Compare commits

...
Author SHA1 Message Date
NFishandGitHub ec8b5f23d3 fix: nextjs security update (e-260) (#29553) 2025-12-12 11:42:48 +08:00
JoeandGareArc 173110e04d fix: dataset editor 2025-06-20 16:10:22 +08:00
Xiyuan ChenandGareArc 63f3af8bc4 feat: use default access mode when importing dsl (#21231) 2025-06-19 17:15:59 +08:00
NFishandGitHub 3e60e682d1 Fix/webapp auth failed (#21149) 2025-06-18 11:25:45 +08:00
Xiyuan ChenandGitHub 0c01f7498d Feat/webapp verified sso 260 (#20815) 2025-06-09 15:11:30 +09:00
NFish c7d4026800 fix: remove all app token when logout 2025-06-06 15:53:40 +08:00
Xiyuan ChenandGitHub 512c1938c1 Feat/webapp verified sso 260: fetch previous app session in public token exchange (#20740) 2025-06-06 16:52:15 +09:00
Xiyuan ChenandGitHub 78cf376872 Feat/webapp verified sso 260: bad import path (#20734) 2025-06-06 16:09:45 +09:00
Xiyuan ChenandGitHub e312894bc9 Feat/webapp verified sso 260: add token exchange for public app (#20731) 2025-06-06 15:49:08 +09:00
NFishandGitHub 26f291396d Fix/webapp no permission page 260 (#20730) 2025-06-06 14:27:25 +08:00
Garfield Dai 4835d78529 Merge tag '0.15.8' into e-260
0.15.8
2025-06-06 12:26:42 +08:00
Xiyuan ChenandGitHub 05b746b350 Feat/webapp verified sso 260 (#20690) 2025-06-05 18:36:59 +09:00
Xiyuan ChenandGitHub 94289b8af9 Feat/webapp verified sso 260 (#20684) 2025-06-05 17:31:08 +09:00
Xiyuan ChenandGitHub dcf4e5a30f Feat/webapp verified sso 260 (#20678) 2025-06-05 16:17:44 +09:00
Xiyuan ChenandGitHub 05903e3251 Feat/webapp verified sso 260 (#20496) 2025-06-05 16:00:37 +09:00
NFishandGitHub 1357999a4c fix: merge web app access scope control (#20675) 2025-06-05 14:37:35 +08:00
-LAN- 4b938ab18d chore: Bump version
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 16:25:40 +08:00
-LAN- 88356de923 fix: Refactor web reader to use readabilipy (#19789)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 16:23:17 +08:00
-LAN-andGitHub 5f09900dca chore(api): Upgrade dependencies (#19736)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-15 14:47:15 +08:00
-LAN- 9ac99abf20 docs(CHANGELOG): Update CHANGELOG
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-14 18:03:05 +08:00
-LAN- 32588f562e feat(model): fix and re-add gpt-4.1.
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-14 18:02:32 +08:00
JoelandGitHub 36f8bd3f1a chore: frontend third-part package security issue (#19655) 2025-05-14 14:08:05 +08:00
Xiyuan ChenandGitHub 4466088f2e fix: invitations get suspended when an existing member appears (#19585) 2025-05-13 13:54:01 +08:00
-LAN- c919074e06 docs(CHANGELOG.md): Update CHANGELOG.md
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-13 10:31:40 +08:00
88cd9aedb7 add gunicorn keepalive setting (#19537)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Bowen Liang <liang.bowen.123@qq.com>
2025-05-13 10:28:13 +08:00
-LAN- 16a4f77fb4 fix(config): Allow DB_EXTRAS to set search_path via options
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-13 10:19:08 +08:00
-LAN-andGitHub 3401c52665 chore(pyproject.toml): Upgrade huggingface-hub, transformers and resend (#19563)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-12 23:21:57 +08:00
NFishandGitHub bc882ac4a1 fix: only owner can edit members in workspace (#19321) 2025-05-07 14:16:54 +08:00
1c2e8e1ce7 fix removing member without permission (#16332) (#19275)
Co-authored-by: Linh Nguyen <55907715+batman0911@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-06 15:41:50 +08:00
Garfield Dai 33d2c9d2ca Merge branch 'release/0.15-support' into e-260 2025-04-28 18:18:54 +08:00
Zixuan ChengandGitHub 4fa3d78ed8 Revert "feat : add GPT4.1 in the model providers" (#19002) 2025-04-28 18:15:24 +08:00
Garfield Dai 849994d35e Merge tag '0.15.7' into e-260
0.15.7
2025-04-28 17:17:26 +08:00
NFishandGitHub 2fce4a338c fix: get realtime groups and members data every time user open the di… (#18988) 2025-04-28 17:01:07 +08:00
-LAN- 5f7f851b17 fix: Refines None checks in result transformation
Simplifies the code by replacing type checks for None with
direct comparisons, improving readability and consistency in
handling None values during output validation.

Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-28 15:40:14 +08:00
-LAN- 559ab46ee1 fix: Removes redundant token calculations and updates dependencies
Eliminates unnecessary pre-calculation of token limits and recalculation of max tokens
across multiple app runners, simplifying the logic for prompt handling.

Updates tiktoken library from version 0.8.0 to 0.9.0 for improved tokenization performance.

Increases default token limit in TokenBufferMemory to accommodate larger prompt messages.

These changes streamline the token management process and leverage the latest
improvements in the tiktoken library.

Fixes potential token overflow issues and prepares the system for handling larger
inputs more efficiently.

Relates to internal optimization tasks.

Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-28 15:39:12 +08:00
-LAN- df98223c8c chore: Updates to version 0.15.7 with new model support
Adds support for GPT-4.1 and Amazon Bedrock DeepSeek-R1 models.
Fixes issues with app creation from template categories and
DSL version checks.

Updates version numbers in configuration files and Docker
setup to 0.15.7 for consistency.

Addresses issues #18807, #18868, #18872, #18878, and #18912.

Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-28 14:19:07 +08:00
Zixuan ChengandGitHub 144f9507f8 feat : add GPT4.1 in the model providers (#18912) 2025-04-27 19:31:20 +08:00
kelvintsimandGitHub 2e097a1ac0 add bedrock deepseek-r1 (#18908) 2025-04-27 19:30:42 +08:00
NFishandGitHub 9f7d8a981f Patch: hotfix/create from template category (#18807) (#18868) 2025-04-27 14:47:18 +08:00
c4729f8c20 fix: check dsl version when create app from explore template (#18872)… (#18881)
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
2025-04-27 14:32:28 +08:00
NFishandGitHub 5cb1cf9eca Patch: Hotfix/create from template category (#18807) (#18869) 2025-04-27 14:28:05 +08:00
zxhlyhandGitHub 40b31bafd5 fix: check dsl version when create app from explore template (#18872) (#18878) 2025-04-27 14:21:45 +08:00
-LAN- d38a2c95fb docs(CHANGELOG): Update CHANGELOG.md
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-25 18:31:08 +08:00
-LAN- 7d18e2a0ef feat(app_dsl_service): Refines version compatibility logic
Updates logic to handle various version comparisons, ensuring
more precise status returns based on version differences.
Improves handling of older and newer versions to prevent
mismatches and ensure appropriate compatibility status.

Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-25 18:27:31 +08:00
kelvintsimandGitHub 024f242251 add bedrock claude-sonnet-3.7 (#18788) 2025-04-25 17:35:12 +08:00
NFishandGitHub de14a55bde fix: i18n update (#18787) 2025-04-25 17:28:32 +08:00
NFishandGitHub cbb1d722a5 fix: break switch logic if the sso protocol is empty (#18783) 2025-04-25 17:19:44 +08:00
NFishandGitHub 1769ce16f3 fix: disable batch run button when user has no permission. (#18777) 2025-04-25 16:46:58 +08:00
NFishandGitHub 170139bb0f fix: update sso protocol default value to '' (#18773) 2025-04-25 16:20:20 +08:00
NFishandGitHub ede0deb447 Fix/web app signin error (#18765) 2025-04-25 15:34:18 +08:00
NFishandGitHub d40f2e7d94 fix: web app login show undefined error message (#18757) 2025-04-25 14:09:38 +08:00
NFishandGitHub 70ebfc064b fix: stop auto retry login when web app return error (#18747) 2025-04-25 12:09:13 +08:00
GareArc d6c252d77e Merge branch 'feat/webapp-auth-api' into e-260 2025-04-24 23:48:25 -04:00
GareArc fc3d3e0565 fix: wrong web sso protocal source in json 2025-04-24 23:48:18 -04:00
Xin ZhangandGitHub b786bbdab5 fix: add workspace limitation in invite-login API (#18724) 2025-04-25 09:52:47 +08:00
Xin ZhangandGitHub f45321dd27 fix: handle WorkspacesLimitExceededError in forgot_password.py (#18716) 2025-04-24 18:41:10 +08:00
NFishandGitHub 746d4d8ead fix: update i18n (#18711) 2025-04-24 18:14:03 +08:00
NFishandGitHub 7c31e3b6ba Hotfix/revert webapp login page (#18706) 2025-04-24 17:54:03 +08:00
Garfield Dai 7c1116f139 update. 2025-04-24 15:27:04 +08:00
Xin ZhangandGitHub b82cc1c2e8 feat: priced limit (#17683) 2025-04-24 14:58:34 +08:00
NFishandGitHub fee51ba994 Feat/e permission (#18656) 2025-04-24 13:10:01 +08:00
GareArc 2259dfdc58 Merge branch 'feat/webapp-auth-api' into e-260 2025-04-23 23:10:02 -04:00
GareArc 3761944a3f fix: remove debug logs 2025-04-23 23:09:45 -04:00
GareArc a239e756b0 Merge tag '0.15.6' into e-260
0.15.6
2025-04-23 22:41:12 -04:00
GareArc ac54dd89f4 fix: change rel url value to target_ref 2025-04-23 22:39:21 -04:00
GareArc 5310ed4b54 Merge branch 'feat/webapp-auth-api' into e-260 2025-04-23 22:38:04 -04:00
-LAN- bfdce78ca5 chore(*): Bump up to 0.15.6
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-23 14:06:46 +08:00
-LAN- 00c2258352 CHANGELOG): Adds initial changelog for version 0.15.6
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-04-23 13:55:33 +08:00
GareArc 09f8da1429 fix: allow empty list api 2025-04-22 22:20:29 -04:00
9f07584a00 Feat/e license limit (#18436)
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
2025-04-23 00:23:38 +08:00
JoelandGitHub a1b3d41712 fix: clickjacking (#18552) 2025-04-22 17:08:52 +08:00
GareArc fcc274d679 fix: add filter in installedapp list api 2025-04-22 02:54:30 -04:00
GareArc 14f378bbc6 Merge branch 'feat/webapp-auth-api' into e-260 2025-04-21 22:18:35 -04:00
GareArc 669fb6be0f fix: wrong field name 2025-04-21 22:18:16 -04:00
GareArc 724ffe55c9 fix: add back sso system feature 2025-04-21 22:02:50 -04:00
GareArc bfa5828259 fix: temp fix for unauthorized user in explore page 2025-04-21 19:40:51 -04:00
GareArc 455d14296f fix: get app id from upstream decorator 2025-04-21 19:03:10 -04:00
GareArc d1a25e54e5 fix: add logging 2025-04-21 18:48:24 -04:00
GareArc 9462ed7bbf fix: add auth constraint to explore apps 2025-04-21 18:47:24 -04:00
GareArc c6e63ac816 Revert "fix: update webapp auth api path"
This reverts commit a27db51b83.
2025-04-21 02:07:43 -04:00
GareArc a27db51b83 fix: update webapp auth api path 2025-04-21 02:06:07 -04:00
GareArc e52a9fbfb7 fix: remove curr user in webapp permission api 2025-04-20 23:33:51 -04:00
GareArc 2af1dd6de3 feat: add webapp auth apis 2025-04-20 23:30:59 -04:00
b26e20fe34 fix: fix vertex gemini 2.0 flash 001 schema (#18405)
Co-authored-by: achmad-kautsar <achmad.kautsar@insignia.co.id>
2025-04-19 22:04:13 +08:00
NFishandGitHub 161ff432f1 fix: update reset password token when email code verify success (#18362) 2025-04-18 17:15:15 +08:00
NFishandGitHub 509733fbf0 fix: update reset password token when email code verify success (#18367) 2025-04-18 17:15:02 +08:00
Xiyuan ChenandGitHub 99a9def623 fix: reset_password security issue (#18366) 2025-04-18 05:04:44 -04:00
GareArc 7770a45253 fix: add password security update 2025-04-18 05:02:26 -04:00
GareArc bafdbade52 fix: wrong json structure 2025-04-11 17:19:34 -04:00
GareArc fa76590c24 chore: add log 2025-04-11 16:59:52 -04:00
GareArc d5b75470e4 fix: bad request 2025-04-11 16:48:09 -04:00
GareArc 5f87bdbe3a fix: add batch get access mode api 2025-04-11 15:24:32 -04:00
GareArc cb13b53ccd fix: update webapp sso features 2025-04-11 03:25:58 -04:00
GareArc a1dc3cfdec fix: update code for access denied error 2025-04-11 02:45:46 -04:00
GareArc 7a4ec9cf23 fix: change error code for webapp auth 2025-04-11 02:41:02 -04:00
GareArc 4785c061a9 feat: add webapp clean up 2025-04-10 15:19:28 -04:00
GareArc 4105c8ff70 fix: bad api call 2025-04-10 06:27:00 -04:00
GareArc b922c8c215 fix: make app private when created 2025-04-10 00:36:35 -04:00
GareArc cbea30e65f fix: bad field name 2025-04-09 17:21:16 -04:00
GareArc e9a207b38e fix: adjust enterprise api 2025-04-09 16:30:41 -04:00
GareArc 5e50570739 fix: update webapp jwt claim and add user accessibility support 2025-04-07 18:41:02 -04:00
GareArc 46d43e6758 feat: add web app auth 2025-04-07 17:03:26 -04:00
Alexi.FandGitHub fe1846c437 fix: change gemini-2.0-flash to validate google api #17082 (#17115) 2025-03-30 13:04:12 +08:00
GareArc 1045f6db7a fix: wrong arg parsing 2025-03-26 01:37:45 -04:00
GareArc 50d36612f0 fix: bad import 2025-03-26 00:34:04 -04:00
GareArc e38631db8a feat: add inner mail api 2025-03-25 21:47:30 -04:00
Garfield Dai 7f63cd52a2 update. 2025-03-24 23:08:54 +08:00
-LAN- 8e75eb5c63 fix: update version to 0.15.5 in packaging and docker-compose files
Sgned-off-by: -LAN- <lapz8200@outlook.com>
2025-03-24 16:47:06 +08:00
-LAN- 970508fcb6 fix: update GitHub Actions workflow to trigger on tags
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-03-24 16:45:29 +08:00
NFish 5b357fdbf0 Merge branch 'release/0.15.5' into e-0154 2025-03-24 16:42:11 +08:00
NFish 9283a5414f fix: update yarn.lock 2025-03-24 16:41:07 +08:00
NFish 8923e64b8d Merge branch 'release/0.15.5' into e-0154 2025-03-24 15:40:32 +08:00
-LAN- 2a2a0e9be9 fix: update DifySandbox image version to 0.2.11 in docker-compose files
Sgned-off-by: -LAN- <laipz8200@outlook.com>
2025-03-24 15:37:55 +08:00
JoelandGitHub 061a765b7d fix: sanitizer svg to avoid xss (#16608) 2025-03-24 14:48:40 +08:00
-LAN- acd7fead87 feat: remove Vanna provider and associated assets from the project
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-03-24 14:34:03 +08:00
KVOJJJinandNFish 64e9d96d84 chore: compatible with es5 (#14268) 2025-03-24 13:17:48 +08:00
NFish d27de3818c Merge branch 'release/0.15.5' into e-0154 2025-03-24 11:46:30 +08:00
NFish bbb080d5b2 fix: update chatbot help doc link on the create app form 2025-03-24 11:28:35 +08:00
NFish 8c025abb3b Merge branch 'release/0.15.5' into e-0154 2025-03-24 10:32:56 +08:00
NFish c01d8a70f3 fix: upgrade nextjs to v14.2.25. a security patch for CVE-2025-29927. 2025-03-24 10:32:18 +08:00
NFish 98606ca558 fix: upgrade nextjs to v14.2.25 2025-03-24 10:12:21 +08:00
Garfield Dai adf3e18ebd Merge tag '0.15.4' into e-0154 2025-03-21 18:29:43 +08:00
-LAN- 1ca15989e0 chore: update version to 0.15.4 in configuration and docker files
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-03-21 16:39:06 +08:00
-LAN- 8b5a3a9424 Merge branch 'release/0.15.4' of github.com:langgenius/dify into release/0.15.4 2025-03-21 16:31:06 +08:00
-LAN- 42ddcf1edd chore: remove 0.15.3 branch config in the build action
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-03-21 16:30:33 +08:00
JoelandGitHub 21561df10f fix: xss in render svg (#16437) 2025-03-21 15:24:58 +08:00
Byron.wangandGitHub 4327ec8c4c fix license expireAt field typo (#16428) 2025-03-21 13:43:43 +08:00
NFish bbc5ec8301 fix: expired date calc error 2025-03-21 11:00:07 +08:00
NFish 4a51a72c1d Merge branch 'e-0154' into deploy/enterprise 2025-03-20 17:34:52 +08:00
NFish 4b6adffa8e fix: hide copyright on forgot-password/install/reset-password page 2025-03-20 17:34:19 +08:00
NFish c7fd73d330 Merge branch 'e-0154' into deploy/enterprise 2025-03-20 10:13:09 +08:00
NFish 8a709e445a fix: remove Dify from Service API doc 2025-03-20 10:12:27 +08:00
NFish f02b77b99f fix: Decouple login page logo component to avoid conflict with internal logo 2025-03-20 10:11:26 +08:00
GareArc abc625bcce Merge branch 'e-0154' into deploy/enterprise 2025-03-18 22:35:39 -04:00
GareArc b6bc1f8bc4 fix: adjust logic for branding toggle 2025-03-18 22:35:27 -04:00
NFish b8f9037cd3 Merge branch 'e-0154' into deploy/enterprise 2025-03-18 16:13:14 +08:00
NFish 02606ba3c7 fix: cannot update webapp copyright info 2025-03-18 16:12:52 +08:00
GareArc 79311d3fb5 Merge branch 'e-0154' into deploy/enterprise 2025-03-18 03:53:18 -04:00
GareArc 31086a1fbf feat: add webapp copyright feature 2025-03-18 03:53:07 -04:00
NFish 6ae5d052e5 Merge branch 'e-0154' into deploy/enterprise 2025-03-18 14:55:36 +08:00
NFish c794ecf101 fix: user can edit webapp copyright info only if webapp_copyright_enabled is true 2025-03-18 14:54:34 +08:00
GareArc d887aae012 Merge branch 'e-0154' into deploy/enterprise 2025-03-18 01:55:38 -04:00
GareArc 1b1e96eff7 fix: typo 2025-03-18 01:55:27 -04:00
GareArc eecd091063 Merge branch 'e-0154' into deploy/enterprise 2025-03-17 15:34:49 -04:00
GareArc d38f2cb380 fix: change subject title 2025-03-17 15:34:28 -04:00
GareArc 56aaee5558 fix: wrong branding title 2025-03-17 15:01:31 -04:00
GareArc d72b4752c9 fix: wrong title location 2025-03-17 15:00:04 -04:00
GareArc ea769c6483 Merge branch 'e-0154' into deploy/enterprise 2025-03-17 14:24:00 -04:00
GareArc ec194fa3d4 fix: invalid email template variables 2025-03-17 14:23:46 -04:00
NFish b877039859 Merge branch 'e-0154' into deploy/enterprise 2025-03-17 10:37:20 +08:00
NFish 54634f26d2 fix: show copyright in webapp 2025-03-17 10:36:51 +08:00
NFish 3bef91a2cd fix: show loading icon when fetching system features 2025-03-15 12:01:30 +08:00
NFish 7da45ba589 fix: show loading icon when fetching system features 2025-03-15 12:00:22 +08:00
NFish e0232c67cc fix: update document title and favicon in client side 2025-03-15 12:00:22 +08:00
GareArc 1dc4a229d4 Merge branch 'e-0154' into deploy/enterprise 2025-03-14 16:37:02 -04:00
GareArc 0e0bada1f3 fix: missing json keys 2025-03-14 16:36:49 -04:00
GareArc 5366a814f9 fix: update json keys 2025-03-14 16:35:05 -04:00
GareArc f1240a22db fix: remove default value 2025-03-14 13:26:44 -04:00
NFish 66f35c2b7e Merge branch 'e-0154' into deploy/enterprise 2025-03-15 01:25:15 +08:00
NFish 766ee48531 fix: update document title and favicon in client side 2025-03-15 01:25:04 +08:00
NFish 083045f45c Merge branch 'e-0154' into deploy/enterprise 2025-03-14 20:49:17 +08:00
NFish fe237802c9 fix: update Dify text 2025-03-14 19:10:03 +08:00
NFish 00b923651f fix: update document title with system features config 2025-03-14 19:10:03 +08:00
NFish 24fce3cc64 chore: use global zustand manage systemFeatures and share between all pages 2025-03-14 19:10:03 +08:00
GareArc 8ba969f67d fix: add ci workflow 2025-03-13 17:15:11 -04:00
GareArc 6844d59371 fix: add default title name 2025-03-13 17:07:45 -04:00
GareArc fe5529db85 Trigger workflow 2025-03-13 17:04:13 -04:00
GareArc d89034d913 feat: add application title 2025-03-13 15:49:04 -04:00
NFish 360fbeb108 fix: update email template, add application_title 2025-03-13 17:28:49 +08:00
GareArc e7c2fa1cfa fix: remove system feature is_branding 2025-03-12 10:48:58 -04:00
Hash BrownandNFish 735f09d977 fix: build failed due to getPrevChatList no longer exists (#13383) 2025-03-12 10:22:33 +08:00
GareArc f83a5e3e49 fix: wrong type 2025-03-11 07:46:48 -04:00
NFish 01a8d4efcc fix: remove dify from invite template 2025-03-11 19:25:30 +08:00
GareArc fdb1e649d4 feat: add branding support 2025-03-11 07:14:52 -04:00
NFish 0856792a57 fix: add email templates that are no brands or logo 2025-03-11 16:03:15 +08:00
crazywoola 0e33a3aa5f chore: add ci 2025-02-19 14:34:36 +08:00
Hash Brownandcrazywoola d3895bcd6b revert 2025-02-19 14:32:28 +08:00
Hash Brownandcrazywoola eeb390650b fix: build failed 2025-02-19 14:32:28 +08:00
-LAN-andGitHub ca19bd31d4 chore(*): Bump version to 0.15.3 (#13308)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 15:20:05 +08:00
-LAN-andGitHub 413dfd5628 feat: add completion mode and context size options for LLM configuration (#13325)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 15:08:53 +08:00
-LAN-andGitHub f9515901cc fix: Azure AI Foundry model cannot be used in the workflow (#13323)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 14:52:57 +08:00
呆萌闷油瓶andGitHub 3f42fabff8 chore:improve thinking display for llm from xinference and ollama pro… (#13318) 2025-02-07 14:29:29 +08:00
-LAN-andGitHub 1caa578771 chore(*): Update style of thinking (#13319)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 14:06:35 +08:00
b7c11c1818 Fix the problem of Workflow terminates after parallel tasks execution, merge node not triggered (#12498)
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
2025-02-07 13:56:08 +08:00
非法操作andGitHub 3eb3db0663 chore: refactor the OpenAICompatible and improve thinking display (#13299) 2025-02-07 13:28:46 +08:00
-LAN-andGitHub be46f32056 fix(credits): require model name equals (#13314)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 13:28:17 +08:00
sinoandGitHub 6e5c915f96 feat(model): add deepseek-r1 for openrouter (#13312) 2025-02-07 12:39:13 +08:00
-LAN-andGitHub 04d13a8116 feat(credits): Allow to configure model-credit mapping (#13274)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-07 11:01:31 +08:00
KemalandGitHub e638ede3f2 Update README_TR.md (#13294) 2025-02-07 09:11:39 +08:00
Riddhimaan-SenapatiandGitHub 2348abe4bf feat: added a couple of models not defined in vertex ai, that were already … (#13296) 2025-02-07 09:11:25 +08:00
呆萌闷油瓶andGitHub f7e7a399d9 feat:add think tag display for xinference deepseek r1 (#13291) 2025-02-06 22:04:58 +08:00
le0zhandGitHub ba91f34636 fix: incorrect transferMethod assignment for remote file (#13286) 2025-02-06 19:32:21 +08:00
16865d43a8 feat: add deepseek models for volcengine provider (#13283)
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
2025-02-06 18:20:03 +08:00
呆萌闷油瓶andGitHub 0d13aee15c feat:add deepseek r1 think display for ollama provider (#13272) 2025-02-06 15:32:10 +08:00
Wu TianweiandGitHub 49b4144ffd fix: add dataset edit permissions (#13223) 2025-02-06 14:26:16 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
186e2d972e chore(deps): bump katex from 0.16.10 to 0.16.21 in /web (#13270)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-02-06 13:27:07 +08:00
40dd63ecef Upgrade oracle models (#13174)
Co-authored-by: engchina <atjapan2015@gmail.com>
2025-02-06 13:24:27 +08:00
-LAN-andGitHub 6d66d6da15 feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-06 13:03:19 +08:00
03ec3513f3 Fix bug large data no render (#12683)
Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com>
2025-02-06 13:00:04 +08:00
-LAN-andGitHub 87763fc234 feat(model_providers): Support deepseek for Azure AI Foundry (#13267)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-06 12:45:48 +08:00
JasonVVandGitHub f6c44cae2e feat(model): add gemini-2.0 model (#13266) 2025-02-06 12:28:59 +08:00
xheandGitHub da2ee04fce fix: correct linewrap think display in generic openai api (#13260)
Signed-off-by: xhe <xw897002528@gmail.com>
2025-02-06 10:53:08 +08:00
JasonVVandGitHub 7673c36af3 feat(model): add gemini-2.0-flash-thinking-exp-01-21 (#13230) 2025-02-06 10:01:00 +08:00
Riddhimaan-SenapatiandGitHub 9457b2af2f feat: added models :gemini 2.0 flash 001 and gemini 2.0 pro exp 02-05 (#13247) 2025-02-06 09:58:39 +08:00
k-zakuandGitHub 7203991032 feat: add parameter "reasoning_effort" and Openai o3-mini (#13243) 2025-02-06 09:29:48 +08:00
xheandGitHub 5a685f7156 feat: add think display for volcengine and generic openapi (#13234)
Signed-off-by: xhe <xw897002528@gmail.com>
2025-02-06 09:24:40 +08:00
Riddhimaan-SenapatiandGitHub a6a25030ad fix: updated _position.yaml to include the latest model already integ… (#13245) 2025-02-06 09:21:51 +08:00
Riddhimaan-SenapatiandGitHub 00458a31d5 feat: added deepseek r1 and v3 to siliconflow (#13238) 2025-02-05 21:59:18 +08:00
-LAN-andGitHub c6ddf6d6cc feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-05 19:15:29 +08:00
34b21b3065 feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129)
Co-authored-by: crazywoola <427733928@qq.com>
2025-02-05 17:04:45 +08:00
Bowen LiangandGitHub 8fbb355cd2 chore: squash system dependencies installation steps (#13206) 2025-02-05 16:42:53 +08:00
HQideaandGitHub e8b3b7e578 Fix new variables in the conversation opener would override prompt_variables (#13191) 2025-02-05 16:16:00 +08:00
-LAN-andGitHub 59ca44f493 chore(model_runtime): Move deepseek ahead in the providers list. (#13197)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-05 16:08:28 +08:00
Bowen LiangandGitHub 9e1457c2c3 fix: mypy checks violation in AzureBlobStorage (#13215) 2025-02-05 15:56:23 +08:00
te-chanandGitHub fac83e14bc Use DefaultAzureCredential for managed identity in azure blob extention (#11559) 2025-02-05 13:43:43 +08:00
Nam VuandGitHub a97cec57e4 fix: SSRF proxy file descriptor leak in concurrent requests (#13108) 2025-02-05 13:10:27 +08:00
Riddhimaan-SenapatiandGitHub 38c10b47d3 Feat: add linkedin to readme (#13203) 2025-02-05 12:27:58 +08:00
MaFee921andGitHub 1a2523fd15 feat: bedrock_endpoint_url (#12838) 2025-02-05 12:24:24 +08:00
Warren ChenandGitHub 03243cb422 Modify params for bedrock retrieve generate (#13182) 2025-02-05 12:17:42 +08:00
Bowen LiangandGitHub 2ad7ee0344 chore: add tests for build docker image when dockerfile changed (#10732) 2025-02-05 11:40:22 +08:00
55ce3618ce fix: Dollar Sign Handling in Markdown (#13178)
Co-authored-by: crazywoola <427733928@qq.com>
2025-02-05 11:00:56 +08:00
TechnoHouseandGitHub e9e34c1ab2 Install apt dependencies using bookworm source, consistent with base image. Remove unnecessary, error-prone pins (#13176) 2025-02-05 10:07:22 +08:00
-LAN-andGitHub d4c916b496 chore(pyproject): Add type stubs into pyproject.toml (#13145)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-04 12:01:28 +08:00
Obada KhaliliandGitHub 8fbc9c9342 Solve circular dependency issue between workflow/constants.ts file and default.ts file (#13165) 2025-02-04 09:26:01 +08:00
aplioandGitHub 1b6fd9dfe8 fix: set indexing technique from dataset during update-by-text (#13155) 2025-02-03 11:06:03 +08:00
非法操作andGitHub 304467e3f5 fix: not install libmagic raise error (#13146) 2025-02-03 11:05:20 +08:00
Kei YAMAZAKIandGitHub 7452032d81 add azure openai api version 2024-12-01-preview (#13135) 2025-02-03 11:04:20 +08:00
aplioandGitHub 87e2048f1b nitpick: fix small typos in template.en.mdx (#13156) 2025-02-03 11:03:11 +08:00
Nam VuandGitHub d876084392 chore: upgrade libldap2 (#13158) 2025-02-03 11:02:14 +08:00
非法操作andGitHub 840729afa5 feat: the think tag display of siliconflow's deepseek r1 (#13153) 2025-02-02 21:55:13 +08:00
Obada KhaliliandGitHub 941ad03f3c pass model and cost so that langfuse can show cost (#13117) 2025-02-02 15:27:27 +08:00
aplioandGitHub d73d191f99 feature. add feat to modify metadata via dataset api (#13116) 2025-02-02 15:27:12 +08:00
Masashi TomookaandGitHub c2664e0283 chore: fix wrong VectorType match case (#13123) 2025-02-02 15:26:59 +08:00
-LAN-andGitHub ee61cede4e test(huggingface_hub): Skip the failed test temporarily. (#13142)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-02 14:47:26 +08:00
-LAN-andGitHub b47669b80b fix: deduct LLM quota after processing invoke result (#13075)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-02-02 12:05:11 +08:00
c0d0c63592 feat: switch to chat messages before regenerated (#11301)
Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com>
2025-01-31 13:05:10 +08:00
Yingchun LaiandGitHub b09c39c8dc refactor: avoid to use extra space when finding model by name (#13043) 2025-01-30 15:08:29 +08:00
heysztandGitHub b4b09ddc3c add tongyi qwen2.5-14b/7b-instruct-1m model (#13089) 2025-01-29 11:58:01 +08:00
Ademílson TonatoandGitHub d0a21086bd refactor: Update Firecrawl API parameters and default settings (#13082) 2025-01-29 11:21:05 +08:00
Yingchun LaiandGitHub d44882c1b5 refactor: reduce duplciate code by inheritance (#13073) 2025-01-28 10:52:01 +08:00
Yingchun LaiandGitHub 23c68efa2d fix: fix the formatter is not applied on log file (#12704) 2025-01-28 10:49:58 +08:00
JasonandGitHub 560c5de1b7 Fixed Novita AI color and added DeepSeek R1 model (#13074) 2025-01-28 10:38:54 +08:00
5d91dbd000 Set default LOG_LEVEL to INFO for celery workers and beat (#13066)
Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com>
2025-01-27 17:09:41 +08:00
heysztandGitHub 6c31ee36cd fix qwen-vl blocking mode (#13052) 2025-01-27 11:35:23 +08:00
jiandanfengandGitHub edc29780ed fix: "Model schema not found" error only in agents (#12655) (#12760) 2025-01-27 11:33:13 +08:00
yjc980121andGitHub aad7e4dd1c fix:Improve MIME type detection for remote URL uploads using python-magic (#12693) 2025-01-27 11:33:03 +08:00
Xin ZhangandGitHub a6a727e8a4 feat: add inner API to create workspace without requiring email (#13021) 2025-01-26 15:36:56 +08:00
NFishandGitHub d1fc65fabc fix: adjust iteration node dark style (#13051) 2025-01-26 11:19:41 +08:00
JasonandGitHub d4be5ef9de Update Novita AI predefined models (#13045) 2025-01-26 09:25:29 +08:00
Shun MiyazawaandGitHub 1374be5a31 fix: Unexpected tag creation when pressing enter during tag conversion (#13041) 2025-01-25 19:30:26 +08:00
Warren ChenandGitHub b2bbc28580 support bedrock kb: retrieve and generate (#13027) 2025-01-25 17:28:06 +08:00
非法操作andGitHub 59b3e672aa feat: add agent thinking content display of deepseek R1 (#12949) 2025-01-24 20:13:42 +08:00
IWAI, MasaharuandGitHub a2f8bce8f5 chore: add Japanese translation: model_providers/bedrock (#13016) 2025-01-24 18:43:33 +08:00
Yueh-Po Peng (Yabi)andGitHub a2b9adb3a2 Change typo in translation (#13004) 2025-01-24 13:48:21 +08:00
IWAI, MasaharuandGitHub 28067640b5 fix: wrong zh_Hans translation: Ohio (#13006) 2025-01-24 13:41:20 +08:00
da67916843 feat: add glm-4-air-0111 (#12997)
Co-authored-by: lowell <lowell.hu@zkteco.in>
2025-01-24 10:04:46 +08:00
zxhlyhandGitHub e54ce479ad Feat/prompt editor dark theme (#12976) 2025-01-23 16:20:00 +08:00
6024d8a42d refactor: Update Firecrawl to use v1 API (#12574)
Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com>
2025-01-23 11:14:48 +08:00
JoelandGitHub f565f08aa0 fix: get property of string type variable caused page crash (#12969) 2025-01-23 11:02:29 +08:00
fd4afe09f8 fix: tools translate search (#12950)
Co-authored-by: lowell <lowell.hu@zkteco.in>
2025-01-22 19:27:02 +08:00
jiandanfengandGitHub dd0904f95c feat: add giteeAI risk control identification. (#12946) 2025-01-22 19:26:25 +08:00
4c3076f2a4 feat: add pg vector index (#12338)
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
2025-01-22 17:07:18 +08:00
-LAN-andGitHub 1e73f63ff8 chore: update version to 0.15.2 in packaging and docker configurations (#12940)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-22 16:40:44 +08:00
sinoandGitHub d167d5b1be feat(ark): support doubao 1.5 series of models (#12935) 2025-01-22 15:25:57 +08:00
le0zhandGitHub 71fa14f791 fix: resolve clipboard.writeText failure under HTTP protocol (#12936) 2025-01-22 15:18:23 +08:00
zxhlyhandGitHub 8dd1873e76 feat: workflow note dark theme (#12932) 2025-01-22 14:22:33 +08:00
-LAN-andGitHub f91f5c7401 fix(batch_create_segment_to_index_task): count max_position in memory. (#12929) 2025-01-22 13:39:02 +08:00
Bowen LiangandGitHub c62b7cc679 chore(build): bump poetry from 1.x to 2.x (#12369) 2025-01-22 13:38:24 +08:00
JyongandGitHub 3ee213ddca add milvus full text search setting (#12930) 2025-01-22 13:36:39 +08:00
8429877b02 fix: Agent is configured for ReAct inference mode, an error is reported when viewing the agent log (#12920)
Co-authored-by: crazywoola <427733928@qq.com>
2025-01-22 13:20:32 +08:00
EricPanandGitHub 05a0faff6a fix: app token's last_used_at can't be updated when last_used_at is null (#12770) 2025-01-22 11:01:45 +08:00
JoelandGitHub e09f6e4987 feat: support config chunk length by env (#12925) 2025-01-22 10:43:40 +08:00
jiandanfengandGitHub e23f4b0265 feat: add gemini-2.0-flash-thinking-exp-01-21 (#12924) 2025-01-22 10:14:37 +08:00
Shun MiyazawaandGitHub f582d4a13e feat: Add ability to change profile avatar (#12642) 2025-01-22 10:11:31 +08:00
2f41bd495d fix:Fix a bug that returns null when the passed path is a file. (#12775)
Co-authored-by: 刘江波 <jiangbo721@163.com>
2025-01-22 10:10:03 +08:00
JyongandGitHub 162a8c4393 fix update segment keyword with same content (#12908) 2025-01-21 19:19:32 +08:00
3d1ce4c53f bug: fixed bedrock rerank bug (#12774)
Co-authored-by: hobo.l <hobo.l@binance.com>
2025-01-21 19:09:36 +08:00
JoelandGitHub 6db3ae9b8e chore: remove webapp ga (#12909) 2025-01-21 18:38:33 +08:00
6d0cb9dc33 fix: variable panel scrollable (#12769)
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
2025-01-21 17:50:42 +08:00
k-zakuandGitHub 46e95e8309 fix: OpenAI o1 Bad Request Error (#12839) 2025-01-21 15:29:13 +08:00
JasonVVandGitHub a7b9375877 Update deepseek model configuration (#12899) 2025-01-21 15:28:11 +08:00
0c6a8a130e fix: external dataset hit test display issue(#12564) (#12612)
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
2025-01-21 14:31:45 +08:00
JasonVVandGitHub 9903f1e703 add deepseek-reasoner (#12898) 2025-01-21 12:40:58 +08:00
Bowen LiangandGitHub 6fad719e42 chore(fix): Invalid quotes for using Array[String] in HTTP request node as JSON body (#12761) 2025-01-21 10:38:44 +08:00
jiandanfengandGitHub 9aaee8ee47 fix: Issues related to the deletion of conversation_id (#12488) (#12665) 2025-01-21 10:25:35 +08:00
Bowen LiangandGitHub 166221d784 chore(lint): fix quotes for f-string formatting by bumping ruff to 0.9.x (#12702) 2025-01-21 10:12:29 +08:00
Ding JiatongandGitHub 925d69a2ee feat:Support Minimax-Text-01 (#12763) 2025-01-21 10:08:53 +08:00
rayshaw001andGitHub 5ff08e241a fix: serply credential check query might return empty records (#12784) 2025-01-21 09:38:56 +08:00
kurokoboandGitHub 3defd24087 feat: allow updating chunk settings for the existing documents (#12833) 2025-01-21 09:25:40 +08:00
jiandanfengandGitHub 9d86147d20 fix: SparkLite API Auth error (#12781) (#12790) 2025-01-20 22:21:21 +08:00
jiandanfengandGitHub 80801ac4ab fix: "parmas" spelling mistake. (#12875) 2025-01-20 22:18:30 +08:00
Xu SongandGitHub 210926cd91 Fix suggested_question_prompt (#12738) 2025-01-20 22:16:30 +08:00
海狸大師andGitHub 677a69deed fix(i18n): correct typo in zh-Hant translation (#12852) 2025-01-20 22:15:41 +08:00
8dfdee21ce chore: fix chinese translation for 'recall' (#12772)
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
2025-01-20 22:15:26 +08:00
jiandanfengandGitHub 6ea77ab4cd fix: DeepSeek API Error with response format active (text and json_object) (#12747) 2025-01-20 22:04:18 +08:00
Hiroshi FujitaandGitHub e3c996688d feat: enhance credential extraction logic based on configurate method (#12853) 2025-01-20 21:59:22 +08:00
Wu TianweiandGitHub bc3a570dda fix: Fix rerank model switching issue (#12721)
ok
2025-01-14 15:42:45 +08:00
0800021a2d chore: translate i18n files (#12708)
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
2025-01-14 13:35:23 +08:00
KVOJJJinandGitHub 435eddd867 Feat: copyright modification (#12707) 2025-01-14 10:00:57 +08:00
-LAN-andGitHub 6e0fb055d1 chore: bump version to 0.15.1 (#12690)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-13 19:21:06 +08:00
euxandGitHub 1e9ac7ffeb feat: add table of contents to Knowledge API doc (#12688) 2025-01-13 18:31:43 +08:00
Warren ChenandGitHub b4873ecb43 [fix] support feature restore (#12563) 2025-01-13 18:29:06 +08:00
1859d57784 api tool support multiple env url (#12249)
Co-authored-by: mabo <mabo@aeyes.ai>
2025-01-13 17:49:30 +08:00
Boris FeldandGitHub 69d58fbb50 Add new integration with Opik Tracking tool (#11501) 2025-01-13 17:41:44 +08:00
-LAN-andGitHub cb34991663 fix: add type hints for App model and improve error handling in audio services (#12677)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-13 15:55:16 +08:00
-LAN-andGitHub c700364e1c fix: Update variable handling in VariableAssignerNode and clean up app_dsl_service (#12672)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-13 15:54:26 +08:00
JyongandGitHub 9a6b1dc3a1 Revert "Feat/new saas billing" (#12673) 2025-01-13 15:17:43 +08:00
Kevin9703andGitHub 54b5b80a07 fix(workflow): fix answer node stream processing in conditional branches (#12510) 2025-01-13 14:54:21 +08:00
831459b895 fix: ruff with statements (#12578)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-01-13 09:55:55 +08:00
yihongandGitHub 4e101604c3 fix: ruff check for True if ... else (#12576)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-13 09:38:48 +08:00
ChuehnoneandGitHub a6455269f0 chore: Adjust translations to align with Taiwanese Mandarin conventions (#12633) 2025-01-13 09:12:43 +08:00
cd257b91c5 Fix pandas indexing method for knowledge base imports (#12637) (#12638)
Co-authored-by: CN-P5 <heibai2006@qq.com>
2025-01-13 09:06:59 +08:00
JyongandGitHub d8f57bf899 Feat/new saas billing (#12591) 2025-01-12 14:50:46 +08:00
gakkiyomiandGitHub 989fb11fd7 improve the readability of the function generate_api_key (#12552) 2025-01-09 21:30:17 +08:00
140965b738 chore: translate i18n files (#12543)
Co-authored-by: WTW0313 <30284043+WTW0313@users.noreply.github.com>
2025-01-09 20:30:06 +08:00
JyongandGitHub 14ee51aead Feat/add knowledge include all filter (#12537) 2025-01-09 20:21:25 +08:00
2e97ba5700 fix: Add datasets list access control and fix datasets config display issue (#12533)
Co-authored-by: nite-knite <nkCoding@gmail.com>
2025-01-09 17:44:11 +08:00
NFishandGitHub f549d53b68 fix: sum costs return error value on overview page (#12534) 2025-01-09 16:04:14 +08:00
crazywoolaandGitHub a085ad4719 feat: show workflow running status (#12531) 2025-01-09 15:36:13 +08:00
lotsikandGitHub f230a9232e fix: Parsing OpenAPI spec for external tools (#12518) (#12530) 2025-01-09 15:30:43 +08:00
e84bf35e2a fix: same chunk insert deadlock (#12502)
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
2025-01-09 15:16:41 +08:00
euxandGitHub 20f090537f feat: add GET upload file API endpoint to dataset service api (#11899) 2025-01-09 14:52:09 +08:00
Gen SatoandGitHub dbe7a7c4fd Fix: Add a INFO-level log when fallback to gpt2tokenizer (#12508) 2025-01-09 14:37:46 +08:00
NFishandGitHub b7a4e3903e fix: add last_refresh_time to track the validity of is_other_tab_refreshing (#12517) 2025-01-09 10:40:45 +08:00
Hiroshi FujitaandGitHub b4c1c2f731 fix: Reverse sync docker-compose-template.yaml (#12509) 2025-01-09 10:21:22 +08:00
kurokoboandGitHub 1b940e7daa feat: add ci job to test template for docker compose (#12514) 2025-01-09 00:04:58 +08:00
非法操作andGitHub f4ee50a7ad chore: improve app doc (#12490) 2025-01-08 18:37:12 +08:00
JyongandGitHub bee32d960a fix #12453 #12482 (#12495) 2025-01-08 18:26:05 +08:00
YoungLHandGitHub 040a3b782c FEAT: support milvus to full text search (#11430)
Signed-off-by: YoungLH <974840768@qq.com>
2025-01-08 17:39:53 +08:00
非法操作andGitHub d649037c3e feat: support single run doc extractor node (#11318) 2025-01-08 15:20:15 +08:00
-LAN-andGitHub 0a49d3dd52 fix: tiktoken cannot be loaded without internet (#12478)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-08 14:49:44 +08:00
Yingchun LaiandGitHub 53bb37b749 fix: fix the incorrect plaintext file key when saving (#10429) 2025-01-08 12:52:45 +08:00
Hiroshi FujitaandGitHub d2586278d6 Feat elasticsearch japanese (#12194) 2025-01-08 12:35:41 +08:00
Wu TianweiandGitHub 6635c393e9 fix: adjust opacity for model selector based on readonly state (#12472) 2025-01-08 12:11:45 +08:00
crazywoolaandGitHub 6222179a57 Revert "fix:deepseek tool call not working correctly" (#12463) 2025-01-08 10:50:34 +08:00
JyongandGitHub 05bda6f38d add tidb on qdrant redis lock (#12462) 2025-01-08 08:55:44 +08:00
Hiroshi FujitaandGitHub 4295cefeb1 fix: allow fallback to remote_url when url is not provided (#12455) 2025-01-07 22:33:25 +08:00
非法操作andGitHub 67228c9b26 fix: url with variable not work (#12452) 2025-01-07 21:55:51 +08:00
JyongandGitHub fd2bfff023 remove knowledge admin role (#12450) 2025-01-07 21:30:23 +08:00
InfinitnetandGitHub 4e6c86341d Add 'document' feature to Sonnet 3.5 through OpenRouter (#12444) 2025-01-07 19:51:38 +08:00
2a14c67edc Fix #12448 - update bedrock retrieve tool, support hybrid search type and re… (#12446)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2025-01-07 19:51:23 +08:00
-LAN-andGitHub c236f05f4b chore: bump version to 0.15.0 (#12297)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-07 18:05:14 +08:00
-LAN-andGitHub 0eeacdc80c refactor: enhance API token validation with session locking and last used timestamp update (#12426)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-07 18:04:41 +08:00
41f39bf3fc Fix newline characters in tables during document parsing (#12112)
Co-authored-by: hisir <admin@qq.com>
2025-01-07 17:26:24 +08:00
呆萌闷油瓶andGitHub 9677144015 fix:deepseek tool call not working correctly (#12437) 2025-01-07 17:25:38 +08:00
SiliconFlow, IncandGitHub 15797c556f add fish-speech-1.5 from siliconflow (#12425) 2025-01-07 15:27:34 +08:00
-LAN-andGitHub acacf35a2a chore(docker/.env.example): Add TOP_K_MAX_VALUE to the .env.example… (#12422)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-07 14:51:16 +08:00
-LAN-andGitHub d3f5b1cbb6 refactor: use tiktoken for token calculation (#12416)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-07 13:32:30 +08:00
whyandGitHub 196ed8101b fix: [PromptEditorHeightResizeWrap] Bug #12410 (#12406) 2025-01-07 12:21:54 +08:00
SiliconFlow, IncandGitHub dc650c5368 Fixes #12414: Add cheaper model and long context model for Qwen2.5-72B-Instruct from siliconflow (#12415) 2025-01-07 11:28:24 +08:00
Alex ChenandGitHub 2bb521b135 Support TTS and Speech2Text for Model Provider GPUStack (#12381) 2025-01-07 09:42:11 +08:00
409cc7d9b0 mark deprecated models in siliconflow #12399 (#12405)
Co-authored-by: crazywoola <427733928@qq.com>
2025-01-07 09:08:58 +08:00
yihongandGitHub fe26be2312 fix: http method can be upper case and lower case close #11877 (#12401)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-06 20:35:53 +08:00
Wu TianweiandGitHub 34519de3b7 fix: enhance chunk list management with new invalidation keys and imp… (#12396)
ok
2025-01-06 18:22:16 +08:00
Warren ChenandGitHub 147d578922 [Fix] revert sagemaker llm to support model hub (#12378) 2025-01-06 18:01:45 +08:00
JyongandGitHub 9c317b64c3 sandbox doesn't provide auto disable log (#12388) 2025-01-06 15:57:13 +08:00
JoelandGitHub 3b8f6233b0 feat: support config top max value by env (#12375) 2025-01-06 10:38:14 +08:00
Hash BrownandGitHub 455b0cd696 chore: chat app textarea auto focus (#12366) 2025-01-05 21:25:00 +08:00
euxandGitHub 1fa66405c5 feat: support configuration of refresh token expiration by environment variable (#12335) 2025-01-04 11:56:44 +08:00
WoodandGitHub b680a85b57 fix: resolve issue with the opening statement generated by the AutomaticRes component failing to sync between states. (#12349) 2025-01-04 11:56:11 +08:00
WoodandGitHub 682ebc5f64 Fix the issue where TextGeneration component does not correctly clear input data. (#12351) 2025-01-04 11:55:55 +08:00
WoodandGitHub b8ba39dfae Bugfix/style and i18n fixes (#12350) 2025-01-04 11:52:13 +08:00
WoodandGitHub 6c9e6a3a5a fix: fix issue with chat-input-area clearing during Responding state. (#12352) 2025-01-04 11:51:35 +08:00
70698024f5 fix: empty delete bug (#12339)
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
2025-01-03 20:46:39 +08:00
6df17a334c fix: Update the API call address for the text_embedding model (#12342)
Co-authored-by: 方程 <fangcheng@oschina.cn>
2025-01-03 19:19:17 +08:00
a5fb59b17f fix: Encode Chinese characters with Unicode before querying to match the Unicode encoded Chinese characters in the db (#12337)
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
2025-01-03 19:12:48 +08:00
-LAN-andGitHub 7ed6485f86 refactor: streamline initialization of application_generate_entity and task_state in task pipeline classes (#12326)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-03 18:41:44 +08:00
Timmy-webandGitHub 478150e850 chore: fix typo in zh-Hant localization (#12329) 2025-01-03 17:38:30 +08:00
jifeiandGitHub 3c2e30f348 fix: #12143 support streaming mode content start with "data:" (#12171) 2025-01-03 16:33:37 +08:00
JyongandGitHub b873e6349c add child chunk preview number limit (#12309) 2025-01-03 16:14:27 +08:00
Shun MiyazawaandGitHub 2b1a32fd9c feat: Add filter to show only apps created by the user (#11968) 2025-01-03 15:38:36 +08:00
Nam VuandGitHub a2105634a4 chore: change app card layout follow by #10847 (#12317) 2025-01-03 14:16:17 +08:00
7c71bd7be7 doc: Added explanation of chunk_overlap to knowledge API (#12247)
Co-authored-by: crazywoola <427733928@qq.com>
2025-01-03 10:02:17 +08:00
丹枫染秋色andGitHub 7c1961e618 feat: Add response format support to GLM-4 (#12252) 2025-01-03 09:38:50 +08:00
baeddd4d15 feat:Add support for stop parameter in hunyuan model #12313 (#12315)
Co-authored-by: xander-art <xander-art@gmail.com>
2025-01-03 09:15:04 +08:00
-LAN-andGitHub 6f5a8a33d9 refactor: replace gevent threadpool with ProcessPoolExecutor in GPT2Tokenizer (#12316)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-03 09:13:18 +08:00
-LAN-andGitHub 52b2559a14 fix(app.py): if condition (#12314)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-03 01:36:23 +08:00
yihongandGitHub 3d150c30a7 fix: utcfromtimestamp is Deprecated change to new api (#12120)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-02 18:52:36 +08:00
Wu TianweiandGitHub e58e573f3e fix: add full doc mode preview length limit (#12310)
ok
2025-01-02 18:36:49 +08:00
-LAN-andGitHub 375aa38f5d fix: improve content decoding in AppDslService (#12304)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-02 16:54:46 +08:00
-LAN-GitHubCopilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
0e6317678f Fix code scanning alert no. 111: Incomplete URL substring sanitization (#12305)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2025-01-02 16:52:43 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
e7dffcd0f6 chore(deps): bump aiohttp from 3.10.5 to 3.10.11 in /api (#12303)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-01-02 16:42:47 +08:00
Hanqing ZhaoandGitHub 065304d175 Modify jp translation (#12292) 2025-01-02 16:28:27 +08:00
-LAN-andGitHub 15f43dd326 chore(deps): update yarl version from 1.9.4 to 1.18.3 (#12302)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-02 16:26:47 +08:00
09d759d196 fix: Fix parent child retrieval issues (#12206)
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
2025-01-02 16:07:21 +08:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
68757950ce chore(deps): bump jinja2 from 3.1.4 to 3.1.5 in /api (#12300)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-01-02 16:04:10 +08:00
-LAN-andGitHub 3c45bdf18a fix: disable gevent in debug mode for better compatibility with JetBrains Python debugger (#12299)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-02 15:59:30 +08:00
Yingchun LaiandGitHub c135967e59 refactor: simplify some exception catch code (#12246) 2025-01-02 14:25:12 +08:00
Sean SunandGitHub f71af7c2a8 fix: DocumentAddByFileApi miss data_source_type field but there is a mandatory value check (#12273) 2025-01-02 14:24:15 +08:00
5b01eb9437 chore: translate i18n files (#12208)
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
2025-01-02 10:04:43 +08:00
呆萌闷油瓶andGitHub 2e716f80d2 fix:The chart of average interaction counts per conversation show not… (#12199) 2025-01-02 10:02:56 +08:00
d7c0bc8c23 feat: Add response format support for openai compat models (#12240)
Co-authored-by: Gio Gutierrez <giovannygutierrez@gmail.com>
2025-01-02 09:59:34 +08:00
yihongandGitHub f30bf08580 fix: close #12215 for yi special case (#12222)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-02 09:58:34 +08:00
-LAN-andGitHub a640803fc9 fix(models): use bigint on workflow_runs.total_tokens (#12279)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-02 09:49:34 +08:00
Warren ChenandGitHub 9954ddb780 [Fix] modify sagemaker llm (#12274) 2025-01-02 09:49:11 +08:00
非法操作andGitHub b218df6920 fix: draft run single node can't get env variable (#12266) 2025-01-01 13:31:44 +08:00
-LAN-andGitHub 5b6950e545 fix: improve error handling in NotionOAuth for block parent page ID r… (#12268)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 17:03:26 +08:00
-LAN-andGitHub c7911c7130 fix: improve JSON parsing error handling in Executor class (#12265)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 17:03:07 +08:00
-LAN-andGitHub 62f792ea14 fix: ensure workflow_run_id is always set and improve handling in Wor… (#12264)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 17:02:44 +08:00
-LAN-andGitHub 6a85960605 feat: implement asynchronous token counting in GPT2Tokenizer (#12239)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 17:02:08 +08:00
-LAN-andGitHub 63a0b8ba79 feat: integrate psycogreen for gevent compatibility in PostgreSQL (#12253)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 14:45:59 +08:00
-LAN-andGitHub 634b382a3d fix: enhance ToolEngineInvokeError to include meta information (#12238)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 14:01:24 +08:00
fbf5deda21 fix(env): docker compose variable interpolation issue for COMPOSE_PRO… (#12093)
Co-authored-by: Han Kyaw <hankyaw@Hans-MBP.lan>
2024-12-31 13:46:51 +08:00
-LAN-andGitHub d4b848272e fix: apply gevent threading patch early and ensure unique workflow node execution IDs (#12196)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 11:42:51 +08:00
Warren ChenandGitHub fc29f2003e translate comments (#12234) 2024-12-31 00:36:03 +08:00
Bowen LiangandGitHub ab469aa07d feat: support opening new tab in markdown button (#12213) 2024-12-30 22:27:25 +08:00
Warren ChenandGitHub 562450751f [Fix] Fix sagemaker_chinese_toxicity_detector and bedrock_retrieve (#12227) 2024-12-30 22:26:04 +08:00
NFishandGitHub adacd01f82 Feat: support account deletion (#10008) 2024-12-30 13:39:26 +08:00
74d3320519 feat: account delete (#11829)
Co-authored-by: NFish <douxc512@gmail.com>
2024-12-30 11:33:42 +08:00
BenjaminandGitHub 309a15d1ba fix: update api libldap package version in Dockerfile for security im… (#12195) 2024-12-29 21:36:07 +08:00
Kazuki TakamatsuandGitHub bcef11681d fix: default value of google storage sa to empty (#12188) 2024-12-29 17:32:55 +08:00
-LAN-andGitHub 8d15c8cfbf fix: improve error handling in NotionExtractor data fetching (#12182)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-29 11:53:09 +08:00
Hiroshi FujitaandGitHub 716bb8574d fix: rendering errors occur when displaying hit test results in full text search (#12191) 2024-12-29 11:52:45 +08:00
呆萌闷油瓶andGitHub bd2fec4813 fix: #12125 (#12184) 2024-12-29 11:52:12 +08:00
非法操作andGitHub ead4b34127 fix: test run custom tool raise error (#12178) 2024-12-28 17:51:22 +08:00
Bowen LiangandGitHub 72ae414da4 chore(lint): correct allowed-unused-imports settings for cleanup unused imports in tests (#11922) 2024-12-28 01:19:31 +08:00
Warren ChenandGitHub 4c9618be3f [fix] modify en-US (#12169) 2024-12-27 21:18:34 +08:00
901028f1e8 [feat] Support Multi-Version Workflows (#11990)
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-12-27 21:05:06 +08:00
Hanqing ZhaoandGitHub adfbfc1255 Modify translation for error branch and update for the parent-child f… (#12127) 2024-12-27 20:55:33 +08:00
非法操作andGitHub b66c03dfe9 fix: workflow_as_tool output files raise error (#12061) 2024-12-27 20:33:28 +08:00
2a909e634b feat: support Ernie-lite-pro-128k (#12161)
Co-authored-by: bigfish49 <bigfish49@126.com>
2024-12-27 20:23:46 +08:00
AkaraChenandGitHub 9d86056f1c chore: add cursor pointer for option card (#12119) 2024-12-27 20:20:25 +08:00
非法操作andGitHub 309fd76ddf fix: comfyui output image's format (#12121) 2024-12-27 20:20:03 +08:00
yihongandGitHub a3293b154e fix: type is wrong issue (#12165)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-12-27 18:33:53 +08:00
NFishandGitHub eb8963a673 fix: workflow page throw warning: Attempts to access this ref will fail (#12166) 2024-12-27 18:33:15 +08:00
NFishandGitHub 89ce9a5db2 Fix: avatar dropdown keyboard navigation (#12155) 2024-12-27 18:10:36 +08:00
JyongandGitHub f4f2567105 owner and admin have all permission of knowledge base (#12157) 2024-12-27 17:09:13 +08:00
JyongandGitHub 5a3fe61f2a disable all chunks status when disable document (#12149) 2024-12-27 17:08:44 +08:00
-LAN-andGitHub 55c327ffcb fix: handle case where member is not found in role update API (#12156)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-27 16:04:50 +08:00
0fdb39f1c3 Fix: The topk parameter doesn't work in sagemaker rerank tool (#12150)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-12-27 14:42:25 +08:00
-LAN-andGitHub dae1b5a619 fix: import jieba.analyse (#12133)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-27 11:37:55 +08:00
-LAN-andGitHub 26b5680913 fix: improve merge branch node ID checks in graph engine (#12128)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-26 23:33:45 +08:00
a2855fa24a chore: translate i18n files (#12118)
Co-authored-by: laipz8200 <16485841+laipz8200@users.noreply.github.com>
2024-12-26 23:33:11 +08:00
9c3cf7b69a fix: 12050 (#12109)
Co-authored-by: Xiaoba Yu <xb1823725853@gmail.com>
2024-12-26 23:32:54 +08:00
-LAN-andGitHub be7877f526 fix: enhance file upload error handling and update base error class (#12132)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-26 23:31:29 +08:00
-LAN-andGitHub e765d8e69e fix: validate imported_version type in AppDslService (#12135)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-26 23:26:55 +08:00
-LAN-andGitHub 4bd8df1fd3 fix: update MessageService.create_feedback to use keyword arguments f… (#12134)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-26 23:26:44 +08:00
-LAN-andGitHub 4e76f2fc44 fix: add properties to retrieve created by account and end user in Wo… (#12129)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-26 19:50:45 +08:00
JyongandGitHub cf00ee42f5 send knowledge base auto disable notification (#12126) 2024-12-26 18:14:08 +08:00
Bowen LiangandGitHub 886758d2be fix: typo in clean messages periodical task's logging (#12090) 2024-12-26 17:42:32 +08:00
yihongandGitHub 8339d2c7c9 fix: issue #11868 bring old logic back (#12100)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-12-26 12:17:55 +08:00
JyongandGitHub 811e4bd0cf fix unstructured setting (#12116) 2024-12-26 12:08:36 +08:00
49feff082f feat: parent child retrieval (#12106)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-12-26 12:01:51 +08:00
yihongandGitHub efdd54a670 fix: issue #12068 by test is answer in the ids (#12105)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-12-26 10:31:05 +08:00
1134 changed files with 39284 additions and 16646 deletions
+1 -1
View File
@@ -8,7 +8,7 @@ inputs:
poetry-version:
description: Poetry version to set up
required: true
default: '1.8.4'
default: '2.0.1'
poetry-lockfile:
description: Path to the Poetry lockfile to restore cache from
required: true
+7 -9
View File
@@ -42,25 +42,23 @@ jobs:
run: poetry install -C api --with dev
- name: Check dependencies in pyproject.toml
run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
run: poetry run -P api bash dev/pytest/pytest_artifacts.sh
- name: Run Unit tests
run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh
- name: Run ModelRuntime
run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
run: poetry run -P api bash dev/pytest/pytest_model_runtime.sh
- name: Run dify config tests
run: poetry run -C api python dev/pytest/pytest_config_tests.py
run: poetry run -P api python dev/pytest/pytest_config_tests.py
- name: Run Tool
run: poetry run -C api bash dev/pytest/pytest_tools.sh
run: poetry run -P api bash dev/pytest/pytest_tools.sh
- name: Run mypy
run: |
pushd api
poetry run python -m mypy --install-types --non-interactive .
popd
poetry run -C api python -m mypy --install-types --non-interactive .
- name: Set up dotenvs
run: |
@@ -80,4 +78,4 @@ jobs:
ssrf_proxy
- name: Run Workflow
run: poetry run -C api bash dev/pytest/pytest_workflow.sh
run: poetry run -P api bash dev/pytest/pytest_workflow.sh
+1
View File
@@ -5,6 +5,7 @@ on:
branches:
- "main"
- "deploy/dev"
- "e-260"
release:
types: [published]
+29
View File
@@ -0,0 +1,29 @@
name: Deploy Enterprise
permissions:
contents: read
on:
workflow_run:
workflows: ["Build and Push API & Web"]
branches:
- "deploy/enterprise"
types:
- completed
jobs:
deploy:
runs-on: ubuntu-latest
if: |
github.event.workflow_run.conclusion == 'success' &&
github.event.workflow_run.head_branch == 'deploy/enterprise'
steps:
- name: Deploy to server
uses: appleboy/ssh-action@v0.1.8
with:
host: ${{ secrets.ENTERPRISE_SSH_HOST }}
username: ${{ secrets.ENTERPRISE_SSH_USER }}
password: ${{ secrets.ENTERPRISE_SSH_PASSWORD }}
script: |
${{ vars.ENTERPRISE_SSH_SCRIPT || secrets.ENTERPRISE_SSH_SCRIPT }}
+47
View File
@@ -0,0 +1,47 @@
name: Build docker image
on:
pull_request:
branches:
- "main"
paths:
- api/Dockerfile
- web/Dockerfile
concurrency:
group: docker-build-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
build-docker:
runs-on: ubuntu-latest
strategy:
matrix:
include:
- service_name: "api-amd64"
platform: linux/amd64
context: "api"
- service_name: "api-arm64"
platform: linux/arm64
context: "api"
- service_name: "web-amd64"
platform: linux/amd64
context: "web"
- service_name: "web-arm64"
platform: linux/arm64
context: "web"
steps:
- name: Set up QEMU
uses: docker/setup-qemu-action@v3
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Build Docker Image
uses: docker/build-push-action@v6
with:
push: false
context: "{{defaultContext}}:${{ matrix.context }}"
platforms: ${{ matrix.platform }}
cache-from: type=gha
cache-to: type=gha,mode=max
+30 -3
View File
@@ -38,12 +38,12 @@ jobs:
if: steps.changed-files.outputs.any_changed == 'true'
run: |
poetry run -C api ruff --version
poetry run -C api ruff check ./api
poetry run -C api ruff format --check ./api
poetry run -C api ruff check ./
poetry run -C api ruff format --check ./
- name: Dotenv check
if: steps.changed-files.outputs.any_changed == 'true'
run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example
- name: Lint hints
if: failure()
@@ -82,6 +82,33 @@ jobs:
if: steps.changed-files.outputs.any_changed == 'true'
run: yarn run lint
docker-compose-template:
name: Docker Compose Template
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Check changed files
id: changed-files
uses: tj-actions/changed-files@v45
with:
files: |
docker/generate_docker_compose
docker/.env.example
docker/docker-compose-template.yaml
docker/docker-compose.yaml
- name: Generate Docker Compose
if: steps.changed-files.outputs.any_changed == 'true'
run: |
cd docker
./generate_docker_compose
- name: Check for changes
if: steps.changed-files.outputs.any_changed == 'true'
run: git diff --exit-code
superlinter:
name: SuperLinter
+1 -1
View File
@@ -70,4 +70,4 @@ jobs:
tidb
- name: Test Vector Stores
run: poetry run -C api bash dev/pytest/pytest_vdb.sh
run: poetry run -P api bash dev/pytest/pytest_vdb.sh
+4
View File
@@ -0,0 +1,4 @@
{
"MD024": false,
"MD013": false
}
+45
View File
@@ -0,0 +1,45 @@
# Changelog
All notable changes to Dify will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [0.15.8] - 2025-05-30
### Added
- Added gunicorn keepalive setting (#19537)
### Fixed
- Fixed database configuration to allow DB_EXTRAS to set search_path via options (#16a4f77)
- Fixed frontend third-party package security issues (#19655)
- Updated dependencies: huggingface-hub (~0.16.4 to ~0.31.0), transformers (~4.35.0 to ~4.39.0), and resend (~0.7.0 to ~2.9.0) (#19563)
- Downgrade boto3 from 1.36 to 1.35 (#19736)
## [0.15.7] - 2025-04-27
### Added
- Added support for GPT-4.1 in model providers (#18912)
- Added support for Amazon Bedrock DeepSeek-R1 model (#18908)
- Added support for Amazon Bedrock Claude Sonnet 3.7 model (#18788)
- Refined version compatibility logic in app DSL service
### Fixed
- Fixed issue with creating apps from template categories (#18807, #18868)
- Fixed DSL version check when creating apps from explore templates (#18872, #18878)
## [0.15.6] - 2025-04-22
### Security
- Fixed clickjacking vulnerability (#18552)
- Fixed reset password security issue (#18366)
- Updated reset password token when email code verification succeeds (#18362)
### Fixed
- Fixed Vertex AI Gemini 2.0 Flash 001 schema (#18405)
+3
View File
@@ -25,6 +25,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="seguir en LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="suivre sur LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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="X(Twitter)でフォロー"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="LinkedIn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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -25,6 +25,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3
View File
@@ -22,6 +22,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="follow on LinkedIn"></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">
+3 -6
View File
@@ -21,6 +21,9 @@
<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="X(Twitter)'da takip et"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="LinkedIn'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">
@@ -62,8 +65,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
**3. Prompt IDE**:
Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.
@@ -150,8 +151,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
## Dify'ı Kullanma
- **Cloud </br>**
İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
-
Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.
- **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
@@ -177,8 +176,6 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
>- RAM >= 4GB
</br>
İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:
```bash
+3
View File
@@ -21,6 +21,9 @@
<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 X(Twitter)"></a>
<a href="https://www.linkedin.com/company/langgenius/" target="_blank">
<img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
alt="theo dõi trên LinkedIn"></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">
+7 -1
View File
@@ -23,6 +23,9 @@ FILES_ACCESS_TIMEOUT=300
# Access token expiration time in minutes
ACCESS_TOKEN_EXPIRE_MINUTES=60
# Refresh token expiration time in days
REFRESH_TOKEN_EXPIRE_DAYS=30
# celery configuration
CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
@@ -427,4 +430,7 @@ CREATE_TIDB_SERVICE_JOB_ENABLED=false
# Maximum number of submitted thread count in a ThreadPool for parallel node execution
MAX_SUBMIT_COUNT=100
# Lockout duration in seconds
LOGIN_LOCKOUT_DURATION=86400
LOGIN_LOCKOUT_DURATION=86400
# Prevent Clickjacking
ALLOW_EMBED=false
+4 -2
View File
@@ -53,10 +53,12 @@ ignore = [
"FURB152", # math-constant
"UP007", # non-pep604-annotation
"UP032", # f-string
"UP045", # non-pep604-annotation-optional
"B005", # strip-with-multi-characters
"B006", # mutable-argument-default
"B007", # unused-loop-control-variable
"B026", # star-arg-unpacking-after-keyword-arg
"B903", # class-as-data-structure
"B904", # raise-without-from-inside-except
"B905", # zip-without-explicit-strict
"N806", # non-lowercase-variable-in-function
@@ -85,11 +87,11 @@ ignore = [
]
"tests/*" = [
"F811", # redefined-while-unused
"F401", # unused-import
]
[lint.pyflakes]
extend-generics = [
allowed-unused-imports = [
"_pytest.monkeypatch",
"tests.integration_tests",
"tests.unit_tests",
]
+13 -12
View File
@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
WORKDIR /app/api
# Install Poetry
ENV POETRY_VERSION=1.8.4
ENV POETRY_VERSION=2.0.1
# if you located in China, you can use aliyun mirror to speed up
# RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -48,16 +48,18 @@ ENV TZ=UTC
WORKDIR /app/api
RUN apt-get update \
&& apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
# if you located in China, you can use aliyun mirror to speed up
# && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
&& 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 expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
# install a chinese font to support the use of tools like matplotlib
&& apt-get install -y fonts-noto-cjk \
RUN \
apt-get update \
# Install dependencies
&& apt-get install -y --no-install-recommends \
# basic environment
curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
# For Security
expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
# install a chinese font to support the use of tools like matplotlib
fonts-noto-cjk \
# install libmagic to support the use of python-magic guess MIMETYPE
libmagic1 \
&& apt-get autoremove -y \
&& rm -rf /var/lib/apt/lists/*
@@ -76,7 +78,6 @@ COPY . /app/api/
COPY docker/entrypoint.sh /entrypoint.sh
RUN chmod +x /entrypoint.sh
ARG COMMIT_SHA
ENV COMMIT_SHA=${COMMIT_SHA}
+1 -1
View File
@@ -79,5 +79,5 @@
2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
```bash
poetry run -C api bash dev/pytest/pytest_all_tests.sh
poetry run -P api bash dev/pytest/pytest_all_tests.sh
```
+20 -9
View File
@@ -1,12 +1,8 @@
from libs import version_utils
# preparation before creating app
version_utils.check_supported_python_version()
import os
import sys
def is_db_command():
import sys
if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
return True
return False
@@ -18,10 +14,25 @@ if is_db_command():
app = create_migrations_app()
else:
from app_factory import create_app
from libs import threadings_utils
# It seems that JetBrains Python debugger does not work well with gevent,
# so we need to disable gevent in debug mode.
# If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
from gevent import monkey # type: ignore
threadings_utils.apply_gevent_threading_patch()
# gevent
monkey.patch_all()
from grpc.experimental import gevent as grpc_gevent # type: ignore
# grpc gevent
grpc_gevent.init_gevent()
import psycogreen.gevent # type: ignore
psycogreen.gevent.patch_psycopg()
from app_factory import create_app
app = create_app()
celery = app.extensions["celery"]
+20 -2
View File
@@ -146,7 +146,7 @@ class EndpointConfig(BaseSettings):
)
CONSOLE_WEB_URL: str = Field(
description="Base URL for the console web interface," "used for frontend references and CORS configuration",
description="Base URL for the console web interface,used for frontend references and CORS configuration",
default="",
)
@@ -488,6 +488,11 @@ class AuthConfig(BaseSettings):
default=60,
)
REFRESH_TOKEN_EXPIRE_DAYS: PositiveFloat = Field(
description="Expiration time for refresh tokens in days",
default=30,
)
LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
default=86400,
@@ -601,7 +606,7 @@ class RagEtlConfig(BaseSettings):
UNSTRUCTURED_API_KEY: Optional[str] = Field(
description="API key for Unstructured.io service",
default=None,
default="",
)
SCARF_NO_ANALYTICS: Optional[str] = Field(
@@ -667,6 +672,11 @@ class IndexingConfig(BaseSettings):
default=4000,
)
CHILD_CHUNKS_PREVIEW_NUMBER: PositiveInt = Field(
description="Maximum number of child chunks to preview",
default=50,
)
class MultiModalTransferConfig(BaseSettings):
MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
@@ -765,6 +775,13 @@ class LoginConfig(BaseSettings):
)
class AccountConfig(BaseSettings):
ACCOUNT_DELETION_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
description="Duration in minutes for which a account deletion token remains valid",
default=5,
)
class FeatureConfig(
# place the configs in alphabet order
AppExecutionConfig,
@@ -792,6 +809,7 @@ class FeatureConfig(
WorkflowNodeExecutionConfig,
WorkspaceConfig,
LoginConfig,
AccountConfig,
# hosted services config
HostedServiceConfig,
CeleryBeatConfig,
+35 -2
View File
@@ -1,9 +1,40 @@
from typing import Optional
from pydantic import Field, NonNegativeInt
from pydantic import Field, NonNegativeInt, computed_field
from pydantic_settings import BaseSettings
class HostedCreditConfig(BaseSettings):
HOSTED_MODEL_CREDIT_CONFIG: str = Field(
description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
default="",
)
def get_model_credits(self, model_name: str) -> int:
"""
Get credit value for a specific model name.
Returns 1 if model is not found in configuration (default credit).
:param model_name: The name of the model to search for
:return: The credit value for the model
"""
if not self.HOSTED_MODEL_CREDIT_CONFIG:
return 1
try:
credit_map = dict(
item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
)
# Search for matching model pattern
for pattern, credit in credit_map.items():
if pattern.strip() == model_name:
return int(credit)
return 1 # Default quota if no match found
except (ValueError, AttributeError):
return 1 # Return default quota if parsing fails
class HostedOpenAiConfig(BaseSettings):
"""
Configuration for hosted OpenAI service
@@ -181,7 +212,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
"""
HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
description="Mode for fetching app templates: remote, db, or builtin default to remote,",
default="remote",
)
@@ -202,5 +233,7 @@ class HostedServiceConfig(
HostedZhipuAIConfig,
# moderation
HostedModerationConfig,
# credit config
HostedCreditConfig,
):
pass
+17 -3
View File
@@ -1,5 +1,5 @@
from typing import Any, Literal, Optional
from urllib.parse import quote_plus
from urllib.parse import parse_qsl, quote_plus
from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
from pydantic_settings import BaseSettings
@@ -166,14 +166,28 @@ class DatabaseConfig(BaseSettings):
default=False,
)
@computed_field
@computed_field # type: ignore[misc]
@property
def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
# Parse DB_EXTRAS for 'options'
db_extras_dict = dict(parse_qsl(self.DB_EXTRAS))
options = db_extras_dict.get("options", "")
# Always include timezone
timezone_opt = "-c timezone=UTC"
if options:
# Merge user options and timezone
merged_options = f"{options} {timezone_opt}"
else:
merged_options = timezone_opt
connect_args = {"options": merged_options}
return {
"pool_size": self.SQLALCHEMY_POOL_SIZE,
"max_overflow": self.SQLALCHEMY_MAX_OVERFLOW,
"pool_recycle": self.SQLALCHEMY_POOL_RECYCLE,
"pool_pre_ping": self.SQLALCHEMY_POOL_PRE_PING,
"connect_args": {"options": "-c timezone=UTC"},
"connect_args": connect_args,
}
@@ -33,3 +33,9 @@ class MilvusConfig(BaseSettings):
description="Name of the Milvus database to connect to (default is 'default')",
default="default",
)
MILVUS_ENABLE_HYBRID_SEARCH: bool = Field(
description="Enable hybrid search features (requires Milvus >= 2.5.0). Set to false for compatibility with "
"older versions",
default=True,
)
+1 -1
View File
@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="0.14.2",
default="0.15.8",
)
COMMIT_SHA: str = Field(
+27
View File
@@ -1,12 +1,32 @@
import mimetypes
import os
import platform
import re
import urllib.parse
import warnings
from collections.abc import Mapping
from typing import Any
from uuid import uuid4
import httpx
try:
import magic
except ImportError:
if platform.system() == "Windows":
warnings.warn(
"To use python-magic guess MIMETYPE, you need to run `pip install python-magic-bin`", stacklevel=2
)
elif platform.system() == "Darwin":
warnings.warn("To use python-magic guess MIMETYPE, you need to run `brew install libmagic`", stacklevel=2)
elif platform.system() == "Linux":
warnings.warn(
"To use python-magic guess MIMETYPE, you need to run `sudo apt-get install libmagic1`", stacklevel=2
)
else:
warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
magic = None # type: ignore
from pydantic import BaseModel
from configs import dify_config
@@ -47,6 +67,13 @@ def guess_file_info_from_response(response: httpx.Response):
# If guessing fails, use Content-Type from response headers
mimetype = response.headers.get("Content-Type", "application/octet-stream")
# Use python-magic to guess MIME type if still unknown or generic
if mimetype == "application/octet-stream" and magic is not None:
try:
mimetype = magic.from_buffer(response.content[:1024], mime=True)
except magic.MagicException:
pass
extension = os.path.splitext(filename)[1]
# Ensure filename has an extension
+1 -1
View File
@@ -56,7 +56,7 @@ class InsertExploreAppListApi(Resource):
app = App.query.filter(App.id == args["app_id"]).first()
if not app:
raise NotFound(f'App \'{args["app_id"]}\' is not found')
raise NotFound(f"App '{args['app_id']}' is not found")
site = app.site
if not site:
+27 -14
View File
@@ -2,30 +2,28 @@ import uuid
from typing import cast
from flask_login import current_user # type: ignore
from flask_restful import Resource, inputs, marshal, marshal_with, reqparse # type: ignore
from flask_restful import (Resource, inputs, marshal, # type: ignore
marshal_with, reqparse)
from sqlalchemy import select
from sqlalchemy.orm import Session
from werkzeug.exceptions import BadRequest, Forbidden, abort
from controllers.console import api
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import (
account_initialization_required,
cloud_edition_billing_resource_check,
enterprise_license_required,
setup_required,
)
from controllers.console.wraps import (account_initialization_required,
cloud_edition_billing_resource_check,
enterprise_license_required,
setup_required)
from core.ops.ops_trace_manager import OpsTraceManager
from extensions.ext_database import db
from fields.app_fields import (
app_detail_fields,
app_detail_fields_with_site,
app_pagination_fields,
)
from fields.app_fields import (app_detail_fields, app_detail_fields_with_site,
app_pagination_fields)
from libs.login import login_required
from models import Account, App
from services.app_dsl_service import AppDslService, ImportMode
from services.app_service import AppService
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
ALLOW_CREATE_APP_MODES = ["chat", "agent-chat", "advanced-chat", "workflow", "completion"]
@@ -57,16 +55,27 @@ class AppListApi(Resource):
)
parser.add_argument("name", type=str, location="args", required=False)
parser.add_argument("tag_ids", type=uuid_list, location="args", required=False)
parser.add_argument("is_created_by_me", type=inputs.boolean, location="args", required=False)
args = parser.parse_args()
# get app list
app_service = AppService()
app_pagination = app_service.get_paginate_apps(current_user.current_tenant_id, args)
app_pagination = app_service.get_paginate_apps(current_user.id, current_user.current_tenant_id, args)
if not app_pagination:
return {"data": [], "total": 0, "page": 1, "limit": 20, "has_more": False}
return marshal(app_pagination, app_pagination_fields)
if FeatureService.get_system_features().webapp_auth.enabled:
app_ids = [str(app.id) for app in app_pagination.items]
res = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids=app_ids)
if len(res) != len(app_ids):
raise BadRequest("Invalid app id in webapp auth")
for app in app_pagination.items:
if str(app.id) in res:
app.access_mode = res[str(app.id)].access_mode
return marshal(app_pagination, app_pagination_fields), 200
@setup_required
@login_required
@@ -110,6 +119,10 @@ class AppApi(Resource):
app_model = app_service.get_app(app_model)
if FeatureService.get_system_features().webapp_auth.enabled:
app_setting = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id=str(app_model.id))
app_model.access_mode = app_setting.access_mode
return app_model
@setup_required
+5 -1
View File
@@ -14,6 +14,8 @@ from fields.app_fields import app_import_fields
from libs.login import login_required
from models import Account
from services.app_dsl_service import AppDslService, ImportStatus
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
class AppImportApi(Resource):
@@ -56,7 +58,9 @@ class AppImportApi(Resource):
app_id=args.get("app_id"),
)
session.commit()
if result.app_id and FeatureService.get_system_features().webapp_auth.enabled:
# update web app setting as private
EnterpriseService.WebAppAuth.update_app_access_mode(result.app_id, "private")
# Return appropriate status code based on result
status = result.status
if status == ImportStatus.FAILED.value:
+6 -2
View File
@@ -22,7 +22,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from libs.login import login_required
from models.model import AppMode
from models import App, AppMode
from services.audio_service import AudioService
from services.errors.audio import (
AudioTooLargeServiceError,
@@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
@login_required
@account_initialization_required
@get_app_model
def post(self, app_model):
def post(self, app_model: App):
from werkzeug.exceptions import InternalServerError
try:
@@ -98,9 +98,13 @@ class ChatMessageTextApi(Resource):
and app_model.workflow.features_dict
):
text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
if text_to_speech is None:
raise ValueError("TTS is not enabled")
voice = args.get("voice") or text_to_speech.get("voice")
else:
try:
if app_model.app_model_config is None:
raise ValueError("AppModelConfig not found")
voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
except Exception:
voice = None
+2 -3
View File
@@ -20,7 +20,6 @@ from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpErr
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import (
AppInvokeQuotaExceededError,
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
@@ -76,7 +75,7 @@ class CompletionMessageApi(Resource):
raise ProviderModelCurrentlyNotSupportError()
except InvokeError as e:
raise CompletionRequestError(e.description)
except (ValueError, AppInvokeQuotaExceededError) as e:
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
@@ -141,7 +140,7 @@ class ChatMessageApi(Resource):
raise InvokeRateLimitHttpError(ex.description)
except InvokeError as e:
raise CompletionRequestError(e.description)
except (ValueError, AppInvokeQuotaExceededError) as e:
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
+1 -2
View File
@@ -273,8 +273,7 @@ FROM
messages m
ON c.id = m.conversation_id
WHERE
c.override_model_configs IS NULL
AND c.app_id = :app_id"""
c.app_id = :app_id"""
arg_dict = {"tz": account.timezone, "app_id": app_model.id}
timezone = pytz.timezone(account.timezone)
+28 -2
View File
@@ -2,7 +2,7 @@ import json
import logging
from flask import abort, request
from flask_restful import Resource, marshal_with, reqparse # type: ignore
from flask_restful import Resource, inputs, marshal_with, reqparse # type: ignore
from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
import services
@@ -14,7 +14,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from factories import variable_factory
from fields.workflow_fields import workflow_fields
from fields.workflow_fields import workflow_fields, workflow_pagination_fields
from fields.workflow_run_fields import workflow_run_node_execution_fields
from libs import helper
from libs.helper import TimestampField, uuid_value
@@ -440,6 +440,31 @@ class WorkflowConfigApi(Resource):
}
class PublishedAllWorkflowApi(Resource):
@setup_required
@login_required
@account_initialization_required
@get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
@marshal_with(workflow_pagination_fields)
def get(self, app_model: App):
"""
Get published workflows
"""
if not current_user.is_editor:
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument("page", type=inputs.int_range(1, 99999), required=False, default=1, location="args")
parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
args = parser.parse_args()
page = args.get("page")
limit = args.get("limit")
workflow_service = WorkflowService()
workflows, has_more = workflow_service.get_all_published_workflow(app_model=app_model, page=page, limit=limit)
return {"items": workflows, "page": page, "limit": limit, "has_more": has_more}
api.add_resource(DraftWorkflowApi, "/apps/<uuid:app_id>/workflows/draft")
api.add_resource(WorkflowConfigApi, "/apps/<uuid:app_id>/workflows/draft/config")
api.add_resource(AdvancedChatDraftWorkflowRunApi, "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
@@ -454,6 +479,7 @@ api.add_resource(
WorkflowDraftRunIterationNodeApi, "/apps/<uuid:app_id>/workflows/draft/iteration/nodes/<string:node_id>/run"
)
api.add_resource(PublishedWorkflowApi, "/apps/<uuid:app_id>/workflows/publish")
api.add_resource(PublishedAllWorkflowApi, "/apps/<uuid:app_id>/workflows")
api.add_resource(DefaultBlockConfigsApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
api.add_resource(
DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"
+12
View File
@@ -53,3 +53,15 @@ 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
class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
error_code = "email_code_account_deletion_rate_limit_exceeded"
description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
code = 429
class EmailPasswordResetLimitError(BaseHTTPException):
error_code = "email_password_reset_limit"
description = "Too many failed password reset attempts. Please try again in 24 hours."
code = 429
+29 -10
View File
@@ -6,26 +6,28 @@ from flask_restful import Resource, reqparse # type: ignore
from constants.languages import languages
from controllers.console import api
from controllers.console.auth.error import (
EmailCodeError,
InvalidEmailError,
InvalidTokenError,
PasswordMismatchError,
)
from controllers.console.error import AccountNotFound, EmailSendIpLimitError
from controllers.console.wraps import setup_required
from controllers.console.auth.error import (EmailCodeError, InvalidEmailError,
InvalidTokenError,
PasswordMismatchError)
from controllers.console.error import (AccountInFreezeError, AccountNotFound,
EmailSendIpLimitError)
from controllers.console.wraps import (email_password_login_enabled,
setup_required)
from events.tenant_event import tenant_was_created
from extensions.ext_database import db
from libs.helper import email, extract_remote_ip
from libs.password import hash_password, valid_password
from models.account import Account
from services.account_service import AccountService, TenantService
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.errors.account import AccountRegisterError
from services.errors.workspace import (WorkSpaceNotAllowedCreateError,
WorkspacesLimitExceededError)
from services.feature_service import FeatureService
class ForgotPasswordSendEmailApi(Resource):
@setup_required
@email_password_login_enabled
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
@@ -57,6 +59,7 @@ class ForgotPasswordSendEmailApi(Resource):
class ForgotPasswordCheckApi(Resource):
@setup_required
@email_password_login_enabled
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=str, required=True, location="json")
@@ -76,11 +79,20 @@ class ForgotPasswordCheckApi(Resource):
if args["code"] != token_data.get("code"):
raise EmailCodeError()
return {"is_valid": True, "email": token_data.get("email")}
# Verified, revoke the first token
AccountService.revoke_reset_password_token(args["token"])
# Refresh token data by generating a new token
_, new_token = AccountService.generate_reset_password_token(
user_email, code=args["code"], additional_data={"phase": "reset"}
)
return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
class ForgotPasswordResetApi(Resource):
@setup_required
@email_password_login_enabled
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("token", type=str, required=True, nullable=False, location="json")
@@ -99,6 +111,9 @@ class ForgotPasswordResetApi(Resource):
if reset_data is None:
raise InvalidTokenError()
# Must use token in reset phase
if reset_data.get("phase", "") != "reset":
raise InvalidTokenError()
AccountService.revoke_reset_password_token(token)
@@ -129,6 +144,10 @@ class ForgotPasswordResetApi(Resource):
)
except WorkSpaceNotAllowedCreateError:
pass
except AccountRegisterError as are:
raise AccountInFreezeError()
except WorkspacesLimitExceededError:
pass
return {"result": "success"}
+40 -10
View File
@@ -5,6 +5,7 @@ from flask import request
from flask_restful import Resource, reqparse # type: ignore
import services
from configs import dify_config
from constants.languages import languages
from controllers.console import api
from controllers.console.auth.error import (
@@ -16,17 +17,21 @@ from controllers.console.auth.error import (
)
from controllers.console.error import (
AccountBannedError,
AccountInFreezeError,
AccountNotFound,
EmailSendIpLimitError,
NotAllowedCreateWorkspace,
WorkspacesLimitExceeded,
)
from controllers.console.wraps import setup_required
from controllers.console.wraps import email_password_login_enabled, setup_required
from events.tenant_event import tenant_was_created
from libs.helper import email, extract_remote_ip
from libs.password import valid_password
from models.account import Account
from services.account_service import AccountService, RegisterService, TenantService
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.billing_service import BillingService
from services.errors.account import AccountRegisterError
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
from services.feature_service import FeatureService
@@ -34,6 +39,7 @@ class LoginApi(Resource):
"""Resource for user login."""
@setup_required
@email_password_login_enabled
def post(self):
"""Authenticate user and login."""
parser = reqparse.RequestParser()
@@ -44,6 +50,9 @@ class LoginApi(Resource):
parser.add_argument("language", type=str, required=False, default="en-US", location="json")
args = parser.parse_args()
if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(args["email"]):
raise AccountInFreezeError()
is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
if is_login_error_rate_limit:
raise EmailPasswordLoginLimitError()
@@ -80,10 +89,15 @@ class LoginApi(Resource):
# SELF_HOSTED only have one workspace
tenants = TenantService.get_join_tenants(account)
if len(tenants) == 0:
return {
"result": "fail",
"data": "workspace not found, please contact system admin to invite you to join in a workspace",
}
system_features = FeatureService.get_system_features()
if system_features.is_allow_create_workspace and not system_features.license.workspaces.is_available():
raise WorkspacesLimitExceeded()
else:
return {
"result": "fail",
"data": "workspace not found, please contact system admin to invite you to join in a workspace",
}
token_pair = AccountService.login(account=account, ip_address=extract_remote_ip(request))
AccountService.reset_login_error_rate_limit(args["email"])
@@ -103,6 +117,7 @@ class LogoutApi(Resource):
class ResetPasswordSendEmailApi(Resource):
@setup_required
@email_password_login_enabled
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
@@ -113,8 +128,10 @@ class ResetPasswordSendEmailApi(Resource):
language = "zh-Hans"
else:
language = "en-US"
account = AccountService.get_user_through_email(args["email"])
try:
account = AccountService.get_user_through_email(args["email"])
except AccountRegisterError as are:
raise AccountInFreezeError()
if account is None:
if FeatureService.get_system_features().is_allow_register:
token = AccountService.send_reset_password_email(email=args["email"], language=language)
@@ -142,8 +159,11 @@ class EmailCodeLoginSendEmailApi(Resource):
language = "zh-Hans"
else:
language = "en-US"
try:
account = AccountService.get_user_through_email(args["email"])
except AccountRegisterError as are:
raise AccountInFreezeError()
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)
@@ -177,10 +197,16 @@ class EmailCodeLoginApi(Resource):
raise EmailCodeError()
AccountService.revoke_email_code_login_token(args["token"])
account = AccountService.get_user_through_email(user_email)
try:
account = AccountService.get_user_through_email(user_email)
except AccountRegisterError as are:
raise AccountInFreezeError()
if account:
tenant = TenantService.get_join_tenants(account)
if not tenant:
workspaces = FeatureService.get_system_features().license.workspaces
if not workspaces.is_available():
raise WorkspacesLimitExceeded()
if not FeatureService.get_system_features().is_allow_create_workspace:
raise NotAllowedCreateWorkspace()
else:
@@ -196,6 +222,10 @@ class EmailCodeLoginApi(Resource):
)
except WorkSpaceNotAllowedCreateError:
return NotAllowedCreateWorkspace()
except AccountRegisterError as are:
raise AccountInFreezeError()
except WorkspacesLimitExceededError:
raise WorkspacesLimitExceeded()
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()}
+3 -1
View File
@@ -16,7 +16,7 @@ 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.account import AccountNotFoundError, AccountRegisterError
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
from services.feature_service import FeatureService
@@ -99,6 +99,8 @@ class OAuthCallback(Resource):
f"{dify_config.CONSOLE_WEB_URL}/signin"
"?message=Workspace not found, please contact system admin to invite you to join in a workspace."
)
except AccountRegisterError as e:
return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message={e.description}")
# Check account status
if account.status == AccountStatus.BANNED.value:
+7 -6
View File
@@ -52,12 +52,12 @@ class DatasetListApi(Resource):
# provider = request.args.get("provider", default="vendor")
search = request.args.get("keyword", default=None, type=str)
tag_ids = request.args.getlist("tag_ids")
include_all = request.args.get("include_all", default="false").lower() == "true"
if ids:
datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
else:
datasets, total = DatasetService.get_datasets(
page, limit, current_user.current_tenant_id, current_user, search, tag_ids
page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
)
# check embedding setting
@@ -457,7 +457,7 @@ class DatasetIndexingEstimateApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -619,9 +619,7 @@ class DatasetRetrievalSettingApi(Resource):
vector_type = dify_config.VECTOR_STORE
match vector_type:
case (
VectorType.MILVUS
| VectorType.RELYT
| VectorType.PGVECTOR
VectorType.RELYT
| VectorType.TIDB_VECTOR
| VectorType.CHROMA
| VectorType.TENCENT
@@ -640,10 +638,12 @@ class DatasetRetrievalSettingApi(Resource):
| VectorType.MYSCALE
| VectorType.ORACLE
| VectorType.ELASTICSEARCH
| VectorType.ELASTICSEARCH_JA
| VectorType.PGVECTOR
| VectorType.TIDB_ON_QDRANT
| VectorType.LINDORM
| VectorType.COUCHBASE
| VectorType.MILVUS
):
return {
"retrieval_method": [
@@ -683,6 +683,7 @@ class DatasetRetrievalSettingMockApi(Resource):
| VectorType.MYSCALE
| VectorType.ORACLE
| VectorType.ELASTICSEARCH
| VectorType.ELASTICSEARCH_JA
| VectorType.COUCHBASE
| VectorType.PGVECTOR
| VectorType.LINDORM
@@ -257,7 +257,8 @@ class DatasetDocumentListApi(Resource):
parser.add_argument("original_document_id", type=str, required=False, location="json")
parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
parser.add_argument("embedding_model", type=str, required=False, nullable=True, location="json")
parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, location="json")
parser.add_argument(
"doc_language", type=str, default="English", required=False, nullable=False, location="json"
)
@@ -309,7 +310,7 @@ class DatasetInitApi(Resource):
@cloud_edition_billing_resource_check("vector_space")
def post(self):
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
parser = reqparse.RequestParser()
@@ -349,8 +350,7 @@ class DatasetInitApi(Resource):
)
except InvokeAuthorizationError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -525,8 +525,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
return response.model_dump(), 200
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -685,7 +684,7 @@ class DocumentProcessingApi(DocumentResource):
document = self.get_document(dataset_id, document_id)
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
if action == "pause":
@@ -749,7 +748,7 @@ class DocumentMetadataApi(DocumentResource):
doc_metadata = req_data.get("doc_metadata")
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
if doc_type is None or doc_metadata is None:
@@ -122,7 +122,7 @@ class DatasetDocumentSegmentListApi(Resource):
segment_ids = request.args.getlist("segment_id")
# The role of the current user in the ta table must be admin or owner
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
@@ -149,7 +149,7 @@ class DatasetDocumentSegmentApi(Resource):
# check user's model setting
DatasetService.check_dataset_model_setting(dataset)
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
@@ -168,8 +168,7 @@ class DatasetDocumentSegmentApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -203,7 +202,7 @@ class DatasetDocumentSegmentAddApi(Resource):
document = DocumentService.get_document(dataset_id, document_id)
if not document:
raise NotFound("Document not found.")
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
# check embedding model setting
if dataset.indexing_technique == "high_quality":
@@ -217,8 +216,7 @@ class DatasetDocumentSegmentAddApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -267,8 +265,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -280,7 +277,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
@@ -323,7 +320,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin or owner
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
@@ -368,9 +365,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
result = []
for index, row in df.iterrows():
if document.doc_form == "qa_model":
data = {"content": row[0], "answer": row[1]}
data = {"content": row.iloc[0], "answer": row.iloc[1]}
else:
data = {"content": row[0]}
data = {"content": row.iloc[0]}
result.append(data)
if len(result) == 0:
raise ValueError("The CSV file is empty.")
@@ -423,7 +420,7 @@ class ChildChunkAddApi(Resource):
).first()
if not segment:
raise NotFound("Segment not found.")
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
# check embedding model setting
if dataset.indexing_technique == "high_quality":
@@ -437,8 +434,7 @@ class ChildChunkAddApi(Resource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -524,7 +520,7 @@ class ChildChunkAddApi(Resource):
if not segment:
raise NotFound("Segment not found.")
# The role of the current user in the ta table must be admin, owner, or editor
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
@@ -574,7 +570,7 @@ class ChildChunkUpdateApi(Resource):
if not child_chunk:
raise NotFound("Child chunk not found.")
# The role of the current user in the ta table must be admin or owner
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
@@ -618,7 +614,7 @@ class ChildChunkUpdateApi(Resource):
if not child_chunk:
raise NotFound("Child chunk not found.")
# The role of the current user in the ta table must be admin or owner
if not current_user.is_editor:
if not current_user.is_dataset_editor:
raise Forbidden()
try:
DatasetService.check_dataset_permission(dataset, current_user)
+21
View File
@@ -46,6 +46,18 @@ class NotAllowedCreateWorkspace(BaseHTTPException):
code = 400
class WorkspaceMembersLimitExceeded(BaseHTTPException):
error_code = "limit_exceeded"
description = "Unable to add member because the maximum workspace's member limit was exceeded"
code = 400
class WorkspacesLimitExceeded(BaseHTTPException):
error_code = "limit_exceeded"
description = "Unable to create workspace because the maximum workspace limit was exceeded"
code = 400
class AccountBannedError(BaseHTTPException):
error_code = "account_banned"
description = "Account is banned."
@@ -92,3 +104,12 @@ class UnauthorizedAndForceLogout(BaseHTTPException):
error_code = "unauthorized_and_force_logout"
description = "Unauthorized and force logout."
code = 401
class AccountInFreezeError(BaseHTTPException):
error_code = "account_in_freeze"
code = 400
description = (
"This email account has been deleted within the past 30 days"
"and is temporarily unavailable for new account registration."
)
@@ -18,7 +18,11 @@ from controllers.console.explore.error import NotChatAppError, NotCompletionAppE
from controllers.console.explore.wraps import InstalledAppResource
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.errors.error import (
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from extensions.ext_database import db
from libs import helper
@@ -32,7 +32,7 @@ class ConversationListApi(InstalledAppResource):
pinned = None
if "pinned" in args and args["pinned"] is not None:
pinned = True if args["pinned"] == "true" else False
pinned = args["pinned"] == "true"
try:
with Session(db.engine) as session:
+6
View File
@@ -23,3 +23,9 @@ class AppSuggestedQuestionsAfterAnswerDisabledError(BaseHTTPException):
error_code = "app_suggested_questions_after_answer_disabled"
description = "Function Suggested questions after answer disabled."
code = 403
class AppAccessDeniedError(BaseHTTPException):
error_code = "access_denied"
description = "App access denied."
code = 403
@@ -1,20 +1,26 @@
import logging
from datetime import UTC, datetime
from typing import Any
from flask import request
from flask_login import current_user # type: ignore
from flask_restful import Resource, inputs, marshal_with, reqparse # type: ignore
from flask_restful import (Resource, inputs, marshal_with, # type: ignore
reqparse)
from sqlalchemy import and_
from werkzeug.exceptions import BadRequest, Forbidden, NotFound
from controllers.console import api
from controllers.console.explore.wraps import InstalledAppResource
from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
from controllers.console.wraps import (account_initialization_required,
cloud_edition_billing_resource_check)
from extensions.ext_database import db
from fields.installed_app_fields import installed_app_list_fields
from libs.login import login_required
from models import App, InstalledApp, RecommendedApp
from services.account_service import TenantService
from services.app_service import AppService
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
class InstalledAppsListApi(Resource):
@@ -48,6 +54,30 @@ class InstalledAppsListApi(Resource):
for installed_app in installed_apps
if installed_app.app is not None
]
# filter out apps that user doesn't have access to
if FeatureService.get_system_features().webapp_auth.enabled:
user_id = current_user.id
res = []
app_ids = [installed_app["app"].id for installed_app in installed_app_list]
webapp_settings = EnterpriseService.WebAppAuth.batch_get_app_access_mode_by_id(app_ids)
for installed_app in installed_app_list:
webapp_setting = webapp_settings.get(installed_app["app"].id)
if not webapp_setting:
continue
if webapp_setting.access_mode == "sso_verified":
continue
app_code = AppService.get_app_code_by_id(str(installed_app["app"].id))
if EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
user_id=user_id,
app_code=app_code,
):
res.append(installed_app)
installed_app_list = res
logging.info(
f"installed_app_list: {installed_app_list}, user_id: {user_id}"
)
installed_app_list.sort(
key=lambda app: (
-app["is_pinned"],
+9 -2
View File
@@ -50,7 +50,7 @@ class MessageListApi(InstalledAppResource):
try:
return MessageService.pagination_by_first_id(
app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
)
except services.errors.conversation.ConversationNotExistsError:
raise NotFound("Conversation Not Exists.")
@@ -66,10 +66,17 @@ class MessageFeedbackApi(InstalledAppResource):
parser = reqparse.RequestParser()
parser.add_argument("rating", type=str, choices=["like", "dislike", None], location="json")
parser.add_argument("content", type=str, location="json")
args = parser.parse_args()
try:
MessageService.create_feedback(app_model, message_id, current_user, args.get("rating"), args.get("content"))
MessageService.create_feedback(
app_model=app_model,
message_id=message_id,
user=current_user,
rating=args.get("rating"),
content=args.get("content"),
)
except services.errors.message.MessageNotExistsError:
raise NotFound("Message Not Exists.")
+5 -1
View File
@@ -13,7 +13,11 @@ from controllers.console.explore.error import NotWorkflowAppError
from controllers.console.explore.wraps import InstalledAppResource
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.errors.error import (
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from libs import helper
from libs.login import current_user
+29 -1
View File
@@ -4,10 +4,14 @@ from flask_login import current_user # type: ignore
from flask_restful import Resource # type: ignore
from werkzeug.exceptions import NotFound
from controllers.console.explore.error import AppAccessDeniedError
from controllers.console.wraps import account_initialization_required
from extensions.ext_database import db
from libs.login import login_required
from models import InstalledApp
from services.app_service import AppService
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
def installed_app_required(view=None):
@@ -48,6 +52,30 @@ def installed_app_required(view=None):
return decorator
def user_allowed_to_access_app(view=None):
def decorator(view):
@wraps(view)
def decorated(installed_app: InstalledApp, *args, **kwargs):
feature = FeatureService.get_system_features()
if feature.webapp_auth.enabled:
app_id = installed_app.app_id
app_code = AppService.get_app_code_by_id(app_id)
res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(
user_id=str(current_user.id),
app_code=app_code,
)
if not res:
raise AppAccessDeniedError()
return view(installed_app, *args, **kwargs)
return decorated
if view:
return decorator(view)
return decorator
class InstalledAppResource(Resource):
# must be reversed if there are multiple decorators
method_decorators = [installed_app_required, account_initialization_required, login_required]
method_decorators = [user_allowed_to_access_app, installed_app_required, account_initialization_required, login_required]
@@ -11,6 +11,7 @@ from controllers.console import api
from controllers.console.workspace.error import (
AccountAlreadyInitedError,
CurrentPasswordIncorrectError,
InvalidAccountDeletionCodeError,
InvalidInvitationCodeError,
RepeatPasswordNotMatchError,
)
@@ -21,6 +22,7 @@ from libs.helper import TimestampField, timezone
from libs.login import login_required
from models import AccountIntegrate, InvitationCode
from services.account_service import AccountService
from services.billing_service import BillingService
from services.errors.account import CurrentPasswordIncorrectError as ServiceCurrentPasswordIncorrectError
@@ -242,6 +244,54 @@ class AccountIntegrateApi(Resource):
return {"data": integrate_data}
class AccountDeleteVerifyApi(Resource):
@setup_required
@login_required
@account_initialization_required
def get(self):
account = current_user
token, code = AccountService.generate_account_deletion_verification_code(account)
AccountService.send_account_deletion_verification_email(account, code)
return {"result": "success", "data": token}
class AccountDeleteApi(Resource):
@setup_required
@login_required
@account_initialization_required
def post(self):
account = current_user
parser = reqparse.RequestParser()
parser.add_argument("token", type=str, required=True, location="json")
parser.add_argument("code", type=str, required=True, location="json")
args = parser.parse_args()
if not AccountService.verify_account_deletion_code(args["token"], args["code"]):
raise InvalidAccountDeletionCodeError()
AccountService.delete_account(account)
return {"result": "success"}
class AccountDeleteUpdateFeedbackApi(Resource):
@setup_required
def post(self):
account = current_user
parser = reqparse.RequestParser()
parser.add_argument("email", type=str, required=True, location="json")
parser.add_argument("feedback", type=str, required=True, location="json")
args = parser.parse_args()
BillingService.update_account_deletion_feedback(args["email"], args["feedback"])
return {"result": "success"}
# Register API resources
api.add_resource(AccountInitApi, "/account/init")
api.add_resource(AccountProfileApi, "/account/profile")
@@ -252,5 +302,8 @@ api.add_resource(AccountInterfaceThemeApi, "/account/interface-theme")
api.add_resource(AccountTimezoneApi, "/account/timezone")
api.add_resource(AccountPasswordApi, "/account/password")
api.add_resource(AccountIntegrateApi, "/account/integrates")
api.add_resource(AccountDeleteVerifyApi, "/account/delete/verify")
api.add_resource(AccountDeleteApi, "/account/delete")
api.add_resource(AccountDeleteUpdateFeedbackApi, "/account/delete/feedback")
# api.add_resource(AccountEmailApi, '/account/email')
# api.add_resource(AccountEmailVerifyApi, '/account/email-verify')
@@ -35,3 +35,9 @@ class AccountNotInitializedError(BaseHTTPException):
error_code = "account_not_initialized"
description = "The account has not been initialized yet. Please proceed with the initialization process first."
code = 400
class InvalidAccountDeletionCodeError(BaseHTTPException):
error_code = "invalid_account_deletion_code"
description = "Invalid account deletion code."
code = 400
+9 -2
View File
@@ -6,6 +6,7 @@ from flask_restful import Resource, abort, marshal_with, reqparse # type: ignor
import services
from configs import dify_config
from controllers.console import api
from controllers.console.error import WorkspaceMembersLimitExceeded
from controllers.console.wraps import (
account_initialization_required,
cloud_edition_billing_resource_check,
@@ -17,6 +18,7 @@ from libs.login import login_required
from models.account import Account, TenantAccountRole
from services.account_service import RegisterService, TenantService
from services.errors.account import AccountAlreadyInTenantError
from services.feature_service import FeatureService
class MemberListApi(Resource):
@@ -54,6 +56,12 @@ class MemberInviteEmailApi(Resource):
inviter = current_user
invitation_results = []
console_web_url = dify_config.CONSOLE_WEB_URL
workspace_members = FeatureService.get_features(tenant_id=inviter.current_tenant.id).workspace_members
if not workspace_members.is_available(len(invitee_emails)):
raise WorkspaceMembersLimitExceeded()
for invitee_email in invitee_emails:
try:
token = RegisterService.invite_new_member(
@@ -71,7 +79,6 @@ class MemberInviteEmailApi(Resource):
invitation_results.append(
{"status": "success", "email": invitee_email, "url": f"{console_web_url}/signin"}
)
break
except Exception as e:
invitation_results.append({"status": "failed", "email": invitee_email, "message": str(e)})
@@ -122,7 +129,7 @@ class MemberUpdateRoleApi(Resource):
return {"code": "invalid-role", "message": "Invalid role"}, 400
member = db.session.get(Account, str(member_id))
if member:
if not member:
abort(404)
try:
+37 -1
View File
@@ -11,7 +11,8 @@ from models.model import DifySetup
from services.feature_service import FeatureService, LicenseStatus
from services.operation_service import OperationService
from .error import NotInitValidateError, NotSetupError, UnauthorizedAndForceLogout
from .error import (NotInitValidateError, NotSetupError,
UnauthorizedAndForceLogout)
def account_initialization_required(view):
@@ -39,6 +40,28 @@ def only_edition_cloud(view):
return decorated
def only_edition_enterprise(view):
@wraps(view)
def decorated(*args, **kwargs):
if not dify_config.ENTERPRISE_ENABLED:
abort(404)
return view(*args, **kwargs)
return decorated
def only_edition_self_hosted(view):
@wraps(view)
def decorated(*args, **kwargs):
if not dify_config.ENTERPRISE_ENABLED:
abort(404)
return view(*args, **kwargs)
return decorated
def only_edition_self_hosted(view):
@wraps(view)
def decorated(*args, **kwargs):
@@ -154,3 +177,16 @@ def enterprise_license_required(view):
return view(*args, **kwargs)
return decorated
def email_password_login_enabled(view):
@wraps(view)
def decorated(*args, **kwargs):
features = FeatureService.get_system_features()
if features.enable_email_password_login:
return view(*args, **kwargs)
# otherwise, return 403
abort(403)
return decorated
+1
View File
@@ -5,4 +5,5 @@ from libs.external_api import ExternalApi
bp = Blueprint("inner_api", __name__, url_prefix="/inner/api")
api = ExternalApi(bp)
from . import mail
from .workspace import workspace
+27
View File
@@ -0,0 +1,27 @@
from flask_restful import (
Resource, # type: ignore
reqparse,
)
from controllers.console.wraps import setup_required
from controllers.inner_api import api
from controllers.inner_api.wraps import inner_api_only
from services.enterprise.mail_service import DifyMail, EnterpriseMailService
class EnterpriseMail(Resource):
@setup_required
@inner_api_only
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("to", type=str, action="append", required=True)
parser.add_argument("subject", type=str, required=True)
parser.add_argument("body", type=str, required=True)
parser.add_argument("substitutions", type=dict, required=False)
args = parser.parse_args()
EnterpriseMailService.send_mail(DifyMail(**args))
return {"message": "success"}, 200
api.add_resource(EnterpriseMail, "/enterprise/mail")
@@ -1,3 +1,5 @@
import json
from flask_restful import Resource, reqparse # type: ignore
from controllers.console.wraps import setup_required
@@ -29,4 +31,34 @@ class EnterpriseWorkspace(Resource):
return {"message": "enterprise workspace created."}
class EnterpriseWorkspaceNoOwnerEmail(Resource):
@setup_required
@inner_api_only
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("name", type=str, required=True, location="json")
args = parser.parse_args()
tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
tenant_was_created.send(tenant)
resp = {
"id": tenant.id,
"name": tenant.name,
"encrypt_public_key": tenant.encrypt_public_key,
"plan": tenant.plan,
"status": tenant.status,
"custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
"created_at": tenant.created_at.isoformat() if tenant.created_at else None,
"updated_at": tenant.updated_at.isoformat() if tenant.updated_at else None,
}
return {
"message": "enterprise workspace created.",
"tenant": resp,
}
api.add_resource(EnterpriseWorkspace, "/enterprise/workspace")
api.add_resource(EnterpriseWorkspaceNoOwnerEmail, "/enterprise/workspace/ownerless")
+1 -1
View File
@@ -7,4 +7,4 @@ api = ExternalApi(bp)
from . import index
from .app import app, audio, completion, conversation, file, message, workflow
from .dataset import dataset, document, hit_testing, segment
from .dataset import dataset, document, hit_testing, segment, upload_file
@@ -18,7 +18,6 @@ from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import (
AppInvokeQuotaExceededError,
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
@@ -74,7 +73,7 @@ class CompletionApi(Resource):
raise ProviderModelCurrentlyNotSupportError()
except InvokeError as e:
raise CompletionRequestError(e.description)
except (ValueError, AppInvokeQuotaExceededError) as e:
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
@@ -133,7 +132,7 @@ class ChatApi(Resource):
raise ProviderModelCurrentlyNotSupportError()
except InvokeError as e:
raise CompletionRequestError(e.description)
except (ValueError, AppInvokeQuotaExceededError) as e:
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
+7 -1
View File
@@ -108,7 +108,13 @@ class MessageFeedbackApi(Resource):
args = parser.parse_args()
try:
MessageService.create_feedback(app_model, message_id, end_user, args.get("rating"), args.get("content"))
MessageService.create_feedback(
app_model=app_model,
message_id=message_id,
user=end_user,
rating=args.get("rating"),
content=args.get("content"),
)
except services.errors.message.MessageNotExistsError:
raise NotFound("Message Not Exists.")
+1 -2
View File
@@ -16,7 +16,6 @@ from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import (
AppInvokeQuotaExceededError,
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
@@ -94,7 +93,7 @@ class WorkflowRunApi(Resource):
raise ProviderModelCurrentlyNotSupportError()
except InvokeError as e:
raise CompletionRequestError(e.description)
except (ValueError, AppInvokeQuotaExceededError) as e:
except ValueError as e:
raise e
except Exception as e:
logging.exception("internal server error.")
@@ -31,8 +31,11 @@ class DatasetListApi(DatasetApiResource):
# provider = request.args.get("provider", default="vendor")
search = request.args.get("keyword", default=None, type=str)
tag_ids = request.args.getlist("tag_ids")
include_all = request.args.get("include_all", default="false").lower() == "true"
datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
datasets, total = DatasetService.get_datasets(
page, limit, tenant_id, current_user, search, tag_ids, include_all
)
# check embedding setting
provider_manager = ProviderManager()
configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
+128 -12
View File
@@ -8,12 +8,17 @@ from werkzeug.exceptions import NotFound
import services.dataset_service
from controllers.common.errors import FilenameNotExistsError
from controllers.service_api import api
from controllers.service_api.app.error import ProviderNotInitializeError
from controllers.service_api.app.error import (
FileTooLargeError,
NoFileUploadedError,
ProviderNotInitializeError,
TooManyFilesError,
UnsupportedFileTypeError,
)
from controllers.service_api.dataset.error import (
ArchivedDocumentImmutableError,
DocumentIndexingError,
NoFileUploadedError,
TooManyFilesError,
InvalidMetadataError,
)
from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
from core.errors.error import ProviderTokenNotInitError
@@ -46,6 +51,9 @@ class DocumentAddByTextApi(DatasetApiResource):
"indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
)
parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
args = parser.parse_args()
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
@@ -57,6 +65,28 @@ class DocumentAddByTextApi(DatasetApiResource):
if not dataset.indexing_technique and not args["indexing_technique"]:
raise ValueError("indexing_technique is required.")
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
text = args.get("text")
name = args.get("name")
if text is None or name is None:
@@ -103,6 +133,8 @@ class DocumentUpdateByTextApi(DatasetApiResource):
"doc_language", type=str, default="English", required=False, nullable=False, location="json"
)
parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
args = parser.parse_args()
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
@@ -111,6 +143,32 @@ class DocumentUpdateByTextApi(DatasetApiResource):
if not dataset:
raise ValueError("Dataset is not exist.")
# indexing_technique is already set in dataset since this is an update
args["indexing_technique"] = dataset.indexing_technique
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
if args["text"]:
text = args.get("text")
name = args.get("name")
@@ -157,6 +215,30 @@ class DocumentAddByFileApi(DatasetApiResource):
args["doc_form"] = "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
@@ -186,7 +268,10 @@ class DocumentAddByFileApi(DatasetApiResource):
user=current_user,
source="datasets",
)
data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
# validate args
knowledge_config = KnowledgeConfig(**args)
@@ -221,6 +306,29 @@ class DocumentUpdateByFileApi(DatasetApiResource):
if "doc_language" not in args:
args["doc_language"] = "English"
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
@@ -238,14 +346,22 @@ class DocumentUpdateByFileApi(DatasetApiResource):
if not file.filename:
raise FilenameNotExistsError
upload_file = FileService.upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
user=current_user,
source="datasets",
)
data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
try:
upload_file = FileService.upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
user=current_user,
source="datasets",
)
except services.errors.file.FileTooLargeError as file_too_large_error:
raise FileTooLargeError(file_too_large_error.description)
except services.errors.file.UnsupportedFileTypeError:
raise UnsupportedFileTypeError()
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
# validate args
args["original_document_id"] = str(document_id)
@@ -53,8 +53,7 @@ class SegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -95,8 +94,7 @@ class SegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -175,8 +173,7 @@ class DatasetSegmentApi(DatasetApiResource):
)
except LLMBadRequestError:
raise ProviderNotInitializeError(
"No Embedding Model available. Please configure a valid provider "
"in the Settings -> Model Provider."
"No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
@@ -0,0 +1,54 @@
from werkzeug.exceptions import NotFound
from controllers.service_api import api
from controllers.service_api.wraps import (
DatasetApiResource,
)
from core.file import helpers as file_helpers
from extensions.ext_database import db
from models.dataset import Dataset
from models.model import UploadFile
from services.dataset_service import DocumentService
class UploadFileApi(DatasetApiResource):
def get(self, tenant_id, dataset_id, document_id):
"""Get upload file."""
# check dataset
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise NotFound("Dataset not found.")
# check document
document_id = str(document_id)
document = DocumentService.get_document(dataset.id, document_id)
if not document:
raise NotFound("Document not found.")
# check upload file
if document.data_source_type != "upload_file":
raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
data_source_info = document.data_source_info_dict
if data_source_info and "upload_file_id" in data_source_info:
file_id = data_source_info["upload_file_id"]
upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
if not upload_file:
raise NotFound("UploadFile not found.")
else:
raise ValueError("Upload file id not found in document data source info.")
url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
return {
"id": upload_file.id,
"name": upload_file.name,
"size": upload_file.size,
"extension": upload_file.extension,
"url": url,
"download_url": f"{url}&as_attachment=true",
"mime_type": upload_file.mime_type,
"created_by": upload_file.created_by,
"created_at": upload_file.created_at.timestamp(),
}, 200
api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")
+26 -15
View File
@@ -1,5 +1,5 @@
from collections.abc import Callable
from datetime import UTC, datetime
from datetime import UTC, datetime, timedelta
from enum import Enum
from functools import wraps
from typing import Optional
@@ -8,6 +8,8 @@ from flask import current_app, request
from flask_login import user_logged_in # type: ignore
from flask_restful import Resource # type: ignore
from pydantic import BaseModel
from sqlalchemy import select, update
from sqlalchemy.orm import Session
from werkzeug.exceptions import Forbidden, Unauthorized
from extensions.ext_database import db
@@ -174,7 +176,7 @@ def validate_dataset_token(view=None):
return decorator
def validate_and_get_api_token(scope=None):
def validate_and_get_api_token(scope: str | None = None):
"""
Validate and get API token.
"""
@@ -188,20 +190,29 @@ def validate_and_get_api_token(scope=None):
if auth_scheme != "bearer":
raise Unauthorized("Authorization scheme must be 'Bearer'")
api_token = (
db.session.query(ApiToken)
.filter(
ApiToken.token == auth_token,
ApiToken.type == scope,
current_time = datetime.now(UTC).replace(tzinfo=None)
cutoff_time = current_time - timedelta(minutes=1)
with Session(db.engine, expire_on_commit=False) as session:
update_stmt = (
update(ApiToken)
.where(
ApiToken.token == auth_token,
(ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
ApiToken.type == scope,
)
.values(last_used_at=current_time)
.returning(ApiToken)
)
.first()
)
result = session.execute(update_stmt)
api_token = result.scalar_one_or_none()
if not api_token:
raise Unauthorized("Access token is invalid")
api_token.last_used_at = datetime.now(UTC).replace(tzinfo=None)
db.session.commit()
if not api_token:
stmt = select(ApiToken).where(ApiToken.token == auth_token, ApiToken.type == scope)
api_token = session.scalar(stmt)
if not api_token:
raise Unauthorized("Access token is invalid")
else:
session.commit()
return api_token
@@ -229,7 +240,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
tenant_id=app_model.tenant_id,
app_id=app_model.id,
type="service_api",
is_anonymous=True if user_id == "DEFAULT-USER" else False,
is_anonymous=user_id == "DEFAULT-USER",
session_id=user_id,
)
db.session.add(end_user)
+14 -1
View File
@@ -15,4 +15,17 @@ api.add_resource(FileApi, "/files/upload")
api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
from . import app, audio, completion, conversation, feature, message, passport, saved_message, site, workflow
from . import (
app,
audio,
completion,
conversation,
feature,
forgot_password,
login,
message,
passport,
saved_message,
site,
workflow,
)
+67 -1
View File
@@ -1,12 +1,18 @@
from flask_restful import marshal_with # type: ignore
from flask import request
from flask_restful import Resource, marshal_with, reqparse # type: ignore
from controllers.common import fields
from controllers.common import helpers as controller_helpers
from controllers.web import api
from controllers.web.error import AppUnavailableError
from controllers.web.wraps import WebApiResource
from libs.passport import PassportService
from models.model import App, AppMode
from services.app_service import AppService
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
from services.webapp_auth_service import WebAppAuthService
class AppParameterApi(WebApiResource):
@@ -42,5 +48,65 @@ class AppMeta(WebApiResource):
return AppService().get_app_meta(app_model)
class AppAccessMode(Resource):
def get(self):
parser = reqparse.RequestParser()
parser.add_argument("appId", type=str, required=False, location="args")
parser.add_argument("appCode", type=str, required=False, location="args")
args = parser.parse_args()
features = FeatureService.get_system_features()
if not features.webapp_auth.enabled:
return {"accessMode": "public"}
app_id = args.get("appId")
if args.get("appCode"):
app_code = args["appCode"]
app_id = AppService.get_app_id_by_code(app_code)
if not app_id:
raise ValueError("appId or appCode must be provided")
res = EnterpriseService.WebAppAuth.get_app_access_mode_by_id(app_id)
return {"accessMode": res.access_mode}
class AppWebAuthPermission(Resource):
def get(self):
user_id = "visitor"
try:
auth_header = request.headers.get("Authorization")
if auth_header is None:
raise
if " " not in auth_header:
raise
auth_scheme, tk = auth_header.split(None, 1)
auth_scheme = auth_scheme.lower()
if auth_scheme != "bearer":
raise
decoded = PassportService().verify(tk)
user_id = decoded.get("user_id", "visitor")
except Exception as e:
pass
parser = reqparse.RequestParser()
parser.add_argument("appId", type=str, required=True, location="args")
args = parser.parse_args()
app_id = args["appId"]
app_code = AppService.get_app_code_by_id(app_id)
res = True
if WebAppAuthService.is_app_require_permission_check(app_id=app_id):
res = EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(str(user_id), app_code)
return {"result": res}
api.add_resource(AppParameterApi, "/parameters")
api.add_resource(AppMeta, "/meta")
# webapp auth apis
api.add_resource(AppAccessMode, "/webapp/access-mode")
api.add_resource(AppWebAuthPermission, "/webapp/permission")
+5 -1
View File
@@ -19,7 +19,11 @@ from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpErr
from controllers.web.wraps import WebApiResource
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.errors.error import (
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from libs import helper
from libs.helper import uuid_value
+1 -1
View File
@@ -39,7 +39,7 @@ class ConversationListApi(WebApiResource):
pinned = None
if "pinned" in args and args["pinned"] is not None:
pinned = True if args["pinned"] == "true" else False
pinned = args["pinned"] == "true"
try:
with Session(db.engine) as session:
+8 -2
View File
@@ -121,9 +121,15 @@ class UnsupportedFileTypeError(BaseHTTPException):
code = 415
class WebSSOAuthRequiredError(BaseHTTPException):
class WebAppAuthRequiredError(BaseHTTPException):
error_code = "web_sso_auth_required"
description = "Web SSO authentication required."
description = "Web app authentication required."
code = 401
class WebAppAuthAccessDeniedError(BaseHTTPException):
error_code = "web_app_access_denied"
description = "You do not have permission to access this web app."
code = 401
+147
View File
@@ -0,0 +1,147 @@
import base64
import secrets
from flask import request
from flask_restful import Resource, reqparse
from sqlalchemy import select
from sqlalchemy.orm import Session
from controllers.console.auth.error import (
EmailCodeError,
EmailPasswordResetLimitError,
InvalidEmailError,
InvalidTokenError,
PasswordMismatchError,
)
from controllers.console.error import AccountNotFound, EmailSendIpLimitError
from controllers.console.wraps import email_password_login_enabled, only_edition_enterprise, setup_required
from controllers.web import api
from extensions.ext_database import db
from libs.helper import email, extract_remote_ip
from libs.password import hash_password, valid_password
from models.account import Account
from services.account_service import AccountService
class ForgotPasswordSendEmailApi(Resource):
@only_edition_enterprise
@setup_required
@email_password_login_enabled
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()
ip_address = extract_remote_ip(request)
if AccountService.is_email_send_ip_limit(ip_address):
raise EmailSendIpLimitError()
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
language = "en-US"
with Session(db.engine) as session:
account = session.execute(select(Account).filter_by(email=args["email"])).scalar_one_or_none()
token = None
if account is None:
raise AccountNotFound()
else:
token = AccountService.send_reset_password_email(account=account, email=args["email"], language=language)
return {"result": "success", "data": token}
class ForgotPasswordCheckApi(Resource):
@only_edition_enterprise
@setup_required
@email_password_login_enabled
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()
user_email = args["email"]
is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
if is_forgot_password_error_rate_limit:
raise EmailPasswordResetLimitError()
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"):
AccountService.add_forgot_password_error_rate_limit(args["email"])
raise EmailCodeError()
# Verified, revoke the first token
AccountService.revoke_reset_password_token(args["token"])
# Refresh token data by generating a new token
_, new_token = AccountService.generate_reset_password_token(
user_email, code=args["code"], additional_data={"phase": "reset"}
)
AccountService.reset_forgot_password_error_rate_limit(args["email"])
return {"is_valid": True, "email": token_data.get("email"), "token": new_token}
class ForgotPasswordResetApi(Resource):
@only_edition_enterprise
@setup_required
@email_password_login_enabled
def post(self):
parser = reqparse.RequestParser()
parser.add_argument("token", type=str, required=True, nullable=False, location="json")
parser.add_argument("new_password", type=valid_password, required=True, nullable=False, location="json")
parser.add_argument("password_confirm", type=valid_password, required=True, nullable=False, location="json")
args = parser.parse_args()
# Validate passwords match
if args["new_password"] != args["password_confirm"]:
raise PasswordMismatchError()
# Validate token and get reset data
reset_data = AccountService.get_reset_password_data(args["token"])
if not reset_data:
raise InvalidTokenError()
# Must use token in reset phase
if reset_data.get("phase", "") != "reset":
raise InvalidTokenError()
# Revoke token to prevent reuse
AccountService.revoke_reset_password_token(args["token"])
# Generate secure salt and hash password
salt = secrets.token_bytes(16)
password_hashed = hash_password(args["new_password"], salt)
email = reset_data.get("email", "")
with Session(db.engine) as session:
account = session.execute(select(Account).filter_by(email=email)).scalar_one_or_none()
if account:
self._update_existing_account(account, password_hashed, salt, session)
else:
raise AccountNotFound()
return {"result": "success"}
def _update_existing_account(self, account, password_hashed, salt, session):
# Update existing account credentials
account.password = base64.b64encode(password_hashed).decode()
account.password_salt = base64.b64encode(salt).decode()
session.commit()
api.add_resource(ForgotPasswordSendEmailApi, "/forgot-password")
api.add_resource(ForgotPasswordCheckApi, "/forgot-password/validity")
api.add_resource(ForgotPasswordResetApi, "/forgot-password/resets")
+109
View File
@@ -0,0 +1,109 @@
import services
from controllers.console.auth.error import (EmailCodeError,
EmailOrPasswordMismatchError,
InvalidEmailError)
from controllers.console.error import AccountBannedError, AccountNotFound
from controllers.console.wraps import only_edition_enterprise, setup_required
from controllers.web import api
from flask_restful import Resource, reqparse
from jwt import InvalidTokenError # type: ignore
from libs.helper import email
from libs.password import valid_password
from services.account_service import AccountService
from services.webapp_auth_service import WebAppAuthService
class LoginApi(Resource):
"""Resource for web app email/password login."""
@setup_required
@only_edition_enterprise
def post(self):
"""Authenticate user and login."""
parser = reqparse.RequestParser()
parser.add_argument("email", type=email, required=True, location="json")
parser.add_argument("password", type=valid_password, required=True, location="json")
args = parser.parse_args()
try:
account = WebAppAuthService.authenticate(args["email"], args["password"])
except services.errors.account.AccountLoginError:
raise AccountBannedError()
except services.errors.account.AccountPasswordError:
raise EmailOrPasswordMismatchError()
except services.errors.account.AccountNotFoundError:
raise AccountNotFound()
token = WebAppAuthService.login(account=account)
return {"result": "success", "data": {"access_token": token}}
# class LogoutApi(Resource):
# @setup_required
# def get(self):
# account = cast(Account, flask_login.current_user)
# if isinstance(account, flask_login.AnonymousUserMixin):
# return {"result": "success"}
# flask_login.logout_user()
# return {"result": "success"}
class EmailCodeLoginSendEmailApi(Resource):
@setup_required
@only_edition_enterprise
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()
if args["language"] is not None and args["language"] == "zh-Hans":
language = "zh-Hans"
else:
language = "en-US"
account = WebAppAuthService.get_user_through_email(args["email"])
if account is None:
raise AccountNotFound()
else:
token = WebAppAuthService.send_email_code_login_email(account=account, language=language)
return {"result": "success", "data": token}
class EmailCodeLoginApi(Resource):
@setup_required
@only_edition_enterprise
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 = WebAppAuthService.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()
WebAppAuthService.revoke_email_code_login_token(args["token"])
account = WebAppAuthService.get_user_through_email(user_email)
if not account:
raise AccountNotFound()
token = WebAppAuthService.login(account=account)
AccountService.reset_login_error_rate_limit(args["email"])
return {"result": "success", "data": {"access_token": token}}
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")
+1 -1
View File
@@ -91,7 +91,7 @@ class MessageListApi(WebApiResource):
try:
return MessageService.pagination_by_first_id(
app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
)
except services.errors.conversation.ConversationNotExistsError:
raise NotFound("Conversation Not Exists.")
+143 -9
View File
@@ -1,16 +1,18 @@
import uuid
from datetime import UTC, datetime, timedelta
from flask import request
from flask_restful import Resource # type: ignore
from werkzeug.exceptions import NotFound, Unauthorized
from configs import dify_config
from controllers.web import api
from controllers.web.error import WebSSOAuthRequiredError
from controllers.web.error import WebAppAuthRequiredError
from extensions.ext_database import db
from flask import request
from flask_restful import Resource
from libs.passport import PassportService
from models.model import App, EndUser, Site
from services.enterprise.enterprise_service import EnterpriseService
from services.feature_service import FeatureService
from services.webapp_auth_service import WebAppAuthService, WebAppAuthType
from werkzeug.exceptions import NotFound, Unauthorized
class PassportResource(Resource):
@@ -19,13 +21,23 @@ class PassportResource(Resource):
def get(self):
system_features = FeatureService.get_system_features()
app_code = request.headers.get("X-App-Code")
web_app_access_token = request.args.get("web_app_access_token")
if app_code is None:
raise Unauthorized("X-App-Code header is missing.")
if system_features.sso_enforced_for_web:
app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
if app_web_sso_enabled:
raise WebSSOAuthRequiredError()
# exchange token for enterprise logined web user
enterprise_user_decoded = decode_enterprise_webapp_user_id(web_app_access_token)
if enterprise_user_decoded:
# a web user has already logged in, exchange a token for this app without redirecting to the login page
return exchange_token_for_existing_web_user(
app_code=app_code, enterprise_user_decoded=enterprise_user_decoded
)
if system_features.webapp_auth.enabled:
app_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code)
if not app_settings or not app_settings.access_mode == "public":
raise WebAppAuthRequiredError()
# get site from db and check if it is normal
site = db.session.query(Site).filter(Site.code == app_code, Site.status == "normal").first()
@@ -65,6 +77,128 @@ class PassportResource(Resource):
api.add_resource(PassportResource, "/passport")
def decode_enterprise_webapp_user_id(jwt_token: str | None):
"""
Decode the enterprise user session from the Authorization header.
"""
if not jwt_token:
return None
decoded = PassportService().verify(jwt_token)
source = decoded.get("token_source")
if not source or source != "webapp_login_token":
raise Unauthorized("Invalid token source. Expected 'webapp_login_token'.")
return decoded
def exchange_token_for_existing_web_user(app_code: str, enterprise_user_decoded: dict):
"""
Exchange a token for an existing web user session.
"""
user_id = enterprise_user_decoded.get("user_id")
end_user_id = enterprise_user_decoded.get("end_user_id")
session_id = enterprise_user_decoded.get("session_id")
user_auth_type = enterprise_user_decoded.get("auth_type")
if not user_auth_type:
raise Unauthorized("Missing auth_type in the token.")
site = db.session.query(Site).filter(Site.code == app_code, Site.status == "normal").first()
if not site:
raise NotFound()
app_model = db.session.query(App).filter(App.id == site.app_id).first()
if not app_model or app_model.status != "normal" or not app_model.enable_site:
raise NotFound()
app_auth_type = WebAppAuthService.get_app_auth_type(app_code=app_code)
if app_auth_type == WebAppAuthType.PUBLIC:
return _exchange_for_public_app_token(app_model, site, enterprise_user_decoded)
elif app_auth_type == WebAppAuthType.EXTERNAL and user_auth_type != "external":
raise WebAppAuthRequiredError("Please login as external user.")
elif app_auth_type == WebAppAuthType.INTERNAL and user_auth_type != "internal":
raise WebAppAuthRequiredError("Please login as internal user.")
end_user = None
if end_user_id:
end_user = db.session.query(EndUser).filter(EndUser.id == end_user_id).first()
if session_id:
end_user = (
db.session.query(EndUser)
.filter(
EndUser.session_id == session_id,
EndUser.tenant_id == app_model.tenant_id,
EndUser.app_id == app_model.id,
)
.first()
)
if not end_user:
if not session_id:
raise NotFound("Missing session_id for existing web user.")
end_user = EndUser(
tenant_id=app_model.tenant_id,
app_id=app_model.id,
type="browser",
is_anonymous=True,
session_id=session_id,
)
db.session.add(end_user)
db.session.commit()
exp_dt = datetime.now(UTC) + timedelta(hours=dify_config.ACCESS_TOKEN_EXPIRE_MINUTES * 24)
exp = int(exp_dt.timestamp())
payload = {
"iss": site.id,
"sub": "Web API Passport",
"app_id": site.app_id,
"app_code": site.code,
"user_id": user_id,
"end_user_id": end_user.id,
"auth_type": user_auth_type,
"granted_at": int(datetime.now(UTC).timestamp()),
"token_source": "webapp",
"exp": exp,
}
token: str = PassportService().issue(payload)
return {
"access_token": token,
}
def _exchange_for_public_app_token(app_model, site, token_decoded):
user_id = token_decoded.get("user_id")
end_user = None
if user_id:
end_user = db.session.query(EndUser).filter(
EndUser.app_id == app_model.id, EndUser.session_id == user_id
).first()
if not end_user:
end_user = EndUser(
tenant_id=app_model.tenant_id,
app_id=app_model.id,
type="browser",
is_anonymous=True,
session_id=generate_session_id(),
)
db.session.add(end_user)
db.session.commit()
payload = {
"iss": site.app_id,
"sub": "Web API Passport",
"app_id": site.app_id,
"app_code": site.code,
"end_user_id": end_user.id,
}
tk = PassportService().issue(payload)
return {
"access_token": tk,
}
def generate_session_id():
"""
Generate a unique session ID.
+5 -1
View File
@@ -14,7 +14,11 @@ from controllers.web.error import (
from controllers.web.wraps import WebApiResource
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.errors.error import (
ModelCurrentlyNotSupportError,
ProviderTokenNotInitError,
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from libs import helper
from models.model import App, AppMode, EndUser
+83 -28
View File
@@ -1,15 +1,18 @@
from datetime import UTC, datetime
from functools import wraps
from controllers.web.error import (WebAppAuthAccessDeniedError,
WebAppAuthRequiredError)
from extensions.ext_database import db
from flask import request
from flask_restful import Resource # type: ignore
from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
from controllers.web.error import WebSSOAuthRequiredError
from extensions.ext_database import db
from libs.passport import PassportService
from models.model import App, EndUser, Site
from services.enterprise.enterprise_service import EnterpriseService
from services.enterprise.enterprise_service import (EnterpriseService,
WebAppSettings)
from services.feature_service import FeatureService
from services.webapp_auth_service import WebAppAuthService
from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
def validate_jwt_token(view=None):
@@ -45,7 +48,8 @@ def decode_jwt_token():
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
decoded = PassportService().verify(tk)
app_code = decoded.get("app_code")
app_model = db.session.query(App).filter(App.id == decoded["app_id"]).first()
app_id = decoded.get("app_id")
app_model = db.session.query(App).filter(App.id == app_id).first()
site = db.session.query(Site).filter(Site.code == app_code).first()
if not app_model:
raise NotFound()
@@ -53,39 +57,90 @@ def decode_jwt_token():
raise BadRequest("Site URL is no longer valid.")
if app_model.enable_site is False:
raise BadRequest("Site is disabled.")
end_user = db.session.query(EndUser).filter(EndUser.id == decoded["end_user_id"]).first()
end_user_id = decoded.get("end_user_id")
end_user = db.session.query(EndUser).filter(EndUser.id == end_user_id).first()
if not end_user:
raise NotFound()
_validate_web_sso_token(decoded, system_features, app_code)
# for enterprise webapp auth
app_web_auth_enabled = False
webapp_settings = None
if system_features.webapp_auth.enabled:
webapp_settings = EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code)
if not webapp_settings:
raise NotFound("Web app settings not found.")
app_web_auth_enabled = webapp_settings.access_mode != "public"
_validate_webapp_token(decoded, app_web_auth_enabled, system_features.webapp_auth.enabled)
_validate_user_accessibility(
decoded, app_code, app_web_auth_enabled, system_features.webapp_auth.enabled, webapp_settings
)
return app_model, end_user
except Unauthorized as e:
if system_features.sso_enforced_for_web:
app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
if app_web_sso_enabled:
raise WebSSOAuthRequiredError()
if system_features.webapp_auth.enabled:
if not app_code:
raise Unauthorized("Please re-login to access the web app.")
app_web_auth_enabled = (
EnterpriseService.WebAppAuth.get_app_access_mode_by_code(app_code=app_code).access_mode != "public"
)
if app_web_auth_enabled:
raise WebAppAuthRequiredError()
raise Unauthorized(e.description)
def _validate_web_sso_token(decoded, system_features, app_code):
app_web_sso_enabled = False
# Check if SSO is enforced for web, and if the token source is not SSO, raise an error and redirect to SSO login
if system_features.sso_enforced_for_web:
app_web_sso_enabled = EnterpriseService.get_app_web_sso_enabled(app_code).get("enabled", False)
if app_web_sso_enabled:
source = decoded.get("token_source")
if not source or source != "sso":
raise WebSSOAuthRequiredError()
# Check if SSO is not enforced for web, and if the token source is SSO,
# raise an error and redirect to normal passport login
if not system_features.sso_enforced_for_web or not app_web_sso_enabled:
def _validate_webapp_token(decoded, app_web_auth_enabled: bool, system_webapp_auth_enabled: bool):
# Check if authentication is enforced for web app, and if the token source is not webapp,
# raise an error and redirect to login
if system_webapp_auth_enabled and app_web_auth_enabled:
source = decoded.get("token_source")
if source and source == "sso":
raise Unauthorized("sso token expired.")
if not source or source != "webapp":
raise WebAppAuthRequiredError()
# Check if authentication is not enforced for web, and if the token source is webapp,
# raise an error and redirect to normal passport login
if not system_webapp_auth_enabled or not app_web_auth_enabled:
source = decoded.get("token_source")
if source and source == "webapp":
raise Unauthorized("webapp token expired.")
def _validate_user_accessibility(
decoded,
app_code,
app_web_auth_enabled: bool,
system_webapp_auth_enabled: bool,
webapp_settings: WebAppSettings | None,
):
if system_webapp_auth_enabled and app_web_auth_enabled:
# Check if the user is allowed to access the web app
user_id = decoded.get("user_id")
if not user_id:
raise WebAppAuthRequiredError()
if not webapp_settings:
raise WebAppAuthRequiredError("Web app settings not found.")
if WebAppAuthService.is_app_require_permission_check(access_mode=webapp_settings.access_mode):
if not EnterpriseService.WebAppAuth.is_user_allowed_to_access_webapp(user_id, app_code=app_code):
raise WebAppAuthAccessDeniedError()
auth_type = decoded.get("auth_type")
granted_at = decoded.get("granted_at")
if not auth_type:
raise WebAppAuthAccessDeniedError("Missing auth_type in the token.")
if not granted_at:
raise WebAppAuthAccessDeniedError("Missing granted_at in the token.")
# check if sso has been updated
if auth_type == "external":
last_update_time = EnterpriseService.get_app_sso_settings_last_update_time()
if granted_at and datetime.fromtimestamp(granted_at, tz=UTC) < last_update_time:
raise WebAppAuthAccessDeniedError("SSO settings have been updated. Please re-login.")
elif auth_type == "internal":
last_update_time = EnterpriseService.get_workspace_sso_settings_last_update_time()
if granted_at and datetime.fromtimestamp(granted_at, tz=UTC) < last_update_time:
raise WebAppAuthAccessDeniedError("SSO settings have been updated. Please re-login.")
class WebApiResource(Resource):
+5 -5
View File
@@ -339,13 +339,13 @@ class BaseAgentRunner(AppRunner):
raise ValueError(f"Agent thought {agent_thought.id} not found")
agent_thought = queried_thought
if thought is not None:
if thought:
agent_thought.thought = thought
if tool_name is not None:
if tool_name:
agent_thought.tool = tool_name
if tool_input is not None:
if tool_input:
if isinstance(tool_input, dict):
try:
tool_input = json.dumps(tool_input, ensure_ascii=False)
@@ -354,7 +354,7 @@ class BaseAgentRunner(AppRunner):
agent_thought.tool_input = tool_input
if observation is not None:
if observation:
if isinstance(observation, dict):
try:
observation = json.dumps(observation, ensure_ascii=False)
@@ -363,7 +363,7 @@ class BaseAgentRunner(AppRunner):
agent_thought.observation = observation
if answer is not None:
if answer:
agent_thought.answer = answer
if messages_ids is not None and len(messages_ids) > 0:
+1 -2
View File
@@ -104,7 +104,6 @@ class CotAgentRunner(BaseAgentRunner, ABC):
# recalc llm max tokens
prompt_messages = self._organize_prompt_messages()
self.recalc_llm_max_tokens(self.model_config, prompt_messages)
# invoke model
chunks = model_instance.invoke_llm(
prompt_messages=prompt_messages,
@@ -172,7 +171,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
self.save_agent_thought(
agent_thought=agent_thought,
tool_name=scratchpad.action.action_name if scratchpad.action else "",
tool_name=(scratchpad.action.action_name if scratchpad.action and not scratchpad.is_final() else ""),
tool_input={scratchpad.action.action_name: scratchpad.action.action_input} if scratchpad.action else {},
tool_invoke_meta={},
thought=scratchpad.thought or "",
-1
View File
@@ -84,7 +84,6 @@ class FunctionCallAgentRunner(BaseAgentRunner):
# recalc llm max tokens
prompt_messages = self._organize_prompt_messages()
self.recalc_llm_max_tokens(self.model_config, prompt_messages)
# invoke model
chunks: Union[Generator[LLMResultChunk, None, None], LLMResult] = model_instance.invoke_llm(
prompt_messages=prompt_messages,
@@ -21,7 +21,7 @@ from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.ops.ops_trace_manager import TraceQueueManager
from core.prompt.utils.get_thread_messages_length import get_thread_messages_length
from extensions.ext_database import db
@@ -336,7 +336,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
except ValidationError as e:
logger.exception("Validation Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
except (ValueError, InvokeError) as e:
except ValueError as e:
if dify_config.DEBUG:
logger.exception("Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
@@ -67,24 +67,17 @@ from models.account import Account
from models.enums import CreatedByRole
from models.workflow import (
Workflow,
WorkflowNodeExecution,
WorkflowRunStatus,
)
logger = logging.getLogger(__name__)
class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleManage, MessageCycleManage):
class AdvancedChatAppGenerateTaskPipeline:
"""
AdvancedChatAppGenerateTaskPipeline is a class that generate stream output and state management for Application.
"""
_task_state: WorkflowTaskState
_application_generate_entity: AdvancedChatAppGenerateEntity
_workflow_system_variables: dict[SystemVariableKey, Any]
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
_conversation_name_generate_thread: Optional[Thread] = None
def __init__(
self,
application_generate_entity: AdvancedChatAppGenerateEntity,
@@ -96,7 +89,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
stream: bool,
dialogue_count: int,
) -> None:
super().__init__(
self._base_task_pipeline = BasedGenerateTaskPipeline(
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
stream=stream,
@@ -113,32 +106,35 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
else:
raise NotImplementedError(f"User type not supported: {type(user)}")
self._workflow_id = workflow.id
self._workflow_features_dict = workflow.features_dict
self._conversation_id = conversation.id
self._conversation_mode = conversation.mode
self._message_id = message.id
self._message_created_at = int(message.created_at.timestamp())
self._workflow_system_variables = {
SystemVariableKey.QUERY: message.query,
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.CONVERSATION_ID: conversation.id,
SystemVariableKey.USER_ID: user_session_id,
SystemVariableKey.DIALOGUE_COUNT: 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._workflow_cycle_manager = WorkflowCycleManage(
application_generate_entity=application_generate_entity,
workflow_system_variables={
SystemVariableKey.QUERY: message.query,
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.CONVERSATION_ID: conversation.id,
SystemVariableKey.USER_ID: user_session_id,
SystemVariableKey.DIALOGUE_COUNT: 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._message_cycle_manager = MessageCycleManage(
application_generate_entity=application_generate_entity, task_state=self._task_state
)
self._conversation_name_generate_thread = None
self._application_generate_entity = application_generate_entity
self._workflow_id = workflow.id
self._workflow_features_dict = workflow.features_dict
self._conversation_id = conversation.id
self._conversation_mode = conversation.mode
self._message_id = message.id
self._message_created_at = int(message.created_at.timestamp())
self._conversation_name_generate_thread: Thread | None = None
self._recorded_files: list[Mapping[str, Any]] = []
self._workflow_run_id = ""
self._workflow_run_id: str = ""
def process(self) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
"""
@@ -146,13 +142,13 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
:return:
"""
# start generate conversation name thread
self._conversation_name_generate_thread = self._generate_conversation_name(
self._conversation_name_generate_thread = self._message_cycle_manager._generate_conversation_name(
conversation_id=self._conversation_id, query=self._application_generate_entity.query
)
generator = self._wrapper_process_stream_response(trace_manager=self._application_generate_entity.trace_manager)
if self._stream:
if self._base_task_pipeline._stream:
return self._to_stream_response(generator)
else:
return self._to_blocking_response(generator)
@@ -269,24 +265,26 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
# init fake graph runtime state
graph_runtime_state: Optional[GraphRuntimeState] = None
for queue_message in self._queue_manager.listen():
for queue_message in self._base_task_pipeline._queue_manager.listen():
event = queue_message.event
if isinstance(event, QueuePingEvent):
yield self._ping_stream_response()
yield self._base_task_pipeline._ping_stream_response()
elif isinstance(event, QueueErrorEvent):
with Session(db.engine) as session:
err = self._handle_error(event=event, session=session, message_id=self._message_id)
with Session(db.engine, expire_on_commit=False) as session:
err = self._base_task_pipeline._handle_error(
event=event, session=session, message_id=self._message_id
)
session.commit()
yield self._error_to_stream_response(err)
yield self._base_task_pipeline._error_to_stream_response(err)
break
elif isinstance(event, QueueWorkflowStartedEvent):
# override graph runtime state
graph_runtime_state = event.graph_runtime_state
with Session(db.engine) as session:
with Session(db.engine, expire_on_commit=False) as session:
# init workflow run
workflow_run = self._handle_workflow_run_start(
workflow_run = self._workflow_cycle_manager._handle_workflow_run_start(
session=session,
workflow_id=self._workflow_id,
user_id=self._user_id,
@@ -297,7 +295,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not message:
raise ValueError(f"Message not found: {self._message_id}")
message.workflow_run_id = workflow_run.id
workflow_start_resp = self._workflow_start_to_stream_response(
workflow_start_resp = self._workflow_cycle_manager._workflow_start_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
@@ -310,12 +308,14 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
workflow_node_execution = self._handle_workflow_node_execution_retried(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_retried(
session=session, workflow_run=workflow_run, event=event
)
node_retry_resp = self._workflow_node_retry_to_stream_response(
node_retry_resp = self._workflow_cycle_manager._workflow_node_retry_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -329,13 +329,15 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
workflow_node_execution = self._handle_node_execution_start(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
workflow_node_execution = self._workflow_cycle_manager._handle_node_execution_start(
session=session, workflow_run=workflow_run, event=event
)
node_start_resp = self._workflow_node_start_to_stream_response(
node_start_resp = self._workflow_cycle_manager._workflow_node_start_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -348,12 +350,16 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
elif isinstance(event, QueueNodeSucceededEvent):
# Record files if it's an answer node or end node
if event.node_type in [NodeType.ANSWER, NodeType.END]:
self._recorded_files.extend(self._fetch_files_from_node_outputs(event.outputs or {}))
self._recorded_files.extend(
self._workflow_cycle_manager._fetch_files_from_node_outputs(event.outputs or {})
)
with Session(db.engine) as session:
workflow_node_execution = self._handle_workflow_node_execution_success(session=session, event=event)
with Session(db.engine, expire_on_commit=False) as session:
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_success(
session=session, event=event
)
node_finish_resp = self._workflow_node_finish_to_stream_response(
node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -364,10 +370,12 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if node_finish_resp:
yield node_finish_resp
elif isinstance(event, QueueNodeFailedEvent | QueueNodeInIterationFailedEvent | QueueNodeExceptionEvent):
with Session(db.engine) as session:
workflow_node_execution = self._handle_workflow_node_execution_failed(session=session, event=event)
with Session(db.engine, expire_on_commit=False) as session:
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_failed(
session=session, event=event
)
node_finish_resp = self._workflow_node_finish_to_stream_response(
node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -381,13 +389,17 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
parallel_start_resp = self._workflow_parallel_branch_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
parallel_start_resp = (
self._workflow_cycle_manager._workflow_parallel_branch_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
)
yield parallel_start_resp
@@ -395,13 +407,17 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
parallel_finish_resp = self._workflow_parallel_branch_finished_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
parallel_finish_resp = (
self._workflow_cycle_manager._workflow_parallel_branch_finished_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
)
yield parallel_finish_resp
@@ -409,9 +425,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_start_resp = self._workflow_iteration_start_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_start_resp = self._workflow_cycle_manager._workflow_iteration_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -423,9 +441,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_next_resp = self._workflow_iteration_next_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_next_resp = self._workflow_cycle_manager._workflow_iteration_next_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -437,9 +457,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_finish_resp = self._workflow_iteration_completed_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_finish_resp = self._workflow_cycle_manager._workflow_iteration_completed_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -454,8 +476,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
if not graph_runtime_state:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_success(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_success(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -466,21 +488,23 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
trace_manager=trace_manager,
)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
yield workflow_finish_resp
self._queue_manager.publish(QueueAdvancedChatMessageEndEvent(), PublishFrom.TASK_PIPELINE)
self._base_task_pipeline._queue_manager.publish(
QueueAdvancedChatMessageEndEvent(), PublishFrom.TASK_PIPELINE
)
elif isinstance(event, QueueWorkflowPartialSuccessEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_partial_success(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_partial_success(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -491,21 +515,23 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
conversation_id=None,
trace_manager=trace_manager,
)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
yield workflow_finish_resp
self._queue_manager.publish(QueueAdvancedChatMessageEndEvent(), PublishFrom.TASK_PIPELINE)
self._base_task_pipeline._queue_manager.publish(
QueueAdvancedChatMessageEndEvent(), PublishFrom.TASK_PIPELINE
)
elif isinstance(event, QueueWorkflowFailedEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_failed(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -517,20 +543,22 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
trace_manager=trace_manager,
exceptions_count=event.exceptions_count,
)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
err_event = QueueErrorEvent(error=ValueError(f"Run failed: {workflow_run.error}"))
err = self._handle_error(event=err_event, session=session, message_id=self._message_id)
err = self._base_task_pipeline._handle_error(
event=err_event, session=session, message_id=self._message_id
)
session.commit()
yield workflow_finish_resp
yield self._error_to_stream_response(err)
yield self._base_task_pipeline._error_to_stream_response(err)
break
elif isinstance(event, QueueStopEvent):
if self._workflow_run_id and graph_runtime_state:
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_failed(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -541,7 +569,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
conversation_id=self._conversation_id,
trace_manager=trace_manager,
)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -555,18 +583,18 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
yield self._message_end_to_stream_response()
break
elif isinstance(event, QueueRetrieverResourcesEvent):
self._handle_retriever_resources(event)
self._message_cycle_manager._handle_retriever_resources(event)
with Session(db.engine) as session:
with Session(db.engine, expire_on_commit=False) as session:
message = self._get_message(session=session)
message.message_metadata = (
json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
)
session.commit()
elif isinstance(event, QueueAnnotationReplyEvent):
self._handle_annotation_reply(event)
self._message_cycle_manager._handle_annotation_reply(event)
with Session(db.engine) as session:
with Session(db.engine, expire_on_commit=False) as session:
message = self._get_message(session=session)
message.message_metadata = (
json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
@@ -587,23 +615,27 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
tts_publisher.publish(queue_message)
self._task_state.answer += delta_text
yield self._message_to_stream_response(
yield self._message_cycle_manager._message_to_stream_response(
answer=delta_text, message_id=self._message_id, from_variable_selector=event.from_variable_selector
)
elif isinstance(event, QueueMessageReplaceEvent):
# published by moderation
yield self._message_replace_to_stream_response(answer=event.text)
yield self._message_cycle_manager._message_replace_to_stream_response(answer=event.text)
elif isinstance(event, QueueAdvancedChatMessageEndEvent):
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
output_moderation_answer = self._handle_output_moderation_when_task_finished(self._task_state.answer)
output_moderation_answer = self._base_task_pipeline._handle_output_moderation_when_task_finished(
self._task_state.answer
)
if output_moderation_answer:
self._task_state.answer = output_moderation_answer
yield self._message_replace_to_stream_response(answer=output_moderation_answer)
yield self._message_cycle_manager._message_replace_to_stream_response(
answer=output_moderation_answer
)
# Save message
with Session(db.engine) as session:
with Session(db.engine, expire_on_commit=False) as session:
self._save_message(session=session, graph_runtime_state=graph_runtime_state)
session.commit()
@@ -621,7 +653,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
def _save_message(self, *, session: Session, graph_runtime_state: Optional[GraphRuntimeState] = None) -> None:
message = self._get_message(session=session)
message.answer = self._task_state.answer
message.provider_response_latency = time.perf_counter() - self._start_at
message.provider_response_latency = time.perf_counter() - self._base_task_pipeline._start_at
message.message_metadata = (
json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
)
@@ -685,20 +717,20 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
:param text: text
:return: True if output moderation should direct output, otherwise False
"""
if self._output_moderation_handler:
if self._output_moderation_handler.should_direct_output():
if self._base_task_pipeline._output_moderation_handler:
if self._base_task_pipeline._output_moderation_handler.should_direct_output():
# stop subscribe new token when output moderation should direct output
self._task_state.answer = self._output_moderation_handler.get_final_output()
self._queue_manager.publish(
self._task_state.answer = self._base_task_pipeline._output_moderation_handler.get_final_output()
self._base_task_pipeline._queue_manager.publish(
QueueTextChunkEvent(text=self._task_state.answer), PublishFrom.TASK_PIPELINE
)
self._queue_manager.publish(
self._base_task_pipeline._queue_manager.publish(
QueueStopEvent(stopped_by=QueueStopEvent.StopBy.OUTPUT_MODERATION), PublishFrom.TASK_PIPELINE
)
return True
else:
self._output_moderation_handler.append_new_token(text)
self._base_task_pipeline._output_moderation_handler.append_new_token(text)
return False
@@ -18,7 +18,7 @@ from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskSt
from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.ops.ops_trace_manager import TraceQueueManager
from extensions.ext_database import db
from factories import file_factory
@@ -245,7 +245,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
except ValidationError as e:
logger.exception("Validation Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
except (ValueError, InvokeError) as e:
except ValueError as e:
if dify_config.DEBUG:
logger.exception("Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
+1 -15
View File
@@ -55,20 +55,6 @@ class AgentChatAppRunner(AppRunner):
query = application_generate_entity.query
files = application_generate_entity.files
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=inputs,
files=files,
query=query,
)
memory = None
if application_generate_entity.conversation_id:
# get memory of conversation (read-only)
@@ -202,7 +188,7 @@ class AgentChatAppRunner(AppRunner):
# change function call strategy based on LLM model
llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
if not model_schema or not model_schema.features:
if not model_schema:
raise ValueError("Model schema not found")
if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
+1 -2
View File
@@ -167,8 +167,7 @@ class AppQueueManager:
else:
if isinstance(data, DeclarativeMeta) or hasattr(data, "_sa_instance_state"):
raise TypeError(
"Critical Error: Passing SQLAlchemy Model instances "
"that cause thread safety issues is not allowed."
"Critical Error: Passing SQLAlchemy Model instances that cause thread safety issues is not allowed."
)
-102
View File
@@ -15,10 +15,8 @@ from core.app.features.annotation_reply.annotation_reply import AnnotationReplyF
from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
from core.external_data_tool.external_data_fetch import ExternalDataFetch
from core.memory.token_buffer_memory import TokenBufferMemory
from core.model_manager import ModelInstance
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
from core.model_runtime.entities.message_entities import AssistantPromptMessage, PromptMessage
from core.model_runtime.entities.model_entities import ModelPropertyKey
from core.model_runtime.errors.invoke import InvokeBadRequestError
from core.moderation.input_moderation import InputModeration
from core.prompt.advanced_prompt_transform import AdvancedPromptTransform
@@ -31,106 +29,6 @@ if TYPE_CHECKING:
class AppRunner:
def get_pre_calculate_rest_tokens(
self,
app_record: App,
model_config: ModelConfigWithCredentialsEntity,
prompt_template_entity: PromptTemplateEntity,
inputs: Mapping[str, str],
files: Sequence["File"],
query: Optional[str] = None,
) -> int:
"""
Get pre calculate rest tokens
:param app_record: app record
:param model_config: model config entity
:param prompt_template_entity: prompt template entity
:param inputs: inputs
:param files: files
:param query: query
:return:
"""
# Invoke model
model_instance = ModelInstance(
provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
)
model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
max_tokens = 0
for parameter_rule in model_config.model_schema.parameter_rules:
if parameter_rule.name == "max_tokens" or (
parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
):
max_tokens = (
model_config.parameters.get(parameter_rule.name)
or model_config.parameters.get(parameter_rule.use_template or "")
) or 0
if model_context_tokens is None:
return -1
if max_tokens is None:
max_tokens = 0
# get prompt messages without memory and context
prompt_messages, stop = self.organize_prompt_messages(
app_record=app_record,
model_config=model_config,
prompt_template_entity=prompt_template_entity,
inputs=inputs,
files=files,
query=query,
)
prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
rest_tokens: int = model_context_tokens - max_tokens - prompt_tokens
if rest_tokens < 0:
raise InvokeBadRequestError(
"Query or prefix prompt is too long, you can reduce the prefix prompt, "
"or shrink the max token, or switch to a llm with a larger token limit size."
)
return rest_tokens
def recalc_llm_max_tokens(
self, model_config: ModelConfigWithCredentialsEntity, prompt_messages: list[PromptMessage]
):
# recalc max_tokens if sum(prompt_token + max_tokens) over model token limit
model_instance = ModelInstance(
provider_model_bundle=model_config.provider_model_bundle, model=model_config.model
)
model_context_tokens = model_config.model_schema.model_properties.get(ModelPropertyKey.CONTEXT_SIZE)
max_tokens = 0
for parameter_rule in model_config.model_schema.parameter_rules:
if parameter_rule.name == "max_tokens" or (
parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
):
max_tokens = (
model_config.parameters.get(parameter_rule.name)
or model_config.parameters.get(parameter_rule.use_template or "")
) or 0
if model_context_tokens is None:
return -1
if max_tokens is None:
max_tokens = 0
prompt_tokens = model_instance.get_llm_num_tokens(prompt_messages)
if prompt_tokens + max_tokens > model_context_tokens:
max_tokens = max(model_context_tokens - prompt_tokens, 16)
for parameter_rule in model_config.model_schema.parameter_rules:
if parameter_rule.name == "max_tokens" or (
parameter_rule.use_template and parameter_rule.use_template == "max_tokens"
):
model_config.parameters[parameter_rule.name] = max_tokens
def organize_prompt_messages(
self,
app_record: App,
+2 -2
View File
@@ -18,7 +18,7 @@ from core.app.apps.chat.generate_response_converter import ChatAppGenerateRespon
from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
from core.app.entities.app_invoke_entities import ChatAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.ops.ops_trace_manager import TraceQueueManager
from extensions.ext_database import db
from factories import file_factory
@@ -237,7 +237,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
except ValidationError as e:
logger.exception("Validation Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
except (ValueError, InvokeError) as e:
except ValueError as e:
if dify_config.DEBUG:
logger.exception("Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
-17
View File
@@ -50,20 +50,6 @@ class ChatAppRunner(AppRunner):
query = application_generate_entity.query
files = application_generate_entity.files
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=inputs,
files=files,
query=query,
)
memory = None
if application_generate_entity.conversation_id:
# get memory of conversation (read-only)
@@ -194,9 +180,6 @@ class ChatAppRunner(AppRunner):
if hosting_moderation_result:
return
# Re-calculate the max tokens if sum(prompt_token + max_tokens) over model token limit
self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
# Invoke model
model_instance = ModelInstance(
provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
@@ -17,7 +17,7 @@ from core.app.apps.completion.generate_response_converter import CompletionAppGe
from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
from core.app.entities.app_invoke_entities import CompletionAppGenerateEntity, InvokeFrom
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.ops.ops_trace_manager import TraceQueueManager
from extensions.ext_database import db
from factories import file_factory
@@ -214,7 +214,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
except ValidationError as e:
logger.exception("Validation Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
except (ValueError, InvokeError) as e:
except ValueError as e:
if dify_config.DEBUG:
logger.exception("Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
@@ -43,20 +43,6 @@ class CompletionAppRunner(AppRunner):
query = application_generate_entity.query
files = application_generate_entity.files
# Pre-calculate the number of tokens of the prompt messages,
# and return the rest number of tokens by model context token size limit and max token size limit.
# If the rest number of tokens is not enough, raise exception.
# Include: prompt template, inputs, query(optional), files(optional)
# Not Include: memory, external data, dataset context
self.get_pre_calculate_rest_tokens(
app_record=app_record,
model_config=application_generate_entity.model_conf,
prompt_template_entity=app_config.prompt_template,
inputs=inputs,
files=files,
query=query,
)
# organize all inputs and template to prompt messages
# Include: prompt template, inputs, query(optional), files(optional)
prompt_messages, stop = self.organize_prompt_messages(
@@ -152,9 +138,6 @@ class CompletionAppRunner(AppRunner):
if hosting_moderation_result:
return
# Re-calculate the max tokens if sum(prompt_token + max_tokens) over model token limit
self.recalc_llm_max_tokens(model_config=application_generate_entity.model_conf, prompt_messages=prompt_messages)
# Invoke model
model_instance = ModelInstance(
provider_model_bundle=application_generate_entity.model_conf.provider_model_bundle,
@@ -89,6 +89,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
Conversation.id == conversation_id,
Conversation.app_id == app_model.id,
Conversation.status == "normal",
Conversation.is_deleted.is_(False),
]
if isinstance(user, Account):
+3 -2
View File
@@ -20,7 +20,7 @@ from core.app.apps.workflow.generate_response_converter import WorkflowAppGenera
from core.app.apps.workflow.generate_task_pipeline import WorkflowAppGenerateTaskPipeline
from core.app.entities.app_invoke_entities import InvokeFrom, WorkflowAppGenerateEntity
from core.app.entities.task_entities import WorkflowAppBlockingResponse, WorkflowAppStreamResponse
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
from core.model_runtime.errors.invoke import InvokeAuthorizationError
from core.ops.ops_trace_manager import TraceQueueManager
from extensions.ext_database import db
from factories import file_factory
@@ -221,6 +221,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
single_iteration_run=WorkflowAppGenerateEntity.SingleIterationRunEntity(
node_id=node_id, inputs=args["inputs"]
),
workflow_run_id=str(uuid.uuid4()),
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
@@ -270,7 +271,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
except ValidationError as e:
logger.exception("Validation Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
except (ValueError, InvokeError) as e:
except ValueError as e:
if dify_config.DEBUG:
logger.exception("Error when generating")
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
@@ -1,7 +1,7 @@
import logging
import time
from collections.abc import Generator
from typing import Any, Optional, Union
from typing import Optional, Union
from sqlalchemy.orm import Session
@@ -58,7 +58,6 @@ from models.workflow import (
Workflow,
WorkflowAppLog,
WorkflowAppLogCreatedFrom,
WorkflowNodeExecution,
WorkflowRun,
WorkflowRunStatus,
)
@@ -66,16 +65,11 @@ from models.workflow import (
logger = logging.getLogger(__name__)
class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleManage):
class WorkflowAppGenerateTaskPipeline:
"""
WorkflowAppGenerateTaskPipeline is a class that generate stream output and state management for Application.
"""
_task_state: WorkflowTaskState
_application_generate_entity: WorkflowAppGenerateEntity
_workflow_system_variables: dict[SystemVariableKey, Any]
_wip_workflow_node_executions: dict[str, WorkflowNodeExecution]
def __init__(
self,
application_generate_entity: WorkflowAppGenerateEntity,
@@ -84,7 +78,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
user: Union[Account, EndUser],
stream: bool,
) -> None:
super().__init__(
self._base_task_pipeline = BasedGenerateTaskPipeline(
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
stream=stream,
@@ -101,19 +95,21 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
else:
raise ValueError(f"Invalid user type: {type(user)}")
self._workflow_cycle_manager = WorkflowCycleManage(
application_generate_entity=application_generate_entity,
workflow_system_variables={
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.USER_ID: user_session_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._application_generate_entity = application_generate_entity
self._workflow_id = workflow.id
self._workflow_features_dict = workflow.features_dict
self._workflow_system_variables = {
SystemVariableKey.FILES: application_generate_entity.files,
SystemVariableKey.USER_ID: user_session_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 = {}
self._workflow_run_id = ""
def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
@@ -122,7 +118,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
:return:
"""
generator = self._wrapper_process_stream_response(trace_manager=self._application_generate_entity.trace_manager)
if self._stream:
if self._base_task_pipeline._stream:
return self._to_stream_response(generator)
else:
return self._to_blocking_response(generator)
@@ -237,29 +233,29 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
"""
graph_runtime_state = None
for queue_message in self._queue_manager.listen():
for queue_message in self._base_task_pipeline._queue_manager.listen():
event = queue_message.event
if isinstance(event, QueuePingEvent):
yield self._ping_stream_response()
yield self._base_task_pipeline._ping_stream_response()
elif isinstance(event, QueueErrorEvent):
err = self._handle_error(event=event)
yield self._error_to_stream_response(err)
err = self._base_task_pipeline._handle_error(event=event)
yield self._base_task_pipeline._error_to_stream_response(err)
break
elif isinstance(event, QueueWorkflowStartedEvent):
# override graph runtime state
graph_runtime_state = event.graph_runtime_state
with Session(db.engine) as session:
with Session(db.engine, expire_on_commit=False) as session:
# init workflow run
workflow_run = self._handle_workflow_run_start(
workflow_run = self._workflow_cycle_manager._handle_workflow_run_start(
session=session,
workflow_id=self._workflow_id,
user_id=self._user_id,
created_by_role=self._created_by_role,
)
self._workflow_run_id = workflow_run.id
start_resp = self._workflow_start_to_stream_response(
start_resp = self._workflow_cycle_manager._workflow_start_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
@@ -271,12 +267,14 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
workflow_node_execution = self._handle_workflow_node_execution_retried(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_retried(
session=session, workflow_run=workflow_run, event=event
)
response = self._workflow_node_retry_to_stream_response(
response = self._workflow_cycle_manager._workflow_node_retry_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -290,12 +288,14 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
workflow_node_execution = self._handle_node_execution_start(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
workflow_node_execution = self._workflow_cycle_manager._handle_node_execution_start(
session=session, workflow_run=workflow_run, event=event
)
node_start_response = self._workflow_node_start_to_stream_response(
node_start_response = self._workflow_cycle_manager._workflow_node_start_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -306,9 +306,11 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if node_start_response:
yield node_start_response
elif isinstance(event, QueueNodeSucceededEvent):
with Session(db.engine) as session:
workflow_node_execution = self._handle_workflow_node_execution_success(session=session, event=event)
node_success_response = self._workflow_node_finish_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_success(
session=session, event=event
)
node_success_response = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -319,12 +321,12 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if node_success_response:
yield node_success_response
elif isinstance(event, QueueNodeFailedEvent | QueueNodeInIterationFailedEvent | QueueNodeExceptionEvent):
with Session(db.engine) as session:
workflow_node_execution = self._handle_workflow_node_execution_failed(
with Session(db.engine, expire_on_commit=False) as session:
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_failed(
session=session,
event=event,
)
node_failed_response = self._workflow_node_finish_to_stream_response(
node_failed_response = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
session=session,
event=event,
task_id=self._application_generate_entity.task_id,
@@ -339,13 +341,17 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
parallel_start_resp = self._workflow_parallel_branch_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
parallel_start_resp = (
self._workflow_cycle_manager._workflow_parallel_branch_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
)
yield parallel_start_resp
@@ -354,13 +360,17 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
parallel_finish_resp = self._workflow_parallel_branch_finished_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
parallel_finish_resp = (
self._workflow_cycle_manager._workflow_parallel_branch_finished_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
)
yield parallel_finish_resp
@@ -369,9 +379,11 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_start_resp = self._workflow_iteration_start_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_start_resp = self._workflow_cycle_manager._workflow_iteration_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -384,9 +396,11 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_next_resp = self._workflow_iteration_next_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_next_resp = self._workflow_cycle_manager._workflow_iteration_next_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -399,9 +413,11 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
with Session(db.engine) as session:
workflow_run = self._get_workflow_run(session=session, workflow_run_id=self._workflow_run_id)
iter_finish_resp = self._workflow_iteration_completed_to_stream_response(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._get_workflow_run(
session=session, workflow_run_id=self._workflow_run_id
)
iter_finish_resp = self._workflow_cycle_manager._workflow_iteration_completed_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -416,8 +432,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_success(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_success(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -431,7 +447,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
@@ -445,8 +461,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_partial_success(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_partial_success(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -461,7 +477,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
@@ -473,8 +489,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
if not graph_runtime_state:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine) as session:
workflow_run = self._handle_workflow_run_failed(
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
@@ -492,7 +508,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
workflow_finish_resp = self._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
+1 -1
View File
@@ -195,7 +195,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
# app config
app_config: WorkflowUIBasedAppConfig
workflow_run_id: Optional[str] = None
workflow_run_id: str
class SingleIterationRunEntity(BaseModel):
"""
@@ -15,7 +15,6 @@ from core.app.entities.queue_entities import (
from core.app.entities.task_entities import (
ErrorStreamResponse,
PingStreamResponse,
TaskState,
)
from core.errors.error import QuotaExceededError
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
@@ -30,22 +29,12 @@ class BasedGenerateTaskPipeline:
BasedGenerateTaskPipeline is a class that generate stream output and state management for Application.
"""
_task_state: TaskState
_application_generate_entity: AppGenerateEntity
def __init__(
self,
application_generate_entity: AppGenerateEntity,
queue_manager: AppQueueManager,
stream: bool,
) -> None:
"""
Initialize GenerateTaskPipeline.
:param application_generate_entity: application generate entity
:param queue_manager: queue manager
:param user: user
:param stream: stream
"""
self._application_generate_entity = application_generate_entity
self._queue_manager = queue_manager
self._start_at = time.perf_counter()
@@ -31,10 +31,19 @@ from services.annotation_service import AppAnnotationService
class MessageCycleManage:
_application_generate_entity: Union[
ChatAppGenerateEntity, CompletionAppGenerateEntity, AgentChatAppGenerateEntity, AdvancedChatAppGenerateEntity
]
_task_state: Union[EasyUITaskState, WorkflowTaskState]
def __init__(
self,
*,
application_generate_entity: Union[
ChatAppGenerateEntity,
CompletionAppGenerateEntity,
AgentChatAppGenerateEntity,
AdvancedChatAppGenerateEntity,
],
task_state: Union[EasyUITaskState, WorkflowTaskState],
) -> None:
self._application_generate_entity = application_generate_entity
self._task_state = task_state
def _generate_conversation_name(self, *, conversation_id: str, query: str) -> Optional[Thread]:
"""
@@ -136,7 +145,7 @@ class MessageCycleManage:
# get extension
if "." in message_file.url:
extension = f'.{message_file.url.split(".")[-1]}'
extension = f".{message_file.url.split('.')[-1]}"
if len(extension) > 10:
extension = ".bin"
else:

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