please contact system admin to invite you to join in a workspace."
)
token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
AccountService.reset_login_error_rate_limit(args["email"])
return {"result": "success", "data": token_pair.model_dump()}
class RefreshTokenApi(Resource):
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("refresh_token", type=str, required=True, location="json")
args = parser.parse_args()
try:
new_token_pair = AccountService.refresh_token(args["refresh_token"])
return {"result": "success", "data": new_token_pair.model_dump()}
except Exception as e:
return {"result": "fail", "data": str(e)}, 401
api.add_resource(LoginApi, "/login")
api.add_resource(LogoutApi, "/logout")
api.add_resource(EmailCodeLoginSendEmailApi, "/email-code-login")
api.add_resource(EmailCodeLoginApi, "/email-code-login/validity")
api.add_resource(ResetPasswordSendEmailApi, "/reset-password")
api.add_resource(RefreshTokenApi, "/refresh-token")
+63 -7
View File
@@ -5,15 +5,20 @@ from typing import Optional
import requests
from flask import current_app, redirect, request
from flask_restful import Resource
from werkzeug.exceptions import Unauthorized
from configs import dify_config
from constants.languages import languages
from events.tenant_event import tenant_was_created
from extensions.ext_database import db
from libs.helper import get_remote_ip
from libs.helper import extract_remote_ip
from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
from models import Account
from models.account import AccountStatus
from services.account_service import AccountService, RegisterService, TenantService
from services.errors.account import AccountNotFoundError
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
from services.feature_service import FeatureService
from .. import api
@@ -43,6 +48,7 @@ def get_oauth_providers():
class OAuthLogin(Resource):
def get(self, provider: str):
invite_token = request.args.get("invite_token") or None
OAUTH_PROVIDERS = get_oauth_providers()
with current_app.app_context():
oauth_provider = OAUTH_PROVIDERS.get(provider)
@@ -50,7 +56,7 @@ class OAuthLogin(Resource):
if not oauth_provider:
return {"error": "Invalid provider"}, 400
auth_url = oauth_provider.get_authorization_url()
auth_url = oauth_provider.get_authorization_url(invite_token=invite_token)
return redirect(auth_url)
@@ -63,6 +69,11 @@ class OAuthCallback(Resource):
return {"error": "Invalid provider"}, 400
code = request.args.get("code")
state = request.args.get("state")
invite_token = None
if state:
invite_token = state
try:
token = oauth_provider.get_access_token(code)
user_info = oauth_provider.get_user_info(token)
@@ -70,7 +81,27 @@ class OAuthCallback(Resource):
logging.exception(f"An error occurred during the OAuth process with {provider}: {e.response.text}")
return {"error": "OAuth process failed"}, 400
account = _generate_account(provider, user_info)
if invite_token and RegisterService.is_valid_invite_token(invite_token):
invitation = RegisterService._get_invitation_by_token(token=invite_token)
if invitation:
invitation_email = invitation.get("email", None)
if invitation_email != user_info.email:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Invalid invitation token.")
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin/invite-settings?invite_token={invite_token}")
try:
account = _generate_account(provider, user_info)
except AccountNotFoundError:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Account not found.")
except WorkSpaceNotFoundError:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
except WorkSpaceNotAllowedCreateError:
return redirect(
f"{dify_config.CONSOLE_WEB_URL}/signin"
"?message=Workspace not found, please contact system admin to invite you to join in a workspace."
)
# Check account status
if account.status in {AccountStatus.BANNED.value, AccountStatus.CLOSED.value}:
return {"error": "Account is banned or closed."}, 403
@@ -80,11 +111,24 @@ class OAuthCallback(Resource):
account.initialized_at = datetime.now(timezone.utc).replace(tzinfo=None)
db.session.commit()
TenantService.create_owner_tenant_if_not_exist(account)
try:
TenantService.create_owner_tenant_if_not_exist(account)
except Unauthorized:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message=Workspace not found.")
except WorkSpaceNotAllowedCreateError:
return redirect(
f"{dify_config.CONSOLE_WEB_URL}/signin"
"?message=Workspace not found, please contact system admin to invite you to join in a workspace."
)
token = AccountService.login(account, ip_address=get_remote_ip(request))
token_pair = AccountService.login(
account=account,
ip_address=extract_remote_ip(request),
)
return redirect(f"{dify_config.CONSOLE_WEB_URL}?console_token={token}")
return redirect(
f"{dify_config.CONSOLE_WEB_URL}?access_token={token_pair.access_token}&refresh_token={token_pair.refresh_token}"
)
def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
@@ -100,8 +144,20 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
# Get account by openid or email.
account = _get_account_by_openid_or_email(provider, user_info)
if account:
tenant = TenantService.get_join_tenants(account)
if not tenant:
if not FeatureService.get_system_features().is_allow_create_workspace:
raise WorkSpaceNotAllowedCreateError()
else:
tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(tenant, account, role="owner")
account.current_tenant = tenant
tenant_was_created.send(tenant)
if not account:
# Create account
if not FeatureService.get_system_features().is_allow_register:
raise AccountNotFoundError()
account_name = user_info.name or "Dify"
account = RegisterService.register(
email=user_info.email, name=account_name, password=None, open_id=user_info.id, provider=provider
@@ -617,6 +617,8 @@ class DatasetRetrievalSettingApi(Resource):
| VectorType.CHROMA
| VectorType.TENCENT
| VectorType.PGVECTO_RS
| VectorType.BAIDU
| VectorType.VIKINGDB
):
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
case (
@@ -653,6 +655,8 @@ class DatasetRetrievalSettingMockApi(Resource):
| VectorType.CHROMA
| VectorType.TENCENT
| VectorType.PGVECTO_RS
| VectorType.BAIDU
| VectorType.VIKINGDB
):
return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
case (
@@ -13,6 +13,7 @@ from libs.login import login_required
from services.dataset_service import DatasetService
from services.external_knowledge_service import ExternalDatasetService
from services.hit_testing_service import HitTestingService
from services.knowledge_service import ExternalDatasetTestService
def _validate_name(name):
@@ -232,8 +233,31 @@ class ExternalKnowledgeHitTestingApi(Resource):
raise InternalServerError(str(e))
class BedrockRetrievalApi(Resource):
# this api is only for internal testing
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
parser.add_argument(
"query",
nullable=False,
required=True,
type=str,
)
parser.add_argument("knowledge_id", nullable=False, required=True, type=str)
args = parser.parse_args()
# Call the knowledge retrieval service
result = ExternalDatasetTestService.knowledge_retrieval(
args["retrieval_setting"], args["query"], args["knowledge_id"]
)
return result, 200
api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")
# this api is only for internal test
api.add_resource(BedrockRetrievalApi, "/test/retrieval")
+6 -2
View File
@@ -2,7 +2,7 @@ import urllib.parse
from flask import request
from flask_login import current_user
from flask_restful import Resource, marshal_with
from flask_restful import Resource, marshal_with, reqparse
import services
from configs import dify_config
@@ -48,6 +48,10 @@ class FileApi(Resource):
# get file from request
file = request.files["file"]
parser = reqparse.RequestParser()
parser.add_argument("source", type=str, required=False, location="args")
source = parser.parse_args().get("source")
# check file
if "file" not in request.files:
raise NoFileUploadedError()
@@ -55,7 +59,7 @@ class FileApi(Resource):
if len(request.files) > 1:
raise TooManyFilesError()
try:
upload_file = FileService.upload_file(file=file, user=current_user)
upload_file = FileService.upload_file(file=file, user=current_user, source=source)
except services.errors.file.FileTooLargeError as file_too_large_error:
raise FileTooLargeError(file_too_large_error.description)
except services.errors.file.UnsupportedFileTypeError:
@@ -1,88 +1,24 @@
import logging
from flask_restful import Resource
from flask_login import current_user
from flask_restful import Resource, marshal, reqparse
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
import services
from controllers.console import api
from controllers.console.app.error import (
CompletionRequestError,
ProviderModelCurrentlyNotSupportError,
ProviderNotInitializeError,
ProviderQuotaExceededError,
)
from controllers.console.datasets.error import DatasetNotInitializedError
from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
from controllers.console.setup import setup_required
from controllers.console.wraps import account_initialization_required
from core.errors.error import (
LLMBadRequestError,
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from fields.hit_testing_fields import hit_testing_record_fields
from libs.login import login_required
from services.dataset_service import DatasetService
from services.hit_testing_service import HitTestingService
class HitTestingApi(Resource):
class HitTestingApi(Resource, DatasetsHitTestingBase):
@setup_required
@login_required
@account_initialization_required
def post(self, dataset_id):
dataset_id_str = str(dataset_id)
dataset = DatasetService.get_dataset(dataset_id_str)
if dataset is None:
raise NotFound("Dataset not found.")
dataset = self.get_and_validate_dataset(dataset_id_str)
args = self.parse_args()
self.hit_testing_args_check(args)
try:
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
parser = reqparse.RequestParser()
parser.add_argument("query", type=str, location="json")
parser.add_argument("retrieval_model", type=dict, required=False, location="json")
parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
args = parser.parse_args()
HitTestingService.hit_testing_args_check(args)
try:
response = HitTestingService.retrieve(
dataset=dataset,
query=args["query"],
account=current_user,
retrieval_model=args["retrieval_model"],
external_retrieval_model=args["external_retrieval_model"],
limit=10,
)
return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
except services.errors.index.IndexNotInitializedError:
raise DatasetNotInitializedError()
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
except QuotaExceededError:
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model or Reranking Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
)
except InvokeError as e:
raise CompletionRequestError(e.description)
except ValueError as e:
raise ValueError(str(e))
except Exception as e:
logging.exception("Hit testing failed.")
raise InternalServerError(str(e))
return self.perform_hit_testing(dataset, args)
api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
@@ -0,0 +1,85 @@
import logging
from flask_login import current_user
from flask_restful import marshal, reqparse
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
import services.dataset_service
from controllers.console.app.error import (
CompletionRequestError,
ProviderModelCurrentlyNotSupportError,
ProviderNotInitializeError,
ProviderQuotaExceededError,
)
from controllers.console.datasets.error import DatasetNotInitializedError
from core.errors.error import (
LLMBadRequestError,
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from fields.hit_testing_fields import hit_testing_record_fields
from services.dataset_service import DatasetService
from services.hit_testing_service import HitTestingService
class DatasetsHitTestingBase:
@staticmethod
def get_and_validate_dataset(dataset_id: str):
dataset = DatasetService.get_dataset(dataset_id)
if dataset is None:
raise NotFound("Dataset not found.")
try:
DatasetService.check_dataset_permission(dataset, current_user)
except services.errors.account.NoPermissionError as e:
raise Forbidden(str(e))
return dataset
@staticmethod
def hit_testing_args_check(args):
HitTestingService.hit_testing_args_check(args)
@staticmethod
def parse_args():
parser = reqparse.RequestParser()
parser.add_argument("query", type=str, location="json")
parser.add_argument("retrieval_model", type=dict, required=False, location="json")
parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
return parser.parse_args()
@staticmethod
def perform_hit_testing(dataset, args):
try:
response = HitTestingService.retrieve(
dataset=dataset,
query=args["query"],
account=current_user,
retrieval_model=args["retrieval_model"],
external_retrieval_model=args["external_retrieval_model"],
limit=10,
)
return {"query": response["query"], "records": marshal(response["records"], hit_testing_record_fields)}
except services.errors.index.IndexNotInitializedError:
raise DatasetNotInitializedError()
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
except QuotaExceededError:
raise ProviderQuotaExceededError()
except ModelCurrentlyNotSupportError:
raise ProviderModelCurrentlyNotSupportError()
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model or Reranking Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
)
except InvokeError as e:
raise CompletionRequestError(e.description)
except ValueError as e:
raise ValueError(str(e))
except Exception as e:
logging.exception("Hit testing failed.")
raise InternalServerError(str(e))
+24
View File
@@ -38,3 +38,27 @@ class AlreadyActivateError(BaseHTTPException):
error_code = "already_activate"
description = "Auth Token is invalid or account already activated, please check again."
code = 403
class NotAllowedCreateWorkspace(BaseHTTPException):
error_code = "unauthorized"
description = "Workspace not found, please contact system admin to invite you to join in a workspace."
code = 400
class AccountBannedError(BaseHTTPException):
error_code = "account_banned"
description = "Account is banned."
code = 400
class NotAllowedRegister(BaseHTTPException):
error_code = "unauthorized"
description = "Account not found."
code = 400
class EmailSendIpLimitError(BaseHTTPException):
error_code = "email_send_ip_limit"
description = "Too many emails have been sent from this IP address recently. Please try again later."
code = 429
@@ -18,7 +18,7 @@ message_fields = {
"inputs": fields.Raw,
"query": fields.String,
"answer": fields.String,
"message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
"message_files": fields.List(fields.Nested(message_file_fields)),
"feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
"created_at": TimestampField,
}
+2 -2
View File
@@ -4,7 +4,7 @@ from flask import request
from flask_restful import Resource, reqparse
from configs import dify_config
from libs.helper import StrLen, email, get_remote_ip
from libs.helper import StrLen, email, extract_remote_ip
from libs.password import valid_password
from models.model import DifySetup
from services.account_service import RegisterService, TenantService
@@ -46,7 +46,7 @@ class SetupApi(Resource):
# setup
RegisterService.setup(
email=args["email"], name=args["name"], password=args["password"], ip_address=get_remote_ip(request)
email=args["email"], name=args["name"], password=args["password"], ip_address=extract_remote_ip(request)
)
return {"result": "success"}, 201
@@ -126,13 +126,12 @@ class ModelProviderIconApi(Resource):
Get model provider icon
"""
@setup_required
@login_required
@account_initialization_required
def get(self, provider: str, icon_type: str, lang: str):
model_provider_service = ModelProviderService()
icon, mimetype = model_provider_service.get_model_provider_icon(
provider=provider, icon_type=icon_type, lang=lang
provider=provider,
icon_type=icon_type,
lang=lang,
)
return send_file(io.BytesIO(icon), mimetype=mimetype)
+7
View File
@@ -0,0 +1,7 @@
from libs.exception import BaseHTTPException
class UnsupportedFileTypeError(BaseHTTPException):
error_code = "unsupported_file_type"
description = "File type not allowed."
code = 415
+5 -7
View File
@@ -4,12 +4,16 @@ from werkzeug.exceptions import NotFound
import services
from controllers.files import api
from libs.exception import BaseHTTPException
from controllers.files.error import UnsupportedFileTypeError
from services.account_service import TenantService
from services.file_service import FileService
class ImagePreviewApi(Resource):
"""
Deprecated
"""
def get(self, file_id):
file_id = str(file_id)
@@ -80,9 +84,3 @@ class WorkspaceWebappLogoApi(Resource):
api.add_resource(ImagePreviewApi, "/files/<uuid:file_id>/image-preview")
api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/file-preview")
api.add_resource(WorkspaceWebappLogoApi, "/files/workspaces/<uuid:workspace_id>/webapp-logo")
class UnsupportedFileTypeError(BaseHTTPException):
error_code = "unsupported_file_type"
description = "File type not allowed."
code = 415
+16 -12
View File
@@ -3,8 +3,8 @@ from flask_restful import Resource, reqparse
from werkzeug.exceptions import Forbidden, NotFound
from controllers.files import api
from controllers.files.error import UnsupportedFileTypeError
from core.tools.tool_file_manager import ToolFileManager
from libs.exception import BaseHTTPException
class ToolFilePreviewApi(Resource):
@@ -16,6 +16,7 @@ class ToolFilePreviewApi(Resource):
parser.add_argument("timestamp", type=str, required=True, location="args")
parser.add_argument("nonce", type=str, required=True, location="args")
parser.add_argument("sign", type=str, required=True, location="args")
parser.add_argument("as_attachment", type=bool, required=False, default=False, location="args")
args = parser.parse_args()
@@ -28,24 +29,27 @@ class ToolFilePreviewApi(Resource):
raise Forbidden("Invalid request.")
try:
result = ToolFileManager.get_file_generator_by_tool_file_id(
stream, tool_file = ToolFileManager.get_file_generator_by_tool_file_id(
file_id,
)
if not result:
if not stream or not tool_file:
raise NotFound("file is not found")
generator, mimetype = result
except Exception:
raise UnsupportedFileTypeError()
return Response(generator, mimetype=mimetype)
response = Response(
stream,
mimetype=tool_file.mimetype,
direct_passthrough=True,
headers={
"Content-Length": str(tool_file.size),
},
)
if args["as_attachment"]:
response.headers["Content-Disposition"] = f"attachment; filename={tool_file.name}"
return response
api.add_resource(ToolFilePreviewApi, "/files/tools/<uuid:file_id>.<string:extension>")
class UnsupportedFileTypeError(BaseHTTPException):
error_code = "unsupported_file_type"
description = "File type not allowed."
code = 415
+1 -2
View File
@@ -5,7 +5,6 @@ from libs.external_api import ExternalApi
bp = Blueprint("service_api", __name__, url_prefix="/v1")
api = ExternalApi(bp)
from . import index
from .app import app, audio, completion, conversation, file, message, workflow
from .dataset import dataset, document, segment
from .dataset import dataset, document, hit_testing, segment
+2 -2
View File
@@ -48,7 +48,7 @@ class MessageListApi(Resource):
"tool_input": fields.String,
"created_at": TimestampField,
"observation": fields.String,
"message_files": fields.List(fields.String, attribute="files"),
"message_files": fields.List(fields.String),
}
message_fields = {
@@ -58,7 +58,7 @@ class MessageListApi(Resource):
"inputs": fields.Raw,
"query": fields.String,
"answer": fields.String(attribute="re_sign_file_url_answer"),
"message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
"message_files": fields.List(fields.Nested(message_file_fields)),
"feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
"retriever_resources": fields.List(fields.Nested(retriever_resource_fields)),
"created_at": TimestampField,
@@ -0,0 +1,17 @@
from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
from controllers.service_api import api
from controllers.service_api.wraps import DatasetApiResource
class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
def post(self, tenant_id, dataset_id):
dataset_id_str = str(dataset_id)
dataset = self.get_and_validate_dataset(dataset_id_str)
args = self.parse_args()
self.hit_testing_args_check(args)
return self.perform_hit_testing(dataset, args)
api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
+6 -2
View File
@@ -1,7 +1,7 @@
import urllib.parse
from flask import request
from flask_restful import marshal_with
from flask_restful import marshal_with, reqparse
import services
from controllers.web import api
@@ -18,6 +18,10 @@ class FileApi(WebApiResource):
# get file from request
file = request.files["file"]
parser = reqparse.RequestParser()
parser.add_argument("source", type=str, required=False, location="args")
source = parser.parse_args().get("source")
# check file
if "file" not in request.files:
raise NoFileUploadedError()
@@ -25,7 +29,7 @@ class FileApi(WebApiResource):
if len(request.files) > 1:
raise TooManyFilesError()
try:
upload_file = FileService.upload_file(file, end_user)
upload_file = FileService.upload_file(file=file, user=end_user, source=source)
except services.errors.file.FileTooLargeError as file_too_large_error:
raise FileTooLargeError(file_too_large_error.description)
except services.errors.file.UnsupportedFileTypeError:
+1 -1
View File
@@ -62,7 +62,7 @@ class MessageListApi(WebApiResource):
"inputs": FilesContainedField,
"query": fields.String,
"answer": fields.String(attribute="re_sign_file_url_answer"),
"message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
"message_files": fields.List(fields.Nested(message_file_fields)),
"feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
"retriever_resources": fields.List(fields.Nested(retriever_resource_fields)),
"created_at": TimestampField,
+1 -1
View File
@@ -17,7 +17,7 @@ message_fields = {
"inputs": fields.Raw,
"query": fields.String,
"answer": fields.String,
"message_files": fields.List(fields.Nested(message_file_fields), attribute="files"),
"message_files": fields.List(fields.Nested(message_file_fields)),
"feedback": fields.Nested(feedback_fields, attribute="user_feedback", allow_null=True),
"created_at": TimestampField,
}
+2 -2
View File
@@ -43,7 +43,7 @@ from core.tools.tool.tool import Tool
from core.tools.tool_manager import ToolManager
from extensions.ext_database import db
from factories import file_factory
from models.model import Conversation, Message, MessageAgentThought
from models.model import Conversation, Message, MessageAgentThought, MessageFile
from models.tools import ToolConversationVariables
logger = logging.getLogger(__name__)
@@ -495,7 +495,7 @@ class BaseAgentRunner(AppRunner):
return result
def organize_agent_user_prompt(self, message: Message) -> UserPromptMessage:
files = message.message_files
files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
if files:
file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())
+1 -1
View File
@@ -369,7 +369,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
return message
def _organize_historic_prompt_messages(
self, current_session_messages: list[PromptMessage] = None
self, current_session_messages: Optional[list[PromptMessage]] = None
) -> list[PromptMessage]:
"""
organize historic prompt messages
+1 -1
View File
@@ -29,7 +29,7 @@ class CotChatAgentRunner(CotAgentRunner):
return SystemPromptMessage(content=system_prompt)
def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
"""
Organize user query
"""
@@ -1,4 +1,5 @@
import json
from typing import Optional
from core.agent.cot_agent_runner import CotAgentRunner
from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage, UserPromptMessage
@@ -21,7 +22,7 @@ class CotCompletionAgentRunner(CotAgentRunner):
return system_prompt
def _organize_historic_prompt(self, current_session_messages: list[PromptMessage] = None) -> str:
def _organize_historic_prompt(self, current_session_messages: Optional[list[PromptMessage]] = None) -> str:
"""
Organize historic prompt
"""
+3 -3
View File
@@ -2,7 +2,7 @@ import json
import logging
from collections.abc import Generator
from copy import deepcopy
from typing import Any, Union
from typing import Any, Optional, Union
from core.agent.base_agent_runner import BaseAgentRunner
from core.app.apps.base_app_queue_manager import PublishFrom
@@ -375,7 +375,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
return tool_calls
def _init_system_message(
self, prompt_template: str, prompt_messages: list[PromptMessage] = None
self, prompt_template: str, prompt_messages: Optional[list[PromptMessage]] = None
) -> list[PromptMessage]:
"""
Initialize system message
@@ -390,7 +390,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
return prompt_messages
def _organize_user_query(self, query, prompt_messages: list[PromptMessage] = None) -> list[PromptMessage]:
def _organize_user_query(self, query, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
"""
Organize user query
"""
@@ -14,7 +14,7 @@ class CotAgentOutputParser:
) -> Generator[Union[str, AgentScratchpadUnit.Action], None, None]:
def parse_action(json_str):
try:
action = json.loads(json_str)
action = json.loads(json_str, strict=False)
action_name = None
action_input = None
@@ -62,6 +62,8 @@ class CotAgentOutputParser:
thought_str = "thought:"
thought_idx = 0
last_character = ""
for response in llm_response:
if response.delta.usage:
usage_dict["usage"] = response.delta.usage
@@ -74,35 +76,38 @@ class CotAgentOutputParser:
while index < len(response):
steps = 1
delta = response[index : index + steps]
last_character = response[index - 1] if index > 0 else ""
yield_delta = False
if delta == "`":
last_character = delta
code_block_cache += delta
code_block_delimiter_count += 1
else:
if not in_code_block:
if code_block_delimiter_count > 0:
last_character = delta
yield code_block_cache
code_block_cache = ""
else:
last_character = delta
code_block_cache += delta
code_block_delimiter_count = 0
if not in_code_block and not in_json:
if delta.lower() == action_str[action_idx] and action_idx == 0:
if last_character not in {"\n", " ", ""}:
yield_delta = True
else:
last_character = delta
action_cache += delta
action_idx += 1
if action_idx == len(action_str):
action_cache = ""
action_idx = 0
index += steps
yield delta
continue
action_cache += delta
action_idx += 1
if action_idx == len(action_str):
action_cache = ""
action_idx = 0
index += steps
continue
elif delta.lower() == action_str[action_idx] and action_idx > 0:
last_character = delta
action_cache += delta
action_idx += 1
if action_idx == len(action_str):
@@ -112,24 +117,25 @@ class CotAgentOutputParser:
continue
else:
if action_cache:
last_character = delta
yield action_cache
action_cache = ""
action_idx = 0
if delta.lower() == thought_str[thought_idx] and thought_idx == 0:
if last_character not in {"\n", " ", ""}:
yield_delta = True
else:
last_character = delta
thought_cache += delta
thought_idx += 1
if thought_idx == len(thought_str):
thought_cache = ""
thought_idx = 0
index += steps
yield delta
continue
thought_cache += delta
thought_idx += 1
if thought_idx == len(thought_str):
thought_cache = ""
thought_idx = 0
index += steps
continue
elif delta.lower() == thought_str[thought_idx] and thought_idx > 0:
last_character = delta
thought_cache += delta
thought_idx += 1
if thought_idx == len(thought_str):
@@ -139,12 +145,20 @@ class CotAgentOutputParser:
continue
else:
if thought_cache:
last_character = delta
yield thought_cache
thought_cache = ""
thought_idx = 0
if yield_delta:
index += steps
last_character = delta
yield delta
continue
if code_block_delimiter_count == 3:
if in_code_block:
last_character = delta
yield from extra_json_from_code_block(code_block_cache)
code_block_cache = ""
@@ -156,8 +170,10 @@ class CotAgentOutputParser:
if delta == "{":
json_quote_count += 1
in_json = True
last_character = delta
json_cache += delta
elif delta == "}":
last_character = delta
json_cache += delta
if json_quote_count > 0:
json_quote_count -= 1
@@ -168,16 +184,19 @@ class CotAgentOutputParser:
continue
else:
if in_json:
last_character = delta
json_cache += delta
if got_json:
got_json = False
last_character = delta
yield parse_action(json_cache)
json_cache = ""
json_quote_count = 0
in_json = False
if not in_code_block and not in_json:
last_character = delta
yield delta.replace("`", "")
index += steps
@@ -10,6 +10,7 @@ from flask import Flask, current_app
from pydantic import ValidationError
import contexts
from constants import UUID_NIL
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
from core.app.apps.advanced_chat.app_runner import AdvancedChatAppRunner
@@ -22,10 +23,10 @@ from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity,
from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.ops.ops_trace_manager import TraceQueueManager
from enums import CreatedByRole
from extensions.ext_database import db
from factories import file_factory
from models.account import Account
from models.enums import CreatedByRole
from models.model import App, Conversation, EndUser, Message
from models.workflow import Workflow
@@ -121,6 +122,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
# always enable retriever resource in debugger mode
app_config.additional_features.show_retrieve_source = True
workflow_run_id = str(uuid.uuid4())
# init application generate entity
application_generate_entity = AdvancedChatAppGenerateEntity(
task_id=str(uuid.uuid4()),
@@ -131,12 +133,13 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
query=query,
files=file_objs,
parent_message_id=args.get("parent_message_id"),
parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
user_id=user.id,
stream=stream,
invoke_from=invoke_from,
extras=extras,
trace_manager=trace_manager,
workflow_run_id=workflow_run_id,
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
@@ -20,8 +20,8 @@ from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.enums import SystemVariableKey
from core.workflow.workflow_entry import WorkflowEntry
from enums import UserFrom
from extensions.ext_database import db
from models.enums import UserFrom
from models.model import App, Conversation, EndUser, Message
from models.workflow import ConversationVariable, WorkflowType
@@ -135,6 +135,9 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
SystemVariableKey.CONVERSATION_ID: self.conversation.id,
SystemVariableKey.USER_ID: user_id,
SystemVariableKey.DIALOGUE_COUNT: conversation_dialogue_count,
SystemVariableKey.APP_ID: app_config.app_id,
SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
}
# init variable pool
@@ -9,6 +9,7 @@ from core.app.apps.advanced_chat.app_generator_tts_publisher import AppGenerator
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.entities.app_invoke_entities import (
AdvancedChatAppGenerateEntity,
InvokeFrom,
)
from core.app.entities.queue_entities import (
QueueAdvancedChatMessageEndEvent,
@@ -45,17 +46,20 @@ from core.app.entities.task_entities import (
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
from core.model_runtime.entities.llm_entities import LLMUsage
from core.model_runtime.utils.encoders import jsonable_encoder
from core.ops.ops_trace_manager import TraceQueueManager
from core.workflow.enums import SystemVariableKey
from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
from enums.workflow_nodes import NodeType
from core.workflow.nodes import NodeType
from events.message_event import message_was_created
from extensions.ext_database import db
from models import Conversation, EndUser, Message, MessageFile
from models.account import Account
from models.model import Conversation, EndUser, Message
from models.enums import CreatedByRole
from models.workflow import (
Workflow,
WorkflowNodeExecution,
WorkflowRunStatus,
)
@@ -72,6 +76,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
_workflow: Workflow
_user: Union[Account, EndUser]
_workflow_system_variables: dict[SystemVariableKey, Any]
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
def __init__(
self,
@@ -108,9 +113,14 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.CONVERSATION_ID: conversation.id,
SystemVariableKey.USER_ID: user_id,
SystemVariableKey.DIALOGUE_COUNT: conversation.dialogue_count,
SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
SystemVariableKey.WORKFLOW_ID: workflow.id,
SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
}
self._task_state = WorkflowTaskState()
self._wip_workflow_node_executions = {}
self._conversation_name_generate_thread = None
self._recorded_files: list[Mapping[str, Any]] = []
@@ -488,10 +498,6 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
self._conversation_name_generate_thread.join()
def _save_message(self, graph_runtime_state: Optional[GraphRuntimeState] = None) -> None:
"""
Save message.
:return:
"""
self._refetch_message()
self._message.answer = self._task_state.answer
@@ -499,6 +505,22 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
self._message.message_metadata = (
json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
)
message_files = [
MessageFile(
message_id=self._message.id,
type=file["type"],
transfer_method=file["transfer_method"],
url=file["remote_url"],
belongs_to="assistant",
upload_file_id=file["related_id"],
created_by_role=CreatedByRole.ACCOUNT
if self._message.invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER}
else CreatedByRole.END_USER,
created_by=self._message.from_account_id or self._message.from_end_user_id or "",
)
for file in self._recorded_files
]
db.session.add_all(message_files)
if graph_runtime_state and graph_runtime_state.llm_usage:
usage = graph_runtime_state.llm_usage
@@ -511,6 +533,10 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
self._message.total_price = usage.total_price
self._message.currency = usage.currency
self._task_state.metadata["usage"] = jsonable_encoder(usage)
else:
self._task_state.metadata["usage"] = jsonable_encoder(LLMUsage.empty_usage())
db.session.commit()
message_was_created.send(
@@ -8,6 +8,7 @@ from typing import Any, Literal, Union, overload
from flask import Flask, current_app
from pydantic import ValidationError
from constants import UUID_NIL
from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfigManager
@@ -19,10 +20,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.ops.ops_trace_manager import TraceQueueManager
from enums import CreatedByRole
from extensions.ext_database import db
from factories import file_factory
from models import Account, App, EndUser
from models.enums import CreatedByRole
logger = logging.getLogger(__name__)
@@ -140,7 +141,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
query=query,
files=file_objs,
parent_message_id=args.get("parent_message_id"),
parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
user_id=user.id,
stream=stream,
invoke_from=invoke_from,
+1 -1
View File
@@ -7,7 +7,7 @@ from factories import file_factory
if TYPE_CHECKING:
from core.app.app_config.entities import AppConfig, VariableEntity
from enums import CreatedByRole
from models.enums import CreatedByRole
class BaseAppGenerator:
+3 -2
View File
@@ -8,6 +8,7 @@ from typing import Any, Literal, Union, overload
from flask import Flask, current_app
from pydantic import ValidationError
from constants import UUID_NIL
from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError, PublishFrom
@@ -19,10 +20,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
from core.app.entities.app_invoke_entities import ChatAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.ops.ops_trace_manager import TraceQueueManager
from enums import CreatedByRole
from extensions.ext_database import db
from factories import file_factory
from models.account import Account
from models.enums import CreatedByRole
from models.model import App, EndUser
logger = logging.getLogger(__name__)
@@ -138,7 +139,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
query=query,
files=file_objs,
parent_message_id=args.get("parent_message_id"),
parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
user_id=user.id,
invoke_from=invoke_from,
extras=extras,
@@ -19,10 +19,10 @@ from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueMa
from core.app.entities.app_invoke_entities import CompletionAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.ops.ops_trace_manager import TraceQueueManager
from enums import CreatedByRole
from extensions.ext_database import db
from factories import file_factory
from models import Account, App, EndUser, Message
from models.enums import CreatedByRole
from services.errors.app import MoreLikeThisDisabledError
from services.errors.message import MessageNotExistsError
@@ -263,7 +263,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
file_extra_config = FileUploadConfigManager.convert(override_model_config_dict)
if file_extra_config:
file_objs = file_factory.build_from_mappings(
mappings=message.files,
mappings=message.message_files,
tenant_id=app_model.tenant_id,
user_id=user.id,
role=role,
@@ -235,13 +235,13 @@ class MessageBasedAppGenerator(BaseAppGenerator):
for file in application_generate_entity.files:
message_file = MessageFile(
message_id=message.id,
type=file.type.value,
transfer_method=file.transfer_method.value,
type=file.type,
transfer_method=file.transfer_method,
belongs_to="user",
url=file.remote_url,
upload_file_id=file.related_id,
created_by_role=("account" if account_id else "end_user"),
created_by=account_id or end_user_id,
created_by=account_id or end_user_id or "",
)
db.session.add(message_file)
db.session.commit()
+3 -1
View File
@@ -22,10 +22,10 @@ from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerat
from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.ops.ops_trace_manager import TraceQueueManager
from enums import CreatedByRole
from extensions.ext_database import db
from factories import file_factory
from models import Account, App, EndUser, Workflow
from models.enums import CreatedByRole
logger = logging.getLogger(__name__)
@@ -95,6 +95,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
)
inputs: Mapping[str, Any] = args["inputs"]
workflow_run_id = str(uuid.uuid4())
# init application generate entity
application_generate_entity = WorkflowAppGenerateEntity(
task_id=str(uuid.uuid4()),
@@ -106,6 +107,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
invoke_from=invoke_from,
call_depth=call_depth,
trace_manager=trace_manager,
workflow_run_id=workflow_run_id,
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
+4 -1
View File
@@ -13,8 +13,8 @@ from core.workflow.callbacks import WorkflowCallback, WorkflowLoggingCallback
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.enums import SystemVariableKey
from core.workflow.workflow_entry import WorkflowEntry
from enums import UserFrom
from extensions.ext_database import db
from models.enums import UserFrom
from models.model import App, EndUser
from models.workflow import WorkflowType
@@ -89,6 +89,9 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
system_inputs = {
SystemVariableKey.FILES: files,
SystemVariableKey.USER_ID: user_id,
SystemVariableKey.APP_ID: app_config.app_id,
SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
}
variable_pool = VariablePool(
@@ -51,6 +51,7 @@ from models.workflow import (
Workflow,
WorkflowAppLog,
WorkflowAppLogCreatedFrom,
WorkflowNodeExecution,
WorkflowRun,
WorkflowRunStatus,
)
@@ -68,6 +69,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
_task_state: WorkflowTaskState
_application_generate_entity: WorkflowAppGenerateEntity
_workflow_system_variables: dict[SystemVariableKey, Any]
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
def __init__(
self,
@@ -96,9 +98,13 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
self._workflow_system_variables = {
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.USER_ID: user_id,
SystemVariableKey.APP_ID: application_generate_entity.app_config.app_id,
SystemVariableKey.WORKFLOW_ID: workflow.id,
SystemVariableKey.WORKFLOW_RUN_ID: application_generate_entity.workflow_run_id,
}
self._task_state = WorkflowTaskState()
self._wip_workflow_node_executions = {}
def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
"""
+5 -7
View File
@@ -40,11 +40,10 @@ from core.workflow.graph_engine.entities.event import (
ParallelBranchRunSucceededEvent,
)
from core.workflow.graph_engine.entities.graph import Graph
from core.workflow.nodes.base_node import BaseNode
from core.workflow.nodes.iteration.entities import IterationNodeData
from core.workflow.nodes.node_mapping import node_classes
from core.workflow.nodes import NodeType
from core.workflow.nodes.iteration import IterationNodeData
from core.workflow.nodes.node_mapping import node_type_classes_mapping
from core.workflow.workflow_entry import WorkflowEntry
from enums import NodeType
from extensions.ext_database import db
from models.model import App
from models.workflow import Workflow
@@ -137,9 +136,8 @@ class WorkflowBasedAppRunner(AppRunner):
raise ValueError("iteration node id not found in workflow graph")
# Get node class
node_type = NodeType.value_of(iteration_node_config.get("data", {}).get("type"))
node_cls = node_classes.get(node_type)
node_cls = cast(type[BaseNode], node_cls)
node_type = NodeType(iteration_node_config.get("data", {}).get("type"))
node_cls = node_type_classes_mapping[node_type]
# init variable pool
variable_pool = VariablePool(
+33 -10
View File
@@ -2,8 +2,9 @@ from collections.abc import Mapping, Sequence
from enum import Enum
from typing import Any, Optional
from pydantic import BaseModel, ConfigDict
from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validator
from constants import UUID_NIL
from core.app.app_config.entities import AppConfig, EasyUIBasedAppConfig, WorkflowUIBasedAppConfig
from core.entities.provider_configuration import ProviderModelBundle
from core.file.models import File
@@ -116,13 +117,36 @@ class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
model_config = ConfigDict(protected_namespaces=())
class ChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
class ConversationAppGenerateEntity(AppGenerateEntity):
"""
Base entity for conversation-based app generation.
"""
conversation_id: Optional[str] = None
parent_message_id: Optional[str] = Field(
default=None,
description=(
"Starting from v0.9.0, parent_message_id is used to support message regeneration for internal chat API."
"For service API, we need to ensure its forward compatibility, "
"so passing in the parent_message_id as request arg is not supported for now. "
"It needs to be set to UUID_NIL so that the subsequent processing will treat it as legacy messages."
),
)
@field_validator("parent_message_id")
@classmethod
def validate_parent_message_id(cls, v, info: ValidationInfo):
if info.data.get("invoke_from") == InvokeFrom.SERVICE_API and v != UUID_NIL:
raise ValueError("parent_message_id should be UUID_NIL for service API")
return v
class ChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
"""
Chat Application Generate Entity.
"""
conversation_id: Optional[str] = None
parent_message_id: Optional[str] = None
pass
class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
@@ -133,16 +157,15 @@ class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
pass
class AgentChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
class AgentChatAppGenerateEntity(ConversationAppGenerateEntity, EasyUIBasedAppGenerateEntity):
"""
Agent Chat Application Generate Entity.
"""
conversation_id: Optional[str] = None
parent_message_id: Optional[str] = None
pass
class AdvancedChatAppGenerateEntity(AppGenerateEntity):
class AdvancedChatAppGenerateEntity(ConversationAppGenerateEntity):
"""
Advanced Chat Application Generate Entity.
"""
@@ -150,8 +173,7 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
# app config
app_config: WorkflowUIBasedAppConfig
conversation_id: Optional[str] = None
parent_message_id: Optional[str] = None
workflow_run_id: Optional[str] = None
query: str
class SingleIterationRunEntity(BaseModel):
@@ -172,6 +194,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
# app config
app_config: WorkflowUIBasedAppConfig
workflow_run_id: Optional[str] = None
class SingleIterationRunEntity(BaseModel):
"""
+2 -2
View File
@@ -5,10 +5,10 @@ from typing import Any, Optional
from pydantic import BaseModel, field_validator
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
from core.workflow.entities.base_node_data_entities import BaseNodeData
from core.workflow.entities.node_entities import NodeRunMetadataKey
from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
from enums import NodeType
from core.workflow.nodes import NodeType
from core.workflow.nodes.base import BaseNodeData
class QueueEvent(str, Enum):
+4 -4
View File
@@ -1,4 +1,4 @@
from collections.abc import Mapping
from collections.abc import Mapping, Sequence
from enum import Enum
from typing import Any, Optional
@@ -120,7 +120,7 @@ class MessageEndStreamResponse(StreamResponse):
event: StreamEvent = StreamEvent.MESSAGE_END
id: str
metadata: dict = {}
files: Optional[list[Mapping[str, Any]]] = None
files: Optional[Sequence[Mapping[str, Any]]] = None
class MessageFileStreamResponse(StreamResponse):
@@ -213,7 +213,7 @@ class WorkflowFinishStreamResponse(StreamResponse):
created_by: Optional[dict] = None
created_at: int
finished_at: int
files: Optional[list[dict]] = []
files: Optional[Sequence[Mapping[str, Any]]] = []
event: StreamEvent = StreamEvent.WORKFLOW_FINISHED
workflow_run_id: str
@@ -298,7 +298,7 @@ class NodeFinishStreamResponse(StreamResponse):
execution_metadata: Optional[dict] = None
created_at: int
finished_at: int
files: Optional[list[dict]] = []
files: Optional[Sequence[Mapping[str, Any]]] = []
parallel_id: Optional[str] = None
parallel_start_node_id: Optional[str] = None
parent_parallel_id: Optional[str] = None
@@ -1,8 +1,10 @@
import logging
from threading import Thread
from typing import Optional, Union
from flask import Flask, current_app
from configs import dify_config
from core.app.entities.app_invoke_entities import (
AdvancedChatAppGenerateEntity,
AgentChatAppGenerateEntity,
@@ -82,7 +84,9 @@ class MessageCycleManage:
try:
name = LLMGenerator.generate_conversation_name(app_model.tenant_id, query)
conversation.name = name
except:
except Exception as e:
if dify_config.DEBUG:
logging.exception(f"generate conversation name failed: {e}")
pass
db.session.merge(conversation)
@@ -1,6 +1,6 @@
import json
import time
from collections.abc import Mapping
from collections.abc import Mapping, Sequence
from datetime import datetime, timezone
from typing import Any, Optional, Union, cast
@@ -34,14 +34,14 @@ from core.ops.entities.trace_entity import TraceTaskName
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
from core.tools.tool_manager import ToolManager
from core.workflow.enums import SystemVariableKey
from core.workflow.nodes import NodeType
from core.workflow.nodes.tool.entities import ToolNodeData
from core.workflow.workflow_entry import WorkflowEntry
from enums import NodeType, WorkflowRunTriggeredFrom
from extensions.ext_database import db
from models.account import Account
from models.enums import CreatedByRole, WorkflowRunTriggeredFrom
from models.model import EndUser
from models.workflow import (
CreatedByRole,
Workflow,
WorkflowNodeExecution,
WorkflowNodeExecutionStatus,
@@ -57,6 +57,7 @@ class WorkflowCycleManage:
_user: Union[Account, EndUser]
_task_state: WorkflowTaskState
_workflow_system_variables: dict[SystemVariableKey, Any]
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
def _handle_workflow_run_start(self) -> WorkflowRun:
max_sequence = (
@@ -85,6 +86,9 @@ class WorkflowCycleManage:
# init workflow run
workflow_run = WorkflowRun()
workflow_run_id = self._workflow_system_variables[SystemVariableKey.WORKFLOW_RUN_ID]
if workflow_run_id:
workflow_run.id = workflow_run_id
workflow_run.tenant_id = self._workflow.tenant_id
workflow_run.app_id = self._workflow.app_id
workflow_run.sequence_number = new_sequence_number
@@ -132,7 +136,7 @@ class WorkflowCycleManage:
outputs = WorkflowEntry.handle_special_values(outputs)
workflow_run.status = WorkflowRunStatus.SUCCEEDED.value
workflow_run.outputs = json.dumps(outputs) if outputs else None
workflow_run.outputs = json.dumps(outputs or {})
workflow_run.elapsed_time = time.perf_counter() - start_at
workflow_run.total_tokens = total_tokens
workflow_run.total_steps = total_steps
@@ -250,6 +254,8 @@ class WorkflowCycleManage:
db.session.refresh(workflow_node_execution)
db.session.close()
self._wip_workflow_node_executions[workflow_node_execution.node_execution_id] = workflow_node_execution
return workflow_node_execution
def _handle_workflow_node_execution_success(self, event: QueueNodeSucceededEvent) -> WorkflowNodeExecution:
@@ -261,22 +267,39 @@ class WorkflowCycleManage:
workflow_node_execution = self._refetch_workflow_node_execution(event.node_execution_id)
inputs = WorkflowEntry.handle_special_values(event.inputs)
process_data = WorkflowEntry.handle_special_values(event.process_data)
outputs = WorkflowEntry.handle_special_values(event.outputs)
execution_metadata = (
json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
)
finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
elapsed_time = (finished_at - event.start_at).total_seconds()
db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
{
WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.SUCCEEDED.value,
WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
WorkflowNodeExecution.process_data: json.dumps(process_data) if event.process_data else None,
WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
WorkflowNodeExecution.execution_metadata: execution_metadata,
WorkflowNodeExecution.finished_at: finished_at,
WorkflowNodeExecution.elapsed_time: elapsed_time,
}
)
db.session.commit()
db.session.close()
process_data = WorkflowEntry.handle_special_values(event.process_data)
workflow_node_execution.status = WorkflowNodeExecutionStatus.SUCCEEDED.value
workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
workflow_node_execution.process_data = json.dumps(process_data) if process_data else None
workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
workflow_node_execution.execution_metadata = (
json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
)
workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
workflow_node_execution.execution_metadata = execution_metadata
workflow_node_execution.finished_at = finished_at
workflow_node_execution.elapsed_time = elapsed_time
db.session.commit()
db.session.refresh(workflow_node_execution)
db.session.close()
self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
return workflow_node_execution
@@ -289,20 +312,36 @@ class WorkflowCycleManage:
workflow_node_execution = self._refetch_workflow_node_execution(event.node_execution_id)
inputs = WorkflowEntry.handle_special_values(event.inputs)
process_data = WorkflowEntry.handle_special_values(event.process_data)
outputs = WorkflowEntry.handle_special_values(event.outputs)
finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
elapsed_time = (finished_at - event.start_at).total_seconds()
db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
{
WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
WorkflowNodeExecution.error: event.error,
WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
WorkflowNodeExecution.process_data: json.dumps(process_data) if event.process_data else None,
WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
WorkflowNodeExecution.finished_at: finished_at,
WorkflowNodeExecution.elapsed_time: elapsed_time,
}
)
db.session.commit()
db.session.close()
process_data = WorkflowEntry.handle_special_values(event.process_data)
workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
workflow_node_execution.error = event.error
workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
workflow_node_execution.inputs = json.dumps(inputs) if inputs else None
workflow_node_execution.process_data = json.dumps(process_data) if process_data else None
workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
workflow_node_execution.elapsed_time = (workflow_node_execution.finished_at - event.start_at).total_seconds()
workflow_node_execution.finished_at = finished_at
workflow_node_execution.elapsed_time = elapsed_time
db.session.commit()
db.session.refresh(workflow_node_execution)
db.session.close()
self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
return workflow_node_execution
@@ -604,7 +643,7 @@ class WorkflowCycleManage:
),
)
def _fetch_files_from_node_outputs(self, outputs_dict: dict) -> list[dict]:
def _fetch_files_from_node_outputs(self, outputs_dict: dict) -> Sequence[Mapping[str, Any]]:
"""
Fetch files from node outputs
:param outputs_dict: node outputs dict
@@ -621,7 +660,7 @@ class WorkflowCycleManage:
return files
def _fetch_files_from_variable_value(self, value: Union[dict, list]) -> list[dict]:
def _fetch_files_from_variable_value(self, value: Union[dict, list]) -> Sequence[Mapping[str, Any]]:
"""
Fetch files from variable value
:param value: variable value
@@ -633,17 +672,17 @@ class WorkflowCycleManage:
files = []
if isinstance(value, list):
for item in value:
file_var = self._get_file_var_from_value(item)
if file_var:
files.append(file_var)
file = self._get_file_var_from_value(item)
if file:
files.append(file)
elif isinstance(value, dict):
file_var = self._get_file_var_from_value(value)
if file_var:
files.append(file_var)
file = self._get_file_var_from_value(value)
if file:
files.append(file)
return files
def _get_file_var_from_value(self, value: Union[dict, list]) -> Mapping[str, str | int | None] | None:
def _get_file_var_from_value(self, value: Union[dict, list]) -> Mapping[str, Any] | None:
"""
Get file var from value
:param value: variable value
@@ -676,17 +715,7 @@ class WorkflowCycleManage:
:param node_execution_id: workflow node execution id
:return:
"""
workflow_node_execution = (
db.session.query(WorkflowNodeExecution)
.filter(
WorkflowNodeExecution.tenant_id == self._application_generate_entity.app_config.tenant_id,
WorkflowNodeExecution.app_id == self._application_generate_entity.app_config.app_id,
WorkflowNodeExecution.workflow_id == self._workflow.id,
WorkflowNodeExecution.triggered_from == WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN.value,
WorkflowNodeExecution.node_execution_id == node_execution_id,
)
.first()
)
workflow_node_execution = self._wip_workflow_node_executions.get(node_execution_id)
if not workflow_node_execution:
raise Exception(f"Workflow node execution not found: {node_execution_id}")
@@ -1,9 +1,9 @@
import os
from collections.abc import Mapping, Sequence
from typing import Any, Optional, TextIO, Union
from pydantic import BaseModel
from configs import dify_config
from core.ops.entities.trace_entity import TraceTaskName
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
from core.tools.entities.tool_entities import ToolInvokeMessage
@@ -50,7 +50,8 @@ class DifyAgentCallbackHandler(BaseModel):
tool_inputs: Mapping[str, Any],
) -> None:
"""Do nothing."""
print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
if dify_config.DEBUG:
print_text("\n[on_tool_start] ToolCall:" + tool_name + "\n" + str(tool_inputs) + "\n", color=self.color)
def on_tool_end(
self,
@@ -62,11 +63,12 @@ class DifyAgentCallbackHandler(BaseModel):
trace_manager: Optional[TraceQueueManager] = None,
) -> None:
"""If not the final action, print out observation."""
print_text("\n[on_tool_end]\n", color=self.color)
print_text("Tool: " + tool_name + "\n", color=self.color)
print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
print_text("\n")
if dify_config.DEBUG:
print_text("\n[on_tool_end]\n", color=self.color)
print_text("Tool: " + tool_name + "\n", color=self.color)
print_text("Inputs: " + str(tool_inputs) + "\n", color=self.color)
print_text("Outputs: " + str(tool_outputs)[:1000] + "\n", color=self.color)
print_text("\n")
if trace_manager:
trace_manager.add_trace_task(
@@ -82,30 +84,33 @@ class DifyAgentCallbackHandler(BaseModel):
def on_tool_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
"""Do nothing."""
print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
if dify_config.DEBUG:
print_text("\n[on_tool_error] Error: " + str(error) + "\n", color="red")
def on_agent_start(self, thought: str) -> None:
"""Run on agent start."""
if thought:
print_text(
"\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
color=self.color,
)
else:
print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
if dify_config.DEBUG:
if thought:
print_text(
"\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\nThought: " + thought + "\n",
color=self.color,
)
else:
print_text("\n[on_agent_start] \nCurrent Loop: " + str(self.current_loop) + "\n", color=self.color)
def on_agent_finish(self, color: Optional[str] = None, **kwargs: Any) -> None:
"""Run on agent end."""
print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
if dify_config.DEBUG:
print_text("\n[on_agent_finish]\n Loop: " + str(self.current_loop) + "\n", color=self.color)
self.current_loop += 1
@property
def ignore_agent(self) -> bool:
"""Whether to ignore agent callbacks."""
return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
return not dify_config.DEBUG
@property
def ignore_chat_model(self) -> bool:
"""Whether to ignore chat model callbacks."""
return not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != "true"
return not dify_config.DEBUG
@@ -44,7 +44,6 @@ class DatasetIndexToolCallbackHandler:
DocumentSegment.index_node_id == document.metadata["doc_id"]
)
# if 'dataset_id' in document.metadata:
if "dataset_id" in document.metadata:
query = query.filter(DocumentSegment.dataset_id == document.metadata["dataset_id"])
+77 -57
View File
@@ -1,10 +1,11 @@
import base64
from configs import dify_config
from core.model_runtime.entities.message_entities import ImagePromptMessageContent
from core.file import file_repository
from core.helper import ssrf_proxy
from core.model_runtime.entities import AudioPromptMessageContent, ImagePromptMessageContent
from extensions.ext_database import db
from extensions.ext_storage import storage
from models import UploadFile
from . import helpers
from .enums import FileAttribute
@@ -12,7 +13,7 @@ from .models import File, FileTransferMethod, FileType
from .tool_file_parser import ToolFileParser
def get_attr(*, file: "File", attr: "FileAttribute"):
def get_attr(*, file: File, attr: FileAttribute):
match attr:
case FileAttribute.TYPE:
return file.type.value
@@ -32,7 +33,7 @@ def get_attr(*, file: "File", attr: "FileAttribute"):
raise ValueError(f"Invalid file attribute: {attr}")
def to_prompt_message_content(file: "File", /):
def to_prompt_message_content(f: File, /):
"""
Convert a File object to an ImagePromptMessageContent object.
@@ -52,34 +53,34 @@ def to_prompt_message_content(file: "File", /):
The detail level of the image prompt is determined by the file's extra_config.
If not specified, it defaults to ImagePromptMessageContent.DETAIL.LOW.
"""
if file.type != FileType.IMAGE:
raise ValueError("Only image file can convert to prompt message content")
match f.type:
case FileType.IMAGE:
if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == "url":
data = _to_url(f)
else:
data = _to_base64_data_string(f)
url_or_b64_data = _get_url_or_b64_data(file=file)
if url_or_b64_data is None:
raise ValueError("Missing file data")
if f._extra_config and f._extra_config.image_config and f._extra_config.image_config.detail:
detail = f._extra_config.image_config.detail
else:
detail = ImagePromptMessageContent.DETAIL.LOW
# decide the detail of image prompt message content
if file._extra_config and file._extra_config.image_config and file._extra_config.image_config.detail:
detail = file._extra_config.image_config.detail
else:
detail = ImagePromptMessageContent.DETAIL.LOW
return ImagePromptMessageContent(data=url_or_b64_data, detail=detail)
return ImagePromptMessageContent(data=data, detail=detail)
case FileType.AUDIO:
encoded_string = _file_to_encoded_string(f)
if f.extension is None:
raise ValueError("Missing file extension")
return AudioPromptMessageContent(data=encoded_string, format=f.extension.lstrip("."))
case _:
raise ValueError(f"file type {f.type} is not supported")
def download(*, upload_file_id: str, tenant_id: str):
upload_file = (
db.session.query(UploadFile).filter(UploadFile.id == upload_file_id, UploadFile.tenant_id == tenant_id).first()
)
if not upload_file:
raise ValueError("upload file not found")
return _download(upload_file.key)
def download(f: File, /):
upload_file = file_repository.get_upload_file(session=db.session(), file=f)
return _download_file_content(upload_file.key)
def _download(path: str, /):
def _download_file_content(path: str, /):
"""
Download and return the contents of a file as bytes.
@@ -100,37 +101,56 @@ def _download(path: str, /):
return data
def _get_base64(*, upload_file_id: str, tenant_id: str) -> str | None:
upload_file = (
db.session.query(UploadFile).filter(UploadFile.id == upload_file_id, UploadFile.tenant_id == tenant_id).first()
)
if not upload_file:
return None
data = _download(upload_file.key)
if data is None:
return None
encoded_string = base64.b64encode(data).decode("utf-8")
return f"data:{upload_file.mime_type};base64,{encoded_string}"
def _get_encoded_string(f: File, /):
match f.transfer_method:
case FileTransferMethod.REMOTE_URL:
response = ssrf_proxy.get(f.remote_url)
response.raise_for_status()
content = response.content
encoded_string = base64.b64encode(content).decode("utf-8")
return encoded_string
case FileTransferMethod.LOCAL_FILE:
upload_file = file_repository.get_upload_file(session=db.session(), file=f)
data = _download_file_content(upload_file.key)
encoded_string = base64.b64encode(data).decode("utf-8")
return encoded_string
case FileTransferMethod.TOOL_FILE:
tool_file = file_repository.get_tool_file(session=db.session(), file=f)
data = _download_file_content(tool_file.file_key)
encoded_string = base64.b64encode(data).decode("utf-8")
return encoded_string
case _:
raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
def _get_url_or_b64_data(file: "File"):
if file.type == FileType.IMAGE:
if file.transfer_method == FileTransferMethod.REMOTE_URL:
return file.remote_url
elif file.transfer_method == FileTransferMethod.LOCAL_FILE:
if file.related_id is None:
raise ValueError("Missing file related_id")
def _to_base64_data_string(f: File, /):
encoded_string = _get_encoded_string(f)
return f"data:{f.mime_type};base64,{encoded_string}"
if dify_config.MULTIMODAL_SEND_IMAGE_FORMAT == "url":
return helpers.get_signed_image_url(upload_file_id=file.related_id)
return _get_base64(upload_file_id=file.related_id, tenant_id=file.tenant_id)
elif file.transfer_method == FileTransferMethod.TOOL_FILE:
# add sign url
if file.related_id is None or file.extension is None:
raise ValueError("Missing file related_id or extension")
return ToolFileParser.get_tool_file_manager().sign_file(
tool_file_id=file.related_id, extension=file.extension
)
def _file_to_encoded_string(f: File, /):
match f.type:
case FileType.IMAGE:
return _to_base64_data_string(f)
case FileType.AUDIO:
return _get_encoded_string(f)
case _:
raise ValueError(f"file type {f.type} is not supported")
def _to_url(f: File, /):
if f.transfer_method == FileTransferMethod.REMOTE_URL:
if f.remote_url is None:
raise ValueError("Missing file remote_url")
return f.remote_url
elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
if f.related_id is None:
raise ValueError("Missing file related_id")
return helpers.get_signed_file_url(upload_file_id=f.related_id)
elif f.transfer_method == FileTransferMethod.TOOL_FILE:
# add sign url
if f.related_id is None or f.extension is None:
raise ValueError("Missing file related_id or extension")
return ToolFileParser.get_tool_file_manager().sign_file(tool_file_id=f.related_id, extension=f.extension)
else:
raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+32
View File
@@ -0,0 +1,32 @@
from sqlalchemy import select
from sqlalchemy.orm import Session
from models import ToolFile, UploadFile
from .models import File
def get_upload_file(*, session: Session, file: File):
if file.related_id is None:
raise ValueError("Missing file related_id")
stmt = select(UploadFile).filter(
UploadFile.id == file.related_id,
UploadFile.tenant_id == file.tenant_id,
)
record = session.scalar(stmt)
if not record:
raise ValueError(f"upload file {file.related_id} not found")
return record
def get_tool_file(*, session: Session, file: File):
if file.related_id is None:
raise ValueError("Missing file related_id")
stmt = select(ToolFile).filter(
ToolFile.id == file.related_id,
ToolFile.tenant_id == file.tenant_id,
)
record = session.scalar(stmt)
if not record:
raise ValueError(f"tool file {file.related_id} not found")
return record
-13
View File
@@ -7,19 +7,6 @@ import time
from configs import dify_config
def get_signed_image_url(upload_file_id: str) -> str:
url = f"{dify_config.FILES_URL}/files/{upload_file_id}/image-preview"
timestamp = str(int(time.time()))
nonce = os.urandom(16).hex()
key = dify_config.SECRET_KEY.encode()
msg = f"image-preview|{upload_file_id}|{timestamp}|{nonce}"
sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
encoded_sign = base64.urlsafe_b64encode(sign).decode()
return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}"
def get_signed_file_url(upload_file_id: str) -> str:
url = f"{dify_config.FILES_URL}/files/{upload_file_id}/file-preview"
+4 -4
View File
@@ -43,13 +43,13 @@ class File(BaseModel):
remote_url: Optional[str] = None # remote url
related_id: Optional[str] = None
filename: Optional[str] = None
extension: Optional[str] = None
extension: Optional[str] = Field(default=None, description="File extension, should contains dot")
mime_type: Optional[str] = None
size: int = 0
size: int = -1
_extra_config: FileExtraConfig | None = None
def to_dict(self) -> Mapping[str, str | int | None]:
data = self.model_dump()
data = self.model_dump(mode="json")
return {
**data,
"url": self.generate_url(),
@@ -72,7 +72,7 @@ class File(BaseModel):
elif self.transfer_method == FileTransferMethod.LOCAL_FILE:
if self.related_id is None:
raise ValueError("Missing file related_id")
return helpers.get_signed_image_url(upload_file_id=self.related_id)
return helpers.get_signed_file_url(upload_file_id=self.related_id)
elif self.transfer_method == FileTransferMethod.TOOL_FILE:
assert self.related_id is not None
assert self.extension is not None
+2 -2
View File
@@ -211,9 +211,9 @@ class IndexingRunner:
tenant_id: str,
extract_settings: list[ExtractSetting],
tmp_processing_rule: dict,
doc_form: str = None,
doc_form: Optional[str] = None,
doc_language: str = "English",
dataset_id: str = None,
dataset_id: Optional[str] = None,
indexing_technique: str = "economy",
) -> dict:
"""
+8 -3
View File
@@ -60,7 +60,11 @@ class TokenBufferMemory:
# instead of all messages from the conversation, we only need to extract messages
# that belong to the thread of last message
thread_messages = extract_thread_messages(messages)
thread_messages.pop(0)
# for newly created message, its answer is temporarily empty, we don't need to add it to memory
if thread_messages and not thread_messages[0].answer:
thread_messages.pop(0)
messages = list(reversed(thread_messages))
prompt_messages = []
@@ -68,7 +72,7 @@ class TokenBufferMemory:
files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
if files:
file_extra_config = None
if self.conversation.mode not in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
if self.conversation.mode not in {AppMode.ADVANCED_CHAT, AppMode.WORKFLOW}:
file_extra_config = FileUploadConfigManager.convert(self.conversation.model_config)
else:
if message.workflow_run_id:
@@ -94,7 +98,8 @@ class TokenBufferMemory:
prompt_message_contents: list[PromptMessageContent] = []
prompt_message_contents.append(TextPromptMessageContent(data=message.query))
for file_obj in file_objs:
prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
prompt_message = file_manager.to_prompt_message_content(file_obj)
prompt_message_contents.append(prompt_message)
prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
else:
+5 -5
View File
@@ -1,9 +1,9 @@
import logging
import os
from collections.abc import Callable, Generator, Sequence
from typing import IO, Optional, Union, cast
from collections.abc import Callable, Generator, Iterable, Sequence
from typing import IO, Any, Optional, Union, cast
from core.embedding.embedding_constant import EmbeddingInputType
from core.entities.embedding_type import EmbeddingInputType
from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
from core.entities.provider_entities import ModelLoadBalancingConfiguration
from core.errors.error import ProviderTokenNotInitError
@@ -274,7 +274,7 @@ class ModelInstance:
user=user,
)
def invoke_tts(self, content_text: str, tenant_id: str, voice: str, user: Optional[str] = None) -> str:
def invoke_tts(self, content_text: str, tenant_id: str, voice: str, user: Optional[str] = None) -> Iterable[bytes]:
"""
Invoke large language tts model
@@ -298,7 +298,7 @@ class ModelInstance:
voice=voice,
)
def _round_robin_invoke(self, function: Callable, *args, **kwargs):
def _round_robin_invoke(self, function: Callable[..., Any], *args, **kwargs):
"""
Round-robin invoke
:param function: function to invoke
@@ -1,6 +1,7 @@
from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
from .message_entities import (
AssistantPromptMessage,
AudioPromptMessageContent,
ImagePromptMessageContent,
PromptMessage,
PromptMessageContent,
@@ -33,4 +34,5 @@ __all__ = [
"LLMResult",
"LLMResultChunk",
"LLMResultChunkDelta",
"AudioPromptMessageContent",
]
@@ -2,7 +2,7 @@ from abc import ABC
from enum import Enum
from typing import Optional
from pydantic import BaseModel, field_validator
from pydantic import BaseModel, Field, field_validator
class PromptMessageRole(Enum):
@@ -55,6 +55,7 @@ class PromptMessageContentType(Enum):
TEXT = "text"
IMAGE = "image"
AUDIO = "audio"
class PromptMessageContent(BaseModel):
@@ -74,6 +75,12 @@ class TextPromptMessageContent(PromptMessageContent):
type: PromptMessageContentType = PromptMessageContentType.TEXT
class AudioPromptMessageContent(PromptMessageContent):
type: PromptMessageContentType = PromptMessageContentType.AUDIO
data: str = Field(..., description="Base64 encoded audio data")
format: str = Field(..., description="Audio format")
class ImagePromptMessageContent(PromptMessageContent):
"""
Model class for image prompt message content.
@@ -94,7 +94,7 @@ class LargeLanguageModel(AIModel):
)
try:
if "response_format" in model_parameters:
if "response_format" in model_parameters and model_parameters["response_format"] in {"JSON", "XML"}:
result = self._code_block_mode_wrapper(
model=model,
credentials=credentials,
@@ -107,7 +107,16 @@ class LargeLanguageModel(AIModel):
callbacks=callbacks,
)
else:
result = self._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream, user)
result = self._invoke(
model=model,
credentials=credentials,
prompt_messages=prompt_messages,
model_parameters=model_parameters,
tools=tools,
stop=stop,
stream=stream,
user=user,
)
except Exception as e:
self._trigger_invoke_error_callbacks(
model=model,
@@ -4,7 +4,7 @@ from typing import Optional
from pydantic import ConfigDict
from core.embedding.embedding_constant import EmbeddingInputType
from core.entities.embedding_type import EmbeddingInputType
from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
from core.model_runtime.model_providers.__base.ai_model import AIModel
@@ -1,7 +1,8 @@
import logging
import re
from abc import abstractmethod
from typing import Optional
from collections.abc import Iterable
from typing import Any, Optional
from pydantic import ConfigDict
@@ -22,8 +23,14 @@ class TTSModel(AIModel):
model_config = ConfigDict(protected_namespaces=())
def invoke(
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
):
self,
model: str,
tenant_id: str,
credentials: dict,
content_text: str,
voice: str,
user: Optional[str] = None,
) -> Iterable[bytes]:
"""
Invoke large language model
@@ -50,8 +57,14 @@ class TTSModel(AIModel):
@abstractmethod
def _invoke(
self, model: str, tenant_id: str, credentials: dict, content_text: str, voice: str, user: Optional[str] = None
):
self,
model: str,
tenant_id: str,
credentials: dict,
content_text: str,
voice: str,
user: Optional[str] = None,
) -> Iterable[bytes]:
"""
Invoke large language model
@@ -68,27 +81,27 @@ class TTSModel(AIModel):
def get_tts_model_voices(self, model: str, credentials: dict, language: Optional[str] = None) -> list:
"""
Get voice for given tts model voices
Retrieves the list of voices supported by a given text-to-speech (TTS) model.
:param language: tts language
:param model: model name
:param credentials: model credentials
:return: voices lists
:param language: The language for which the voices are requested.
:param model: The name of the TTS model.
:param credentials: The credentials required to access the TTS model.
:return: A list of voices supported by the TTS model.
"""
model_schema = self.get_model_schema(model, credentials)
if model_schema and ModelPropertyKey.VOICES in model_schema.model_properties:
voices = model_schema.model_properties[ModelPropertyKey.VOICES]
if language:
return [
{"name": d["name"], "value": d["mode"]}
for d in voices
if language and language in d.get("language")
]
else:
return [{"name": d["name"], "value": d["mode"]} for d in voices]
if not model_schema or ModelPropertyKey.VOICES not in model_schema.model_properties:
raise ValueError("this model does not support voice")
def _get_model_default_voice(self, model: str, credentials: dict) -> any:
voices = model_schema.model_properties[ModelPropertyKey.VOICES]
if language:
return [
{"name": d["name"], "value": d["mode"]} for d in voices if language and language in d.get("language")
]
else:
return [{"name": d["name"], "value": d["mode"]} for d in voices]
def _get_model_default_voice(self, model: str, credentials: dict) -> Any:
"""
Get voice for given tts model
@@ -111,8 +124,10 @@ class TTSModel(AIModel):
"""
model_schema = self.get_model_schema(model, credentials)
if model_schema and ModelPropertyKey.AUDIO_TYPE in model_schema.model_properties:
return model_schema.model_properties[ModelPropertyKey.AUDIO_TYPE]
if not model_schema or ModelPropertyKey.AUDIO_TYPE not in model_schema.model_properties:
raise ValueError("this model does not support audio type")
return model_schema.model_properties[ModelPropertyKey.AUDIO_TYPE]
def _get_model_word_limit(self, model: str, credentials: dict) -> int:
"""
@@ -121,8 +136,10 @@ class TTSModel(AIModel):
"""
model_schema = self.get_model_schema(model, credentials)
if model_schema and ModelPropertyKey.WORD_LIMIT in model_schema.model_properties:
return model_schema.model_properties[ModelPropertyKey.WORD_LIMIT]
if not model_schema or ModelPropertyKey.WORD_LIMIT not in model_schema.model_properties:
raise ValueError("this model does not support word limit")
return model_schema.model_properties[ModelPropertyKey.WORD_LIMIT]
def _get_model_workers_limit(self, model: str, credentials: dict) -> int:
"""
@@ -131,8 +148,10 @@ class TTSModel(AIModel):
"""
model_schema = self.get_model_schema(model, credentials)
if model_schema and ModelPropertyKey.MAX_WORKERS in model_schema.model_properties:
return model_schema.model_properties[ModelPropertyKey.MAX_WORKERS]
if not model_schema or ModelPropertyKey.MAX_WORKERS not in model_schema.model_properties:
raise ValueError("this model does not support max workers")
return model_schema.model_properties[ModelPropertyKey.MAX_WORKERS]
@staticmethod
def _split_text_into_sentences(org_text, max_length=2000, pattern=r"[。.!?]"):
@@ -169,7 +169,7 @@ class AnthropicLargeLanguageModel(LargeLanguageModel):
stop: Optional[list[str]] = None,
stream: bool = True,
user: Optional[str] = None,
callbacks: list[Callback] = None,
callbacks: Optional[list[Callback]] = None,
) -> Union[LLMResult, Generator]:
"""
Code block mode wrapper for invoking large language model
@@ -1081,8 +1081,97 @@ LLM_BASE_MODELS = [
),
),
),
AzureBaseModel(
base_model_name="o1-preview",
entity=AIModelEntity(
model="fake-deployment-name",
label=I18nObject(
en_US="fake-deployment-name-label",
),
model_type=ModelType.LLM,
features=[
ModelFeature.AGENT_THOUGHT,
],
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
model_properties={
ModelPropertyKey.MODE: LLMMode.CHAT.value,
ModelPropertyKey.CONTEXT_SIZE: 128000,
},
parameter_rules=[
ParameterRule(
name="temperature",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
),
ParameterRule(
name="top_p",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
),
ParameterRule(
name="response_format",
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
type="string",
help=I18nObject(
zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
),
required=False,
options=["text", "json_object"],
),
_get_max_tokens(default=512, min_val=1, max_val=32768),
],
pricing=PriceConfig(
input=15.00,
output=60.00,
unit=0.000001,
currency="USD",
),
),
),
AzureBaseModel(
base_model_name="o1-mini",
entity=AIModelEntity(
model="fake-deployment-name",
label=I18nObject(
en_US="fake-deployment-name-label",
),
model_type=ModelType.LLM,
features=[
ModelFeature.AGENT_THOUGHT,
],
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
model_properties={
ModelPropertyKey.MODE: LLMMode.CHAT.value,
ModelPropertyKey.CONTEXT_SIZE: 128000,
},
parameter_rules=[
ParameterRule(
name="temperature",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TEMPERATURE],
),
ParameterRule(
name="top_p",
**PARAMETER_RULE_TEMPLATE[DefaultParameterName.TOP_P],
),
ParameterRule(
name="response_format",
label=I18nObject(zh_Hans="回复格式", en_US="response_format"),
type="string",
help=I18nObject(
zh_Hans="指定模型必须输出的格式", en_US="specifying the format that the model must output"
),
required=False,
options=["text", "json_object"],
),
_get_max_tokens(default=512, min_val=1, max_val=65536),
],
pricing=PriceConfig(
input=3.00,
output=12.00,
unit=0.000001,
currency="USD",
),
),
),
]
EMBEDDING_BASE_MODELS = [
AzureBaseModel(
base_model_name="text-embedding-ada-002",
@@ -53,6 +53,9 @@ model_credential_schema:
type: select
required: true
options:
- label:
en_US: 2024-09-01-preview
value: 2024-09-01-preview
- label:
en_US: 2024-08-01-preview
value: 2024-08-01-preview
@@ -120,6 +123,18 @@ model_credential_schema:
show_on:
- variable: __model_type
value: llm
- label:
en_US: o1-mini
value: o1-mini
show_on:
- variable: __model_type
value: llm
- label:
en_US: o1-preview
value: o1-preview
show_on:
- variable: __model_type
value: llm
- label:
en_US: gpt-4o-mini
value: gpt-4o-mini
@@ -119,7 +119,15 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
try:
client = AzureOpenAI(**self._to_credential_kwargs(credentials))
if ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
if model.startswith("o1"):
client.chat.completions.create(
messages=[{"role": "user", "content": "ping"}],
model=model,
temperature=1,
max_completion_tokens=20,
stream=False,
)
elif ai_model_entity.entity.model_properties.get(ModelPropertyKey.MODE) == LLMMode.CHAT.value:
# chat model
client.chat.completions.create(
messages=[{"role": "user", "content": "ping"}],
@@ -312,10 +320,24 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
if user:
extra_model_kwargs["user"] = user
# clear illegal prompt messages
prompt_messages = self._clear_illegal_prompt_messages(model, prompt_messages)
block_as_stream = False
if model.startswith("o1"):
if stream:
block_as_stream = True
stream = False
if "stream_options" in extra_model_kwargs:
del extra_model_kwargs["stream_options"]
if "stop" in extra_model_kwargs:
del extra_model_kwargs["stop"]
# chat model
messages = [self._convert_prompt_message_to_dict(m) for m in prompt_messages]
response = client.chat.completions.create(
messages=messages,
messages=[self._convert_prompt_message_to_dict(m) for m in prompt_messages],
model=model,
stream=stream,
**model_parameters,
@@ -325,7 +347,91 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
if stream:
return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages, tools)
return self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
block_result = self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
if block_as_stream:
return self._handle_chat_block_as_stream_response(block_result, prompt_messages, stop)
return block_result
def _handle_chat_block_as_stream_response(
self,
block_result: LLMResult,
prompt_messages: list[PromptMessage],
stop: Optional[list[str]] = None,
) -> Generator[LLMResultChunk, None, None]:
"""
Handle llm chat response
:param model: model name
:param credentials: credentials
:param response: response
:param prompt_messages: prompt messages
:param tools: tools for tool calling
:param stop: stop words
:return: llm response chunk generator
"""
text = block_result.message.content
text = cast(str, text)
if stop:
text = self.enforce_stop_tokens(text, stop)
yield LLMResultChunk(
model=block_result.model,
prompt_messages=prompt_messages,
system_fingerprint=block_result.system_fingerprint,
delta=LLMResultChunkDelta(
index=0,
message=AssistantPromptMessage(content=text),
finish_reason="stop",
usage=block_result.usage,
),
)
def _clear_illegal_prompt_messages(self, model: str, prompt_messages: list[PromptMessage]) -> list[PromptMessage]:
"""
Clear illegal prompt messages for OpenAI API
:param model: model name
:param prompt_messages: prompt messages
:return: cleaned prompt messages
"""
checklist = ["gpt-4-turbo", "gpt-4-turbo-2024-04-09"]
if model in checklist:
# count how many user messages are there
user_message_count = len([m for m in prompt_messages if isinstance(m, UserPromptMessage)])
if user_message_count > 1:
for prompt_message in prompt_messages:
if isinstance(prompt_message, UserPromptMessage):
if isinstance(prompt_message.content, list):
prompt_message.content = "\n".join(
[
item.data
if item.type == PromptMessageContentType.TEXT
else "[IMAGE]"
if item.type == PromptMessageContentType.IMAGE
else ""
for item in prompt_message.content
]
)
if model.startswith("o1"):
system_message_count = len([m for m in prompt_messages if isinstance(m, SystemPromptMessage)])
if system_message_count > 0:
new_prompt_messages = []
for prompt_message in prompt_messages:
if isinstance(prompt_message, SystemPromptMessage):
prompt_message = UserPromptMessage(
content=prompt_message.content,
name=prompt_message.name,
)
new_prompt_messages.append(prompt_message)
prompt_messages = new_prompt_messages
return prompt_messages
def _handle_chat_generate_response(
self,
@@ -560,7 +666,7 @@ class AzureOpenAILargeLanguageModel(_CommonAzureOpenAI, LargeLanguageModel):
tokens_per_message = 4
# if there's a name, the role is omitted
tokens_per_name = -1
elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4"):
elif model.startswith("gpt-35-turbo") or model.startswith("gpt-4") or model.startswith("o1"):
tokens_per_message = 3
tokens_per_name = 1
else:

Some files were not shown because too many files have changed in this diff Show More