Compare commits

...

215 Commits
1.4.0 ... 1.4.2

Author SHA1 Message Date
-LAN-
acb2488fc8 chore(package): Bump version to 1.4.2 (#20897)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-11 16:28:36 +08:00
Yeuoly
d6d8cca053 refactor: replace compact response generation with length-prefixed response for backwards invocation api (#20903) 2025-06-11 16:01:50 +08:00
非法操作
f601093ccc fix: only enterprise version request app access mode (#20785) 2025-06-11 15:38:51 +08:00
Bowen Liang
0f3d4d0b6e chore: bump mypy to 1.16 (#20608) 2025-06-11 01:01:33 +08:00
Nite Knite
60777bc610 chore: update plugin publish link text (#20873) 2025-06-10 17:34:26 +08:00
Jyong
21a50e22d2 fix auto metadata filter (#20845) 2025-06-10 10:46:17 +02:00
HyaCinth
fc6e2d14a5 fix(web): optimize prompt change logic for LLM nodes (#20841) (#20865) 2025-06-10 09:04:10 +02:00
QuantumGhost
c439e82038 refactor(api): Decouple ParameterExtractorNode from LLMNode (#20843)
- Extract methods used by `ParameterExtractorNode` from `LLMNode` into a separate file.
- Convert `ParameterExtractorNode` into a subclass of `BaseNode`.
- Refactor code referencing the extracted methods to ensure functionality and clarity.
- Fixes the issue that `ParameterExtractorNode` returns error when executed.
- Fix relevant test cases.

Closes #20840.
2025-06-10 11:47:50 +08:00
QuantumGhost
a97ff587d2 fix(api): Resolve error encountered when executing QuestionClassifieNode (#20829)
The `QuestionClassifierNode` class extends `LLMNode`, meaning that, per the Liskov Substitution Principle, `QuestionClassifierNodeData` **SHOULD** be compatible in contexts where `LLMNodeData` is expected.

However, the absence of the `structured_output_enabled` attribute violates this principle, causing `QuestionClassifierNode` to fail during execution.

This commit implements a quick and temporary workaround. A proper resolution would involve refactoring to decouple `QuestionClassifierNode` from `LLMNode` to address the underlying design issue.

Fixes #20725.
2025-06-10 00:34:51 +08:00
Yeuoly
91144207e0 refactor(DSL imports): using organization/name/version to fetch DSL dependencies. (#20757) 2025-06-09 19:05:29 +08:00
Xiyuan Chen
0720bc7408 Feat/webapp verified sso main (#20494) 2025-06-09 17:19:53 +09:00
非法操作
ab62a9662c fix: some dark mode display incorrect (#20788) 2025-06-09 16:09:27 +08:00
NFish
d6a8af03b4 Fix/add webapp no permission page (#20819) 2025-06-09 15:44:49 +08:00
yihong
65c7c01d90 fix: clean up two unreachable code (#20773)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-06-07 23:06:46 +08:00
Bharat Ramanathan
e6e76852d5 Add support for W&B dedicated cloud instances in Weave tracing integration (#20765)
Co-authored-by: crazywoola <427733928@qq.com>
2025-06-07 23:06:23 +08:00
QuantumGhost
930c4cb609 feat(api): Adjust WorkflowDraftVariable and WorkflowNodeExecutionModel (#20746)
- Add `node_execution_id` column to `WorkflowDraftVariable`, allowing efficient implementation of 
  the "Reset to last run value" feature.
- Add additional index for `WorkflowNodeExecutionModel` to improve the performance of last run lookup.

Closes #20745.
2025-06-06 21:03:59 +08:00
Joel
0c8447fd0e fix: missing bot name in orchestrate (#20747) 2025-06-06 16:44:36 +08:00
jefferyvvv
37c3283450 fix: opensearch vector search falls back to keyword search (#20723)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
2025-06-06 16:29:15 +08:00
Joel
723b69cf8d chore: chart panel ui enhance (#20743) 2025-06-06 16:15:37 +08:00
Joel
85859b6723 feat: add browser list (#20717) 2025-06-06 10:53:57 +08:00
Bowen Liang
c1a13fa553 chore: replace pseudo-random generators with secrets module (#20616) 2025-06-06 10:48:28 +08:00
Joel
4f0c9fdf2b chore: remove repeat public api and service api panel (#20715) 2025-06-06 10:44:21 +08:00
jefferyvvv
4271602cfc fix: opensearch metadata filtering returns empty (#20701)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-06-06 09:10:01 +08:00
Bowen Liang
4f14d7c0ca chore: bump uv to 0.7.x (#20692) 2025-06-06 09:09:31 +08:00
Yeuoly
38554c5f3e fix(inner_api/plugin/wraps): refresh user model after creation in get user function (#20704) 2025-06-05 23:36:33 +08:00
jefferyvvv
138ad6e8b3 fix: opensearch fulltext search with metadata filtering dsl error (#20702)
Co-authored-by: wenjun.gu <wenjun.gu@envision-energy.com>
2025-06-05 23:09:00 +08:00
湛露先生
f76f70f0b6 Fix builtin_providers for tools. (#20697)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-06-05 23:05:50 +08:00
Nite Knite
7094680e23 feat: reorder app types (#20685) 2025-06-05 17:02:26 +08:00
KVOJJJin
59dc7c880e Fix: style of radio checked (#20681) 2025-06-05 15:47:42 +08:00
HaiyangP
3fb9b41fe5 A more concise and effective extractor for excel and csv files (#20625)
Co-authored-by: haiyangpengai <xxxx>
2025-06-05 14:59:55 +08:00
Novice
0ccf8cb23e fix: agent moderation not working (#20673) 2025-06-05 14:56:41 +08:00
minglu7
837f769960 fix: update text_to_audio method to send data as JSON (#20663) 2025-06-05 14:33:24 +08:00
github-actions[bot]
3367d4258d chore: translate i18n files (#20664)
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
2025-06-05 13:35:40 +08:00
GuanMu
d608be6e7f Add vscode debugger (#20668) 2025-06-05 13:35:32 +08:00
geosmart
de9c7f2ea4 Update template.zh.mdx-fix document update metadata body param (#20659) 2025-06-05 12:11:11 +08:00
XiaoBa
1fbbbb735d fix: the locale format(#20662) (#20665)
Co-authored-by: Xiaoba Yu <xb1823725853@gmail.com>
2025-06-05 11:07:54 +08:00
NFish
9915a70d7f Fix/webapp access scope (#20109) 2025-06-05 10:55:17 +08:00
Eric Guo
822298f69d Fix 500 error (#20614) 2025-06-05 10:29:13 +08:00
Arcaner
ad2f25875e fix(llm_node): update file variable mapping to use vision configs (#20417) 2025-06-05 09:58:24 +08:00
Abdullah AlOsaimi
ad8e79c440 assign dataset indexing_technique to args if not explicitly provided (#20597) 2025-06-05 09:47:57 +08:00
非法操作
f2dcfc976d feat: allow fill inputs from url params (#20630) 2025-06-05 09:44:41 +08:00
-LAN-
5ccfb1f4ba refactor: Improve model status handling and structured output (#20586)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-04 19:56:54 +08:00
Dongyu Li
92614765ff Feat/queue monitor (#20647) 2025-06-04 19:56:34 +08:00
sayThQ199
4f066454d0 fix(markdown): Ensure abbr: links render correctly in react-markdown v9+ (#20648) 2025-06-04 19:52:12 +08:00
quicksand
7ae5819c67 feat: plugin storage support volcengine tos (#20613) 2025-06-04 19:46:47 +08:00
Bowen Liang
2b0f3edcef chore: ensure web code consistency by applying pnpm fix (#20643) 2025-06-04 19:45:29 +08:00
非法操作
244687c9a7 fix: plugin update redcorner mark display incorrect (#20636) 2025-06-04 19:44:47 +08:00
Joel
d22c351221 chore: fix some security issues in markdown (#20639) 2025-06-04 15:56:29 +08:00
Abdullah AlOsaimi
006496f24e raise error when process_rule is required but missing (#20599) 2025-06-04 14:19:35 +08:00
kenwoodjw
01d500db14 fix: autocorrect everything in web (#20605)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
2025-06-04 14:12:24 +08:00
Novice
4ac3600f81 fix: update app tag error (#20618) 2025-06-04 13:55:00 +08:00
GuanMu
6aba223383 fix: adjust sticky header properties in Container component (#20624) 2025-06-04 13:54:30 +08:00
Bowen Liang
f1c19cda74 fix: unable to upload custom file in case of incorrect inffered by multiple extensions mapped from mime type with filename extension hints (#20559) 2025-06-04 13:20:57 +08:00
-LAN-
275e86a26c refactor: Removes tenant ID check from rate limit logic (#20585)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-03 18:56:38 +08:00
sayThQ199
077d627953 fix: ensure newlines around think tags for proper markdown rendering (#20594) 2025-06-03 18:56:09 +08:00
非法操作
ca0b268ae5 fix: variable aggregator with group and file raise exception (#20581) 2025-06-03 18:17:34 +08:00
crazywoola
25be7c1ad5 Revert "♻️ refactor(middleware): remove duplicate CSP header assignment" (#20592) 2025-06-03 17:43:48 +08:00
Bowen Liang
888cd86afd chore: prepare the plugin daemon base url to yarl URL ahead intstead of in every invocation (#20541) 2025-06-03 17:01:35 +08:00
Muttakin Islam Hasib
157d916154 ♻️ refactor(middleware): remove duplicate CSP header assignment (#20548) 2025-06-03 16:46:57 +08:00
Anshuman Saini
e40e9db39a fixes #19634 (#20545) 2025-06-03 16:38:48 +08:00
-LAN-
36f1b4b222 fix: Ensure model config integrity in retrieval processes (#20576)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-03 16:36:18 +08:00
-LAN-
257bf13fef refactor: Removes unused LLMMode value_of method (#20575)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-03 16:36:10 +08:00
-LAN-
957f5b212e fix: Upgrade Flask-Cors (#20577)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-03 16:35:34 +08:00
-LAN-
72fdafc180 refactor: Replaces direct DB session usage with context managers (#20569)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-06-03 16:16:06 +08:00
GuanMu
db83bfc53a chore: update pnpm version to 10.11.1 (#20573) 2025-06-03 15:21:53 +08:00
Joel
744159a079 fix: agent thought replaced by response text (#20571) 2025-06-03 14:54:42 +08:00
KVOJJJin
d6b30efe2c Fix/dark theme style issues (#20566) 2025-06-03 13:53:24 +08:00
zhaobingshuang
3f7aa38d77 fix: #20560 When elasticsearch is used as the vector database, the Retrieval Test fails to filter the data after setting the Score Threshold, and the score of the recalled results is empty (#20561) 2025-06-03 13:24:26 +08:00
Contrail
a145c2a8fe fix: ensure proper conversation role alternation for vLLM (#18837) 2025-06-03 12:47:39 +08:00
不如归去
c29cb503be Fix #20536: Force header in custom tool be string (#20537)
Co-authored-by: Peter Xin <iami@Artemis.local>
2025-06-02 18:09:01 +08:00
不如归去
8025ad0661 Fixes #20534: Allow $ref in parameter for custom tools (#20535)
Co-authored-by: Peter Xin <iami@Artemis.local>
2025-06-02 18:08:53 +08:00
Cheney Zhang
b4b59148dc check zilliz cloud of full-text search (#20519) 2025-06-02 18:04:13 +08:00
kenwoodjw
23c9f1b444 fix ts5097 (#20543)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
2025-06-02 18:02:50 +08:00
湛露先生
b33f8b47ca nacos config init , and force add ts parms. (#20526)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-06-01 10:17:40 +08:00
kurokobo
c26e1929d6 fix(housekeeping): exclude files that are used as app icons or avatar images from being removed (#20532) 2025-05-31 23:27:47 +08:00
Joel
e01d975b80 fix: the plugin order is not the same as passed to api in DSL (#20515) 2025-05-30 18:13:00 +08:00
-LAN-
92528360f9 fix: fetch tenant_id in other trace providers besides langfuse (#20495)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 17:15:49 +08:00
Davide Delbianco
1d9c90089c Amend color typo (#20497)
Co-authored-by: Davide Delbianco <davide.delbianco@zucchetti.it>
2025-05-30 15:27:30 +08:00
zxhlyh
e303417e04 fix: agent app tool update (#20490) 2025-05-30 14:56:32 +08:00
Kaitlyn Feng
c8d9f8e2e4 fix: resolve unstable scrolling in workflow debug panel with multiple input fields #19697 (#19698) 2025-05-30 14:54:30 +08:00
Ganondorf
51f64797cd Add APIs for Knowledge Base Tag Management and Dataset Binding (#20023)
Co-authored-by: lizb <lizb@sugon.com>
2025-05-30 14:48:00 +08:00
Dongyu Li
1ea4459d9f update knowledge base api (#20426) 2025-05-30 14:45:30 +08:00
Yasuhiro Ohno
55371e5abf Improve CONVERSATION_TITLE_PROMPT to correctly handle Japanese and input (#20351) 2025-05-30 14:43:51 +08:00
Jyong
fb12a3033d fix celery job not closed issue (#19268) 2025-05-30 14:42:47 +08:00
-LAN-
a6ea15e63c Refactor/message cycle manage and knowledge retrieval (#20460)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 14:36:44 +08:00
yihong
5a991295e0 fix: drop some type fixme (#20344) 2025-05-30 14:10:09 +08:00
Wu Tianwei
9b47f9f786 fix(json-schema-editor): Add container reference for resize observer in CodeEditor; Update language hook and help doc URL in JsonSchemaConfig (#20488) 2025-05-30 13:54:12 +08:00
sayThQ199
f65c2fcb1d Refactor/markdown component split (#20177) 2025-05-30 11:31:50 +08:00
非法操作
156bb8238d fix: some display error in dark mode (#20469) 2025-05-30 11:25:46 +08:00
-LAN-
db488bef51 refactor(api/core/workflow/enums): Rename WORKFLOW_RUN_ID to WORKFLOW_EXECUTION_ID (#20459)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 11:05:08 +08:00
github-actions[bot]
d72d02b970 chore: translate i18n files (#20476)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-05-30 10:57:37 +08:00
非法操作
dd2725be68 fix: import from curl not work for --data (#20471) 2025-05-30 10:52:38 +08:00
crazywoola
8e2d342de6 Feat/15534 support replacing the bot in chat input placeholder with the bots name (#20473) 2025-05-30 10:51:19 +08:00
Davide Delbianco
91eeb2ab76 chore: Colorize new OpenAI LLM versions (#20463)
Co-authored-by: Davide Delbianco <davide.delbianco@zucchetti.it>
2025-05-30 09:24:31 +08:00
-LAN-
f2e0d161a1 fix(ops_trace_manager): Adds app_id to TraceTask initialization (#20461)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 09:00:05 +08:00
-LAN-
2ebf4e767b fix(models): WorkflowRun's total_steps and exceptions_count mismatch with database (#20452)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 07:53:13 +08:00
-LAN-
f7fb10635f refactor(workflow): Rename workflow node execution models (#20458)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 04:56:37 +08:00
-LAN-
32e779eef3 refactor(workflow): Rename NodeRunMetadataKey to WorkflowNodeExecutionMetadataKey (#20457)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 04:47:56 +08:00
-LAN-
482e50aae9 Refactor/remove db from cycle manager (#20455)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 04:34:13 +08:00
-LAN-
cd0a05f114 tests: Removes outdated marketplace download test (#20454)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-30 01:57:55 +08:00
Yeuoly
d4408e0f54 fix: handle values in output arrays for CodeNode transformation (#20437) 2025-05-29 17:55:20 +08:00
Bowen Liang
eee88a8012 chore: improve error logging for requests to plugin daemon (#20328) 2025-05-29 17:12:27 +08:00
crazywoola
0368e1769a fix: wrong env usage in middleware (#20436) 2025-05-29 17:10:49 +08:00
quicksand
2d4f8f1377 fix: apps/annotation missing 1 required positional argument: 'end_user' (#20428) 2025-05-29 16:10:28 +08:00
NFish
8ef91222ea fix: show 'reset brand' button after set branding image (#20420) 2025-05-29 15:13:00 +08:00
-LAN-
808aa4467c docs: Update PR template to emphasize guidelines and issue linking (#20382)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-29 14:32:08 +08:00
Novice
b2ab401279 chore: remove agent turn limits (#19930) 2025-05-29 09:51:56 +08:00
Novice
9bbd646f40 fix: inner invoke llm token too long (#20391) 2025-05-29 09:49:44 +08:00
NFish
57ece83c30 Fix/branding broken (#20375)
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
2025-05-28 20:06:58 +08:00
-LAN-
c3c67d9608 fix: register user model to current_user in backward invoke. (#20374)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-28 19:56:33 +08:00
-LAN-
f59fb94dae feat(agent_node): ensure that the enum-checking syntax is compatible with Python 3.11. (#20373)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-28 19:56:17 +08:00
zxhlyh
00199c41bb fix: workflow plugins list update (#20357) 2025-05-28 17:45:08 +08:00
teawoong Kim
400ae664bb fix(http): force multipart/form-data even without files(#20322) (#20323) 2025-05-28 17:04:38 +08:00
comfuture
b39ca7ee31 Fixes some i18n(ko) translations. (#20348) 2025-05-28 16:58:59 +08:00
Junjie.M
4250501058 fix: reset password page dark style (#20350) 2025-05-28 16:36:32 +08:00
-LAN-
eaaf551497 fix: Instance <Account> is not bound to a Session (#20347)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-28 16:36:08 +08:00
-LAN-
f233a64eb5 fix(workflow): fetch user failed when workflow run in parallel mode (#20321)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 22:41:07 +08:00
AichiB7A
2b81b6673f [Observability] Add type check and try-except in otel (#20319) 2025-05-27 21:17:45 +08:00
-LAN-
4c46f04d77 fix: Enhances tenant ID handling in telemetry (#20304)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 17:44:40 +08:00
Joel
d467c8536b fix: i18n auto run failed (#20302) 2025-05-27 17:29:56 +08:00
Joel
abc32edf28 chore: enchance the copywriting of tool (#20294) 2025-05-27 16:40:11 +08:00
crazywoola
047a1b5166 Chore/update img (#20292) 2025-05-27 16:33:43 +08:00
crazywoola
a06fa7374d update img (#20291) 2025-05-27 16:30:04 +08:00
-LAN-
fe01de5667 chore(*): Bump version to 1.4.1 (#20275)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 15:32:59 +08:00
-LAN-
275b042998 chore(remove_app_and_related_data_task): Revert _delete_app_workflow_node_executions (#20278)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 14:58:08 +08:00
rouxiaomin
4c4887c5fc feat(qdrant):add replication_factor when create collection in qdrant (#20133)
Co-authored-by: 刘敏 <min.liu@tongdun.net>
2025-05-27 14:46:04 +08:00
Mio Inamijima
0ebaba98f0 fix: dataset permission check for partial team members (#19249) (#20242)
Co-authored-by: MioINAMIJIMA <m.inamijima@optimaize-consulting.com>
2025-05-27 14:33:11 +08:00
-LAN-
d3bfcd498b fix: Refactor web reader to use readabilipy (#19789)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 14:17:32 +08:00
GQ1994
efad1e4790 Modifying the preview of the uploaded avatar will freeze, fix the bug… (#20202)
Co-authored-by: qingguo <qingguo@lexin.com>
2025-05-27 14:04:22 +08:00
-LAN-
9c9d3d7bd0 feat: document extractor chardet encoding (#20269)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 13:27:46 +08:00
Good Wood
756f35f480 feat: add pagination for plugin page (#20151) 2025-05-27 12:54:52 +08:00
-LAN-
55503ce771 fix: persist workflow execution status on partial success and failure (#20264)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 11:24:08 +08:00
Dongyu Li
c57726a587 fix[cve]: update qdrant-client from 1.7.3 to 1.9.0 (#20231) 2025-05-27 11:08:26 +08:00
zxhlyh
b12c28a984 fix: workflow http node (#20262) 2025-05-27 11:05:38 +08:00
-LAN-
b357eca307 fix: Copy request context and current user in app generators. (#20240)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-27 10:56:23 +08:00
非法操作
acd4b9a8ac fix: not save workflow_run_id of chatflow message (#20257) 2025-05-27 10:43:22 +08:00
GuanMu
ded4b024f3 Fix dataseat card height (#20239) 2025-05-27 09:42:29 +08:00
-LAN-
f21e6e03a3 refactor: Consolidate Flask-Login Authentication Logic (#20235)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-26 18:22:01 +08:00
Good Wood
6f982eb7e4 feat: add author_name for app list card (#16900)
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-05-26 18:20:53 +08:00
cooper.wu
2cad98f01f fix: #18132 when deepseek llm model, auto_generate name can't work (#18646)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2025-05-26 18:04:52 +08:00
HyaCinth
eb26dc3213 fix: Remove the custom comparison function from the memo HOC(#19679) (#20197) 2025-05-26 18:04:25 +08:00
CorrectRoad
405c4d51f0 feat: clean chunk content after add (#19785) 2025-05-26 17:53:50 +08:00
GuanMu
3e30914e13 feat: add alias for production web start command (#20229) 2025-05-26 16:52:56 +08:00
HyaCinth
53aaf91ce4 fix: show two PromptLogModal when click log button (#20115) (#20142) 2025-05-26 16:45:10 +08:00
Heyang Wang
b9b5d43dc6 fix: add 'floatfmt' when extract number from excel ( #20153 ) (#20193)
Co-authored-by: wangheyang <wangheyang@corp.netease.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-26 16:41:57 +08:00
yihong
38e48c0c40 doc: tiny fix github -> GitHub (#20185)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-05-26 16:33:12 +08:00
Good Wood
84679f1a5b fix: prevent save when default max_iteration has value in agent node (#20211) 2025-05-26 16:28:29 +08:00
GonzaHM
4c7351176c fix: resolve Mermaid mindmap generation issue (#20227) 2025-05-26 16:26:56 +08:00
Joel
ba7a2fd135 fix: can not show loop detail in one step run (#20215) 2025-05-26 14:23:11 +08:00
Wu Tianwei
3995f55cbc fix: update Line component for dark mode support and improve Empty co… (#20196)
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-26 10:42:54 +08:00
sayThQ199
cbfc32b11f fix(echarts): Resolve chart flickering and animation loop in Markdown (#20161) 2025-05-25 18:05:41 +08:00
非法操作
9b1dc1de7a fix: system file upload can't export custom file types (#20122) 2025-05-22 22:29:27 +08:00
非法操作
db09d18e92 fix: some dark theme not display well (#20121) 2025-05-22 22:29:12 +08:00
wellCh4n
210b9ebf56 fix: GitHub stars count sync not working (#20126) 2025-05-22 22:28:43 +08:00
Chenhe Gu
fa80ef90d2 simplify app create experience with collapsed basic app types and imp… (#20007) 2025-05-22 18:02:40 +08:00
NFish
6c492e51fa fix: update messages credita (#20092) 2025-05-22 17:39:28 +08:00
sayThQ199
7bf00ef25c fix(markdown): improve ECharts rendering for streaming content and da… (#20101)
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-22 16:31:13 +08:00
He Wang
8fad3036bf set oceanbase ip to 127.0.0.1 to avoid connection failure after restart (#20103) 2025-05-22 16:19:53 +08:00
Boris Feld
c939f04b1a Add support for tracking conversation with Opik Tracer (#20063) 2025-05-22 16:11:50 +08:00
Nite Knite
916c415b4b feat: add entry point for requesting a plugin (#20026) 2025-05-22 14:15:00 +08:00
Boris Feld
9afd7f6c87 chore: Update S3StorageConfig to match boto3 type hints (#20072) 2025-05-22 14:10:14 +08:00
jameshui1997
648393cc7b fix: improve tracing provider validation logic in OpsTraceManager (#20042) 2025-05-22 14:08:36 +08:00
He Huang
6f48af2610 Refactor OpenSearch config to separate use_ssl and verify_certs flags (#20075)
Co-authored-by: he.huang <he.huang1@outlook.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-22 10:14:38 +08:00
zhudongwork
adca981eee fix: uninitialized variable error on empty knowledge retrieval(agent) (#20025)
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-22 10:09:07 +08:00
GonzaHM
38b1e46241 fix: correct indentation in dataset retrieval model assignment (#20040) 2025-05-22 10:05:24 +08:00
-LAN-
6b3666f826 feat: Split WorkflowCycleManager (#20071)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-22 09:49:25 +08:00
heyszt
02929b2cce Fix/fix trace provider delete err (#20070) 2025-05-21 23:51:42 +08:00
-LAN-
d31235ca13 feat: Introduce WorkflowExecution Domain Entity and Repository, Replace WorkflowRun Direct Usage, and Unify Stream Response Logic (#20067)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-21 22:01:53 +08:00
wlleiiwang
7d230acf40 tencent vectordb compatible with version 1.1.3 and below (#20056)
Co-authored-by: wlleiiwang <wlleiiwang@tencent.com>
2025-05-21 20:24:05 +08:00
QuantumGhost
13dc1c8795 Simplify execution_metadata Handling for WorkflowNodeExecution (#20062)
Currently, `WorkflowNodeExecution.execution_metadata_dict` returns `None` when metadata is absent in the database. This requires all callers to perform `None` checks when processing metadata, leading to more complex caller-side logic.

This pull request updates the `execution_metadata_dict` method to return an empty dictionary instead of `None` when metadata is absent. This change would simplify the caller logic, as it removes the need for explicit `None` checks and provides a more consistent data structure to work with.
2025-05-21 18:38:16 +08:00
Hanqing Zhao
997b46bfaa Fix/modify translation (#20046) 2025-05-21 16:41:05 +08:00
-LAN-
57bcb616bc fix(sqlalchemy_workflow_node_execution_repository): Missing triggered_from while querying WorkflowNodeExecution (#20044)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-21 16:37:44 +08:00
-LAN-
3196dc2d61 refactor: Use typed SQLAlchemy base model and fix type errors (#19980)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-21 15:38:03 +08:00
Panpan
ef3569e667 feat: support chatflow start node custom input field hidden (#19678) 2025-05-21 13:52:21 +08:00
wellCh4n
627911d4ff feat: Move to node in workflow panel and fix help link hover style (#19998) 2025-05-21 11:29:24 +08:00
quicksand
2266f7cb6a Feat:Plugin Storage Type Support Aliyun OSS (#20012) 2025-05-21 11:28:47 +08:00
crazywoola
a0ebbaa840 fix: emoji picker in dark mode (#20019) 2025-05-21 11:23:26 +08:00
俊晨
36b321735e fix create_tracing_app_config error (#19884) (#20004)
Co-authored-by: codly <codly.fun@gmail.com>
2025-05-21 10:45:10 +08:00
crazywoola
75cacc2855 fix: ReactFlow background in dark theme (#20013) 2025-05-21 10:32:07 +08:00
NFish
83e71ab27c fix: update IN SERVICE status text in app detail panel (#19993) 2025-05-21 10:16:21 +08:00
crazywoola
d35d854259 Revert "fix: fix duplicate app lose custom image" (#19995) 2025-05-20 18:42:59 +08:00
luckylhb90
c58678d84d chore: Reduce the invocation of the plugin interface (#19629)
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-20 16:55:21 +08:00
CorrectRoad
618981f1ae fix: fix duplicate app lose custom image (#19775) 2025-05-20 16:44:51 +08:00
crazywoola
b2ae46b80f fix: search query and refine the logic (#19987) 2025-05-20 16:42:37 +08:00
ruanjiefeng
9ebc58b1a2 feat: Web <video> and <audio> element support src attribute (#19988) 2025-05-20 16:37:31 +08:00
Zihe JI
87f9d11d65 fix: ensure Decimal values in metadata are JSON serializable (fixes #19936) (#19955)
Co-authored-by: crazywoola <427733928@qq.com>
2025-05-20 15:38:31 +08:00
Darlewo
8cb3b4aef2 fix: multiple retrieve reranking_enabled switch (#19958) 2025-05-20 15:22:03 +08:00
Good Wood
09547b4c8d fix: fix page broken for undefined permission (#19972) 2025-05-20 14:41:10 +08:00
NFish
d186daa131 E-300 (#19726)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Hash Brown <hi@xzd.me>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: GareArc <chen4851@purdue.edu>
Co-authored-by: Byron.wang <byron@dify.ai>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Garfield Dai <dai.hai@foxmail.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: Alexi.F <654973939@qq.com>
Co-authored-by: Xiyuan Chen <52963600+GareArc@users.noreply.github.com>
Co-authored-by: kautsar_masuara <61046989+izon-masuara@users.noreply.github.com>
Co-authored-by: achmad-kautsar <achmad.kautsar@insignia.co.id>
Co-authored-by: Xin Zhang <sjhpzx@gmail.com>
Co-authored-by: kelvintsim <83445753+kelvintsim@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Zixuan Cheng <61724187+Theysua@users.noreply.github.com>
2025-05-20 12:07:50 +08:00
Raina Otoni
6a8ca8296b chore: update redis dependency to version 6.1.0 in api/pyproject.toml (#19885) 2025-05-20 10:45:03 +08:00
crazywoola
7ae529c3b0 Revert "chore: upgrade Redis from v6 to v7 in middlewares" (#19960) 2025-05-20 10:44:53 +08:00
湛露先生
911f9eadd0 fix model workflow_draft_variables duplicate app_id set. (#19949)
Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>
2025-05-20 10:26:34 +08:00
Amir Mohsen Asaran
c9ee60e197 Feat(WaterCrawl error handling): add custom exceptions and error handling (#19948) 2025-05-20 10:25:16 +08:00
yeyunwen
4e5789df89 docs: Optimize Response data array object indentation for the /messages interface (#19922) 2025-05-20 10:23:48 +08:00
Bowen Liang
a18a6f50ab chore: upgrade Redis from v6 to v7 in middlewares (#19935) 2025-05-20 09:36:21 +08:00
wellCh4n
276c02f341 feat: Variable click jumps to source node (#13623) 2025-05-19 23:17:18 +08:00
QuantumGhost
6a9e0b1005 feat(api): Introduce WorkflowDraftVariable Model (#19737)
- Introduce `WorkflowDraftVariable` model and the corresponding migration.
- Implement `EnumText`,  a custom column type for SQLAlchemy designed
  to work seamlessly with enumeration classes based on `StrEnum`.
2025-05-19 22:59:56 +08:00
非法操作
bbebf9ad3e fix: db_model save to _node_execution_cache (#19911) 2025-05-19 17:17:43 +08:00
heyszt
11146b6bae fix create_tracing_app_config error (#19884) 2025-05-19 10:09:21 +08:00
非法操作
499392c6f9 chore: improve some doc (#19881) 2025-05-18 21:42:03 +08:00
yeyunwen
a287da9ccd docs: Add text_to_speech left out in the API response (#19862) 2025-05-18 12:59:15 +08:00
dave
c22e640df3 fix(devcontainer): uv sync fail (#19834) 2025-05-18 12:58:45 +08:00
Junjie.M
2862631f03 fix: tool node number type constant field dark style (#19818) 2025-05-18 12:58:22 +08:00
非法操作
749bcc889b fix: nav selector's dark theme (#19869) 2025-05-18 12:51:09 +08:00
Hashcon
6a74c97a0a feat: add debug log for request and response (#19781) (#19783)
Co-authored-by: hashjang <hash@geek.com>
Co-authored-by: QuantumGhost <obelisk.reg+git@gmail.com>
2025-05-17 17:31:09 +08:00
-LAN-
e0e8cd6ca3 feat(DraftWorkflowApi): Requires environment_variables in DraftWorkflowApi (#19849)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-17 13:45:00 +08:00
GQ1994
e7659ecd9d revert https://github.com/langgenius/dify/pull/19497 (19497) (#19807)
Co-authored-by: qingguo <qingguo@lexin.com>
2025-05-17 12:32:27 +08:00
-LAN-
7d0106b220 fix: correct type mismatch in WorkflowService node execution handling (#19846)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-05-17 12:31:27 +08:00
Joel
df631591f2 fix: upload avatar failed (#19853) 2025-05-17 10:55:12 +08:00
-LAN-
4977bb21ec feat(workflow): domain model for workflow node execution (#19430)
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-05-17 00:56:16 +08:00
Junjie.M
aeceb200ec fix: llm parameters radio type dark style (#19833) 2025-05-16 20:45:15 +08:00
CorrectRoad
a15129a00c fix: fix overflow when bot description too long (#19805) 2025-05-16 14:35:22 +08:00
CorrectRoad
de2cfd2927 fix: fix metadata condition name overflow (#19812) 2025-05-16 14:33:14 +08:00
KVOJJJin
8bf9adbc08 Fix: style of app publisher (#19803) 2025-05-16 14:32:30 +08:00
Emmanuel Ferdman
582b721160 Resolve Python Logger library warnings (#19791)
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-05-16 14:31:54 +08:00
828 changed files with 20702 additions and 9481 deletions

View File

@@ -1,5 +1,4 @@
FROM mcr.microsoft.com/devcontainers/python:3.12
# [Optional] Uncomment this section to install additional OS packages.
# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
# && apt-get -y install --no-install-recommends <your-package-list-here>
RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
&& apt-get -y install libgmp-dev libmpfr-dev libmpc-dev

View File

@@ -1,12 +1,13 @@
#!/bin/bash
npm add -g pnpm@10.8.0
npm add -g pnpm@10.11.1
cd web && pnpm install
pipx install uv
echo 'alias start-api="cd /workspaces/dify/api && uv run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
echo 'alias start-worker="cd /workspaces/dify/api && uv run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
echo 'alias start-web="cd /workspaces/dify/web && pnpm dev"' >> ~/.bashrc
echo 'alias start-web-prod="cd /workspaces/dify/web && pnpm build && pnpm start"' >> ~/.bashrc
echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env up -d"' >> ~/.bashrc
echo 'alias stop-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify --env-file middleware.env down"' >> ~/.bashrc

View File

@@ -8,7 +8,7 @@ inputs:
uv-version:
description: UV version to set up
required: true
default: '0.6.14'
default: '~=0.7.11'
uv-lockfile:
description: Path to the UV lockfile to restore cache from
required: true

View File

@@ -1,25 +1,23 @@
# Summary
> [!IMPORTANT]
>
> 1. Make sure you have read our [contribution guidelines](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)
> 2. Ensure there is an associated issue and you have been assigned to it
> 3. Use the correct syntax to link this PR: `Fixes #<issue number>`.
Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.
## Summary
> [!Tip]
> Close issue syntax: `Fixes #<issue number>` or `Resolves #<issue number>`, see [documentation](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) for more details.
<!-- Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change. -->
# Screenshots
## Screenshots
| Before | After |
|--------|-------|
| ... | ... |
# Checklist
> [!IMPORTANT]
> Please review the checklist below before submitting your pull request.
## Checklist
- [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs)
- [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
- [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
- [x] I've updated the documentation accordingly.
- [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods

View File

@@ -139,6 +139,7 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0
persist-credentials: false
- name: Check changed files

View File

@@ -31,11 +31,19 @@ jobs:
echo "FILES_CHANGED=false" >> $GITHUB_ENV
fi
- name: Install pnpm
uses: pnpm/action-setup@v4
with:
version: 10
run_install: false
- name: Set up Node.js
if: env.FILES_CHANGED == 'true'
uses: actions/setup-node@v4
with:
node-version: 'lts/*'
cache: pnpm
cache-dependency-path: ./web/package.json
- name: Install dependencies
if: env.FILES_CHANGED == 'true'

7
.gitignore vendored
View File

@@ -192,12 +192,12 @@ sdks/python-client/dist
sdks/python-client/dify_client.egg-info
.vscode/*
!.vscode/launch.json
!.vscode/launch.json.template
!.vscode/README.md
pyrightconfig.json
api/.vscode
.idea/
.vscode
# pnpm
/.pnpm-store
@@ -207,3 +207,6 @@ plugins.jsonl
# mise
mise.toml
# Next.js build output
.next/

14
.vscode/README.md vendored Normal file
View File

@@ -0,0 +1,14 @@
# Debugging with VS Code
This `launch.json.template` file provides various debug configurations for the Dify project within VS Code / Cursor. To use these configurations, you should copy the contents of this file into a new file named `launch.json` in the same `.vscode` directory.
## How to Use
1. **Create `launch.json`**: If you don't have one, create a file named `launch.json` inside the `.vscode` directory.
2. **Copy Content**: Copy the entire content from `launch.json.template` into your newly created `launch.json` file.
3. **Select Debug Configuration**: Go to the Run and Debug view in VS Code / Cursor (Ctrl+Shift+D or Cmd+Shift+D).
4. **Start Debugging**: Select the desired configuration from the dropdown menu and click the green play button.
## Tips
- If you need to debug with Edge browser instead of Chrome, modify the `serverReadyAction` configuration in the "Next.js: debug full stack" section, change `"debugWithChrome"` to `"debugWithEdge"` to use Microsoft Edge for debugging.

68
.vscode/launch.json.template vendored Normal file
View File

@@ -0,0 +1,68 @@
{
"version": "0.2.0",
"configurations": [
{
"name": "Python: Flask API",
"type": "debugpy",
"request": "launch",
"module": "flask",
"env": {
"FLASK_APP": "app.py",
"FLASK_ENV": "development",
"GEVENT_SUPPORT": "True"
},
"args": [
"run",
"--host=0.0.0.0",
"--port=5001",
"--no-debugger",
"--no-reload"
],
"jinja": true,
"justMyCode": true,
"cwd": "${workspaceFolder}/api",
"python": "${workspaceFolder}/api/.venv/bin/python"
},
{
"name": "Python: Celery Worker (Solo)",
"type": "debugpy",
"request": "launch",
"module": "celery",
"env": {
"GEVENT_SUPPORT": "True"
},
"args": [
"-A",
"app.celery",
"worker",
"-P",
"solo",
"-c",
"1",
"-Q",
"dataset,generation,mail,ops_trace",
"--loglevel",
"INFO"
],
"justMyCode": false,
"cwd": "${workspaceFolder}/api",
"python": "${workspaceFolder}/api/.venv/bin/python"
},
{
"name": "Next.js: debug full stack",
"type": "node",
"request": "launch",
"program": "${workspaceFolder}/web/node_modules/next/dist/bin/next",
"runtimeArgs": ["--inspect"],
"skipFiles": ["<node_internals>/**"],
"serverReadyAction": {
"action": "debugWithChrome",
"killOnServerStop": true,
"pattern": "- Local:.+(https?://.+)",
"uriFormat": "%s",
"webRoot": "${workspaceFolder}/web"
},
"cwd": "${workspaceFolder}/web"
}
]
}

View File

@@ -235,7 +235,7 @@ At the same time, please consider supporting Dify by sharing it on social media
## Community & contact
- [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
- [GitHub Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
- [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
- [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
- [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.

View File

@@ -223,7 +223,7 @@ docker compose up -d
</a>
## المجتمع والاتصال
- [مناقشة Github](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
- [مناقشة GitHub](https://github.com/langgenius/dify/discussions). الأفضل لـ: مشاركة التعليقات وطرح الأسئلة.
- [المشكلات على GitHub](https://github.com/langgenius/dify/issues). الأفضل لـ: الأخطاء التي تواجهها في استخدام Dify.AI، واقتراحات الميزات. انظر [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
- [Discord](https://discord.gg/FngNHpbcY7). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.
- [تويتر](https://twitter.com/dify_ai). الأفضل لـ: مشاركة تطبيقاتك والترفيه مع المجتمع.

View File

@@ -234,7 +234,7 @@ GitHub-এ ডিফাইকে স্টার দিয়ে রাখুন
## কমিউনিটি এবং যোগাযোগ
- [Github Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
- [GitHub Discussion](https://github.com/langgenius/dify/discussions) ফিডব্যাক এবং প্রতিক্রিয়া জানানোর মাধ্যম।
- [GitHub Issues](https://github.com/langgenius/dify/issues). Dify.AI ব্যবহার করে আপনি যেসব বাগের সম্মুখীন হন এবং ফিচার প্রস্তাবনা। আমাদের [অবদান নির্দেশিকা](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) দেখুন।
- [Discord](https://discord.gg/FngNHpbcY7) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম।
- [X(Twitter)](https://twitter.com/dify_ai) আপনার এপ্লিকেশন শেয়ার এবং কমিউনিটি আড্ডার মাধ্যম।

View File

@@ -243,7 +243,7 @@ docker compose up -d
我们欢迎您为 Dify 做出贡献,以帮助改善 Dify。包括提交代码、问题、新想法或分享您基于 Dify 创建的有趣且有用的 AI 应用程序。同时,我们也欢迎您在不同的活动、会议和社交媒体上分享 Dify。
- [Github Discussion](https://github.com/langgenius/dify/discussions). 👉:分享您的应用程序并与社区交流。
- [GitHub Discussion](https://github.com/langgenius/dify/discussions). 👉:分享您的应用程序并与社区交流。
- [GitHub Issues](https://github.com/langgenius/dify/issues)。👉:使用 Dify.AI 时遇到的错误和问题,请参阅[贡献指南](CONTRIBUTING.md)。
- [电子邮件支持](mailto:hello@dify.ai?subject=[GitHub]Questions%20About%20Dify)。👉:关于使用 Dify.AI 的问题。
- [Discord](https://discord.gg/FngNHpbcY7)。👉:分享您的应用程序并与社区交流。

View File

@@ -230,7 +230,7 @@ Falls Sie Code beitragen möchten, lesen Sie bitte unseren [Contribution Guide](
## Gemeinschaft & Kontakt
* [Github Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Am besten geeignet für: den Austausch von Feedback und das Stellen von Fragen.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Am besten für: Fehler, auf die Sie bei der Verwendung von Dify.AI stoßen, und Funktionsvorschläge. Siehe unseren [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.
* [X(Twitter)](https://twitter.com/dify_ai). Am besten geeignet für: den Austausch von Bewerbungen und den Austausch mit der Community.

View File

@@ -236,7 +236,7 @@ docker compose up -d
## コミュニティ & お問い合わせ
* [Github Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
* [GitHub Discussion](https://github.com/langgenius/dify/discussions). 主に: フィードバックの共有や質問。
* [GitHub Issues](https://github.com/langgenius/dify/issues). 主に: Dify.AIを使用する際に発生するエラーや問題については、[貢献ガイド](CONTRIBUTING_JA.md)を参照してください
* [Discord](https://discord.gg/FngNHpbcY7). 主に: アプリケーションの共有やコミュニティとの交流。
* [X(Twitter)](https://twitter.com/dify_ai). 主に: アプリケーションの共有やコミュニティとの交流。

View File

@@ -235,7 +235,7 @@ At the same time, please consider supporting Dify by sharing it on social media
## Community & Contact
* [Github Discussion](https://github.com/langgenius/dify/discussions
* [GitHub Discussion](https://github.com/langgenius/dify/discussions
). Best for: sharing feedback and asking questions.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).

View File

@@ -229,7 +229,7 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
## 커뮤니티 & 연락처
* [Github 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
* [GitHub 토론](https://github.com/langgenius/dify/discussions). 피드백 공유 및 질문하기에 적합합니다.
* [GitHub 이슈](https://github.com/langgenius/dify/issues). Dify.AI 사용 중 발견한 버그와 기능 제안에 적합합니다. [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.
* [디스코드](https://discord.gg/FngNHpbcY7). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.
* [트위터](https://twitter.com/dify_ai). 애플리케이션 공유 및 커뮤니티와 소통하기에 적합합니다.

View File

@@ -229,7 +229,7 @@ Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkra
## Skupnost in stik
* [Github Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
* [GitHub Discussion](https://github.com/langgenius/dify/discussions). Najboljše za: izmenjavo povratnih informacij in postavljanje vprašanj.
* [GitHub Issues](https://github.com/langgenius/dify/issues). Najboljše za: hrošče, na katere naletite pri uporabi Dify.AI, in predloge funkcij. Oglejte si naš [vodnik za prispevke](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
* [Discord](https://discord.gg/FngNHpbcY7). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.
* [X(Twitter)](https://twitter.com/dify_ai). Najboljše za: deljenje vaših aplikacij in druženje s skupnostjo.

View File

@@ -227,7 +227,7 @@ Aynı zamanda, lütfen Dify'ı sosyal medyada, etkinliklerde ve konferanslarda p
## Topluluk & iletişim
* [Github Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
* [GitHub Tartışmaları](https://github.com/langgenius/dify/discussions). En uygun: geri bildirim paylaşmak ve soru sormak için.
* [GitHub Sorunları](https://github.com/langgenius/dify/issues). En uygun: Dify.AI kullanırken karşılaştığınız hatalar ve özellik önerileri için. [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakın.
* [Discord](https://discord.gg/FngNHpbcY7). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.
* [X(Twitter)](https://twitter.com/dify_ai). En uygun: uygulamalarınızı paylaşmak ve toplulukla vakit geçirmek için.

View File

@@ -233,7 +233,7 @@ Dify 的所有功能都提供相應的 API因此您可以輕鬆地將 Dify
## 社群與聯絡方式
- [Github Discussion](https://github.com/langgenius/dify/discussions):最適合分享反饋和提問。
- [GitHub Discussion](https://github.com/langgenius/dify/discussions):最適合分享反饋和提問。
- [GitHub Issues](https://github.com/langgenius/dify/issues):最適合報告使用 Dify.AI 時遇到的問題和提出功能建議。請參閱我們的[貢獻指南](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)。
- [Discord](https://discord.gg/FngNHpbcY7):最適合分享您的應用程式並與社群互動。
- [X(Twitter)](https://twitter.com/dify_ai):最適合分享您的應用程式並與社群互動。

View File

@@ -152,6 +152,7 @@ QDRANT_API_KEY=difyai123456
QDRANT_CLIENT_TIMEOUT=20
QDRANT_GRPC_ENABLED=false
QDRANT_GRPC_PORT=6334
QDRANT_REPLICATION_FACTOR=1
#Couchbase configuration
COUCHBASE_CONNECTION_STRING=127.0.0.1
@@ -269,6 +270,7 @@ OPENSEARCH_PORT=9200
OPENSEARCH_USER=admin
OPENSEARCH_PASSWORD=admin
OPENSEARCH_SECURE=true
OPENSEARCH_VERIFY_CERTS=true
# Baidu configuration
BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287
@@ -348,6 +350,7 @@ SENTRY_DSN=
# DEBUG
DEBUG=false
ENABLE_REQUEST_LOGGING=False
SQLALCHEMY_ECHO=false
# Notion import configuration, support public and internal
@@ -488,3 +491,10 @@ OTEL_METRIC_EXPORT_TIMEOUT=30000
# Prevent Clickjacking
ALLOW_EMBED=false
# Dataset queue monitor configuration
QUEUE_MONITOR_THRESHOLD=200
# You can configure multiple ones, separated by commas. eg: test1@dify.ai,test2@dify.ai
QUEUE_MONITOR_ALERT_EMAILS=
# Monitor interval in minutes, default is 30 minutes
QUEUE_MONITOR_INTERVAL=30

View File

@@ -43,6 +43,7 @@ select = [
"S307", # suspicious-eval-usage, disallow use of `eval` and `ast.literal_eval`
"S301", # suspicious-pickle-usage, disallow use of `pickle` and its wrappers.
"S302", # suspicious-marshal-usage, disallow use of `marshal` module
"S311", # suspicious-non-cryptographic-random-usage
]
ignore = [

View File

@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
WORKDIR /app/api
# Install uv
ENV UV_VERSION=0.6.14
ENV UV_VERSION=0.7.11
RUN pip install --no-cache-dir uv==${UV_VERSION}

View File

@@ -54,6 +54,7 @@ def initialize_extensions(app: DifyApp):
ext_otel,
ext_proxy_fix,
ext_redis,
ext_request_logging,
ext_sentry,
ext_set_secretkey,
ext_storage,
@@ -83,6 +84,7 @@ def initialize_extensions(app: DifyApp):
ext_blueprints,
ext_commands,
ext_otel,
ext_request_logging,
]
for ext in extensions:
short_name = ext.__name__.split(".")[-1]

View File

@@ -846,6 +846,9 @@ def clear_orphaned_file_records(force: bool):
{"type": "text", "table": "workflow_node_executions", "column": "outputs"},
{"type": "text", "table": "conversations", "column": "introduction"},
{"type": "text", "table": "conversations", "column": "system_instruction"},
{"type": "text", "table": "accounts", "column": "avatar"},
{"type": "text", "table": "apps", "column": "icon"},
{"type": "text", "table": "sites", "column": "icon"},
{"type": "json", "table": "messages", "column": "inputs"},
{"type": "json", "table": "messages", "column": "message"},
]

View File

@@ -17,6 +17,12 @@ class DeploymentConfig(BaseSettings):
default=False,
)
# Request logging configuration
ENABLE_REQUEST_LOGGING: bool = Field(
description="Enable request and response body logging",
default=False,
)
EDITION: str = Field(
description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
default="SELF_HOSTED",

View File

@@ -2,7 +2,7 @@ import os
from typing import Any, Literal, Optional
from urllib.parse import parse_qsl, quote_plus
from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
from pydantic import Field, NonNegativeFloat, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
from pydantic_settings import BaseSettings
from .cache.redis_config import RedisConfig
@@ -256,6 +256,25 @@ class InternalTestConfig(BaseSettings):
)
class DatasetQueueMonitorConfig(BaseSettings):
"""
Configuration settings for Dataset Queue Monitor
"""
QUEUE_MONITOR_THRESHOLD: Optional[NonNegativeInt] = Field(
description="Threshold for dataset queue monitor",
default=200,
)
QUEUE_MONITOR_ALERT_EMAILS: Optional[str] = Field(
description="Emails for dataset queue monitor alert, separated by commas",
default=None,
)
QUEUE_MONITOR_INTERVAL: Optional[NonNegativeFloat] = Field(
description="Interval for dataset queue monitor in minutes",
default=30,
)
class MiddlewareConfig(
# place the configs in alphabet order
CeleryConfig,
@@ -303,5 +322,6 @@ class MiddlewareConfig(
BaiduVectorDBConfig,
OpenGaussConfig,
TableStoreConfig,
DatasetQueueMonitorConfig,
):
pass

View File

@@ -1,4 +1,4 @@
from typing import Optional
from typing import Literal, Optional
from pydantic import Field
from pydantic_settings import BaseSettings
@@ -34,7 +34,7 @@ class S3StorageConfig(BaseSettings):
default=None,
)
S3_ADDRESS_STYLE: str = Field(
S3_ADDRESS_STYLE: Literal["auto", "virtual", "path"] = Field(
description="S3 addressing style: 'auto', 'path', or 'virtual'",
default="auto",
)

View File

@@ -33,6 +33,11 @@ class OpenSearchConfig(BaseSettings):
default=False,
)
OPENSEARCH_VERIFY_CERTS: bool = Field(
description="Whether to verify SSL certificates for HTTPS connections (recommended to set True in production)",
default=True,
)
OPENSEARCH_AUTH_METHOD: AuthMethod = Field(
description="Authentication method for OpenSearch connection (default is 'basic')",
default=AuthMethod.BASIC,

View File

@@ -33,3 +33,8 @@ class QdrantConfig(BaseSettings):
description="Port number for gRPC connection to Qdrant server (default is 6334)",
default=6334,
)
QDRANT_REPLICATION_FACTOR: PositiveInt = Field(
description="Replication factor for Qdrant collections (default is 1)",
default=1,
)

View File

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
CURRENT_VERSION: str = Field(
description="Dify version",
default="1.4.0",
default="1.4.2",
)
COMMIT_SHA: str = Field(

View File

@@ -60,8 +60,7 @@ class NacosHttpClient:
sign_str = tenant + "+"
if group:
sign_str = sign_str + group + "+"
if sign_str:
sign_str += ts
sign_str += ts # Directly concatenate ts without conditional checks, because the nacos auth header forced it.
return sign_str
def get_access_token(self, force_refresh=False):

View File

@@ -11,10 +11,6 @@ if TYPE_CHECKING:
from core.workflow.entities.variable_pool import VariablePool
tenant_id: ContextVar[str] = ContextVar("tenant_id")
workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
"""
To avoid race-conditions caused by gunicorn thread recycling, using RecyclableContextVar to replace with
"""

View File

@@ -208,7 +208,7 @@ class AnnotationBatchImportApi(Resource):
if len(request.files) > 1:
raise TooManyFilesError()
# check file type
if not file.filename.endswith(".csv"):
if not file.filename or not file.filename.endswith(".csv"):
raise ValueError("Invalid file type. Only CSV files are allowed")
return AppAnnotationService.batch_import_app_annotations(app_id, file)

View File

@@ -17,15 +17,13 @@ from controllers.console.wraps import (
)
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"]
@@ -75,7 +73,17 @@ class AppListApi(Resource):
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
@@ -119,6 +127,10 @@ 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

View File

@@ -81,8 +81,7 @@ class DraftWorkflowApi(Resource):
parser.add_argument("graph", type=dict, required=True, nullable=False, location="json")
parser.add_argument("features", type=dict, required=True, nullable=False, location="json")
parser.add_argument("hash", type=str, required=False, location="json")
# TODO: set this to required=True after frontend is updated
parser.add_argument("environment_variables", type=list, required=False, location="json")
parser.add_argument("environment_variables", type=list, required=True, location="json")
parser.add_argument("conversation_variables", type=list, required=False, location="json")
args = parser.parse_args()
elif "text/plain" in content_type:

View File

@@ -6,12 +6,12 @@ from sqlalchemy.orm import Session
from controllers.console import api
from controllers.console.app.wraps import get_app_model
from controllers.console.wraps import account_initialization_required, setup_required
from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
from extensions.ext_database import db
from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
from libs.login import login_required
from models import App
from models.model import AppMode
from models.workflow import WorkflowRunStatus
from services.workflow_app_service import WorkflowAppService
@@ -38,7 +38,7 @@ class WorkflowAppLogApi(Resource):
parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
args = parser.parse_args()
args.status = WorkflowRunStatus(args.status) if args.status else None
args.status = WorkflowExecutionStatus(args.status) if args.status else None
if args.created_at__before:
args.created_at__before = isoparse(args.created_at__before)

View File

@@ -1,3 +1,6 @@
from typing import cast
from flask_login import current_user
from flask_restful import Resource, marshal_with, reqparse
from flask_restful.inputs import int_range
@@ -12,8 +15,7 @@ from fields.workflow_run_fields import (
)
from libs.helper import uuid_value
from libs.login import login_required
from models import App
from models.model import AppMode
from models import Account, App, AppMode, EndUser
from services.workflow_run_service import WorkflowRunService
@@ -90,7 +92,12 @@ class WorkflowRunNodeExecutionListApi(Resource):
run_id = str(run_id)
workflow_run_service = WorkflowRunService()
node_executions = workflow_run_service.get_workflow_run_node_executions(app_model=app_model, run_id=run_id)
user = cast("Account | EndUser", current_user)
node_executions = workflow_run_service.get_workflow_run_node_executions(
app_model=app_model,
run_id=run_id,
user=user,
)
return {"data": node_executions}

View File

@@ -24,7 +24,7 @@ from libs.password import hash_password, valid_password
from models.account import Account
from services.account_service import AccountService, TenantService
from services.errors.account import AccountRegisterError
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
from services.feature_service import FeatureService
@@ -168,6 +168,8 @@ class ForgotPasswordResetApi(Resource):
)
except WorkSpaceNotAllowedCreateError:
pass
except WorkspacesLimitExceededError:
pass
except AccountRegisterError:
raise AccountInFreezeError()

View File

@@ -21,6 +21,7 @@ from controllers.console.error import (
AccountNotFound,
EmailSendIpLimitError,
NotAllowedCreateWorkspace,
WorkspacesLimitExceeded,
)
from controllers.console.wraps import email_password_login_enabled, setup_required
from events.tenant_event import tenant_was_created
@@ -30,7 +31,7 @@ from models.account import Account
from services.account_service import AccountService, RegisterService, TenantService
from services.billing_service import BillingService
from services.errors.account import AccountRegisterError
from services.errors.workspace import WorkSpaceNotAllowedCreateError
from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkspacesLimitExceededError
from services.feature_service import FeatureService
@@ -88,10 +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"])
@@ -196,15 +202,18 @@ class EmailCodeLoginApi(Resource):
except AccountRegisterError as are:
raise AccountInFreezeError()
if account:
tenant = TenantService.get_join_tenants(account)
if not tenant:
tenants = TenantService.get_join_tenants(account)
if not tenants:
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:
tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(tenant, account, role="owner")
account.current_tenant = tenant
tenant_was_created.send(tenant)
new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(new_tenant, account, role="owner")
account.current_tenant = new_tenant
tenant_was_created.send(new_tenant)
if account is None:
try:
@@ -215,6 +224,8 @@ class EmailCodeLoginApi(Resource):
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()}

View File

@@ -148,15 +148,15 @@ def _generate_account(provider: str, user_info: OAuthUserInfo):
account = _get_account_by_openid_or_email(provider, user_info)
if account:
tenant = TenantService.get_join_tenants(account)
if not tenant:
tenants = TenantService.get_join_tenants(account)
if not tenants:
if not FeatureService.get_system_features().is_allow_create_workspace:
raise WorkSpaceNotAllowedCreateError()
else:
tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(tenant, account, role="owner")
account.current_tenant = tenant
tenant_was_created.send(tenant)
new_tenant = TenantService.create_tenant(f"{account.name}'s Workspace")
TenantService.create_tenant_member(new_tenant, account, role="owner")
account.current_tenant = new_tenant
tenant_was_created.send(new_tenant)
if not account:
if not FeatureService.get_system_features().is_allow_register:

View File

@@ -540,9 +540,22 @@ class DatasetIndexingStatusApi(Resource):
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
documents_status.append(marshal(document, document_status_fields))
# Create a dictionary with document attributes and additional fields
document_dict = {
"id": document.id,
"indexing_status": document.indexing_status,
"processing_started_at": document.processing_started_at,
"parsing_completed_at": document.parsing_completed_at,
"cleaning_completed_at": document.cleaning_completed_at,
"splitting_completed_at": document.splitting_completed_at,
"completed_at": document.completed_at,
"paused_at": document.paused_at,
"error": document.error,
"stopped_at": document.stopped_at,
"completed_segments": completed_segments,
"total_segments": total_segments,
}
documents_status.append(marshal(document_dict, document_status_fields))
data = {"data": documents_status}
return data

View File

@@ -583,11 +583,22 @@ class DocumentBatchIndexingStatusApi(DocumentResource):
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused:
document.indexing_status = "paused"
documents_status.append(marshal(document, document_status_fields))
# Create a dictionary with document attributes and additional fields
document_dict = {
"id": document.id,
"indexing_status": "paused" if document.is_paused else document.indexing_status,
"processing_started_at": document.processing_started_at,
"parsing_completed_at": document.parsing_completed_at,
"cleaning_completed_at": document.cleaning_completed_at,
"splitting_completed_at": document.splitting_completed_at,
"completed_at": document.completed_at,
"paused_at": document.paused_at,
"error": document.error,
"stopped_at": document.stopped_at,
"completed_segments": completed_segments,
"total_segments": total_segments,
}
documents_status.append(marshal(document_dict, document_status_fields))
data = {"data": documents_status}
return data
@@ -616,11 +627,22 @@ class DocumentIndexingStatusApi(DocumentResource):
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused:
document.indexing_status = "paused"
return marshal(document, document_status_fields)
# Create a dictionary with document attributes and additional fields
document_dict = {
"id": document.id,
"indexing_status": "paused" if document.is_paused else document.indexing_status,
"processing_started_at": document.processing_started_at,
"parsing_completed_at": document.parsing_completed_at,
"cleaning_completed_at": document.cleaning_completed_at,
"splitting_completed_at": document.splitting_completed_at,
"completed_at": document.completed_at,
"paused_at": document.paused_at,
"error": document.error,
"stopped_at": document.stopped_at,
"completed_segments": completed_segments,
"total_segments": total_segments,
}
return marshal(document_dict, document_status_fields)
class DocumentDetailApi(DocumentResource):

View File

@@ -374,7 +374,7 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
if len(request.files) > 1:
raise TooManyFilesError()
# check file type
if not file.filename.endswith(".csv"):
if not file.filename or not file.filename.endswith(".csv"):
raise ValueError("Invalid file type. Only CSV files are allowed")
try:

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."

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

View File

@@ -1,3 +1,4 @@
import logging
from datetime import UTC, datetime
from typing import Any
@@ -15,6 +16,11 @@ 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
logger = logging.getLogger(__name__)
class InstalledAppsListApi(Resource):
@@ -48,6 +54,28 @@ 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
logger.debug(f"installed_app_list: {installed_app_list}, user_id: {user_id}")
installed_app_list.sort(
key=lambda app: (
-app["is_pinned"],

View File

@@ -4,10 +4,14 @@ from flask_login import current_user
from flask_restful import Resource
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 +52,36 @@ 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,
]

View File

@@ -6,6 +6,7 @@ from flask_restful import Resource, abort, marshal_with, reqparse
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(

View File

@@ -41,12 +41,16 @@ class PluginListApi(Resource):
@account_initialization_required
def get(self):
tenant_id = current_user.current_tenant_id
parser = reqparse.RequestParser()
parser.add_argument("page", type=int, required=False, location="args", default=1)
parser.add_argument("page_size", type=int, required=False, location="args", default=256)
args = parser.parse_args()
try:
plugins = PluginService.list(tenant_id)
plugins_with_total = PluginService.list_with_total(tenant_id, args["page"], args["page_size"])
except PluginDaemonClientSideError as e:
raise ValueError(e)
return jsonable_encoder({"plugins": plugins})
return jsonable_encoder({"plugins": plugins_with_total.list, "total": plugins_with_total.total})
class PluginListLatestVersionsApi(Resource):

View File

@@ -68,16 +68,24 @@ class TenantListApi(Resource):
@account_initialization_required
def get(self):
tenants = TenantService.get_join_tenants(current_user)
tenant_dicts = []
for tenant in tenants:
features = FeatureService.get_features(tenant.id)
if features.billing.enabled:
tenant.plan = features.billing.subscription.plan
else:
tenant.plan = "sandbox"
if tenant.id == current_user.current_tenant_id:
tenant.current = True # Set current=True for current tenant
return {"workspaces": marshal(tenants, tenants_fields)}, 200
# Create a dictionary with tenant attributes
tenant_dict = {
"id": tenant.id,
"name": tenant.name,
"status": tenant.status,
"created_at": tenant.created_at,
"plan": features.billing.subscription.plan if features.billing.enabled else "sandbox",
"current": tenant.id == current_user.current_tenant_id,
}
tenant_dicts.append(tenant_dict)
return {"workspaces": marshal(tenant_dicts, tenants_fields)}, 200
class WorkspaceListApi(Resource):

View File

@@ -44,6 +44,17 @@ 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):

View File

@@ -64,9 +64,24 @@ class PluginUploadFileApi(Resource):
extension = guess_extension(tool_file.mimetype) or ".bin"
preview_url = ToolFileManager.sign_file(tool_file_id=tool_file.id, extension=extension)
tool_file.mime_type = mimetype
tool_file.extension = extension
tool_file.preview_url = preview_url
# Create a dictionary with all the necessary attributes
result = {
"id": tool_file.id,
"user_id": tool_file.user_id,
"tenant_id": tool_file.tenant_id,
"conversation_id": tool_file.conversation_id,
"file_key": tool_file.file_key,
"mimetype": tool_file.mimetype,
"original_url": tool_file.original_url,
"name": tool_file.name,
"size": tool_file.size,
"mime_type": mimetype,
"extension": extension,
"preview_url": preview_url,
}
return result, 201
except services.errors.file.FileTooLargeError as file_too_large_error:
raise FileTooLargeError(file_too_large_error.description)
except services.errors.file.UnsupportedFileTypeError:

View File

@@ -5,5 +5,6 @@ from libs.external_api import ExternalApi
bp = Blueprint("inner_api", __name__, url_prefix="/inner/api")
api = ExternalApi(bp)
from . import mail
from .plugin import plugin
from .workspace import workspace

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 enterprise_inner_api_only
from services.enterprise.mail_service import DifyMail, EnterpriseMailService
class EnterpriseMail(Resource):
@setup_required
@enterprise_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")

View File

@@ -29,7 +29,7 @@ from core.plugin.entities.request import (
RequestRequestUploadFile,
)
from core.tools.entities.tool_entities import ToolProviderType
from libs.helper import compact_generate_response
from libs.helper import length_prefixed_response
from models.account import Account, Tenant
from models.model import EndUser
@@ -44,7 +44,7 @@ class PluginInvokeLLMApi(Resource):
response = PluginModelBackwardsInvocation.invoke_llm(user_model.id, tenant_model, payload)
return PluginModelBackwardsInvocation.convert_to_event_stream(response)
return compact_generate_response(generator())
return length_prefixed_response(0xF, generator())
class PluginInvokeTextEmbeddingApi(Resource):
@@ -101,7 +101,7 @@ class PluginInvokeTTSApi(Resource):
)
return PluginModelBackwardsInvocation.convert_to_event_stream(response)
return compact_generate_response(generator())
return length_prefixed_response(0xF, generator())
class PluginInvokeSpeech2TextApi(Resource):
@@ -162,7 +162,7 @@ class PluginInvokeToolApi(Resource):
),
)
return compact_generate_response(generator())
return length_prefixed_response(0xF, generator())
class PluginInvokeParameterExtractorNodeApi(Resource):
@@ -228,7 +228,7 @@ class PluginInvokeAppApi(Resource):
files=payload.files,
)
return compact_generate_response(PluginAppBackwardsInvocation.convert_to_event_stream(response))
return length_prefixed_response(0xF, PluginAppBackwardsInvocation.convert_to_event_stream(response))
class PluginInvokeEncryptApi(Resource):

View File

@@ -2,12 +2,14 @@ from collections.abc import Callable
from functools import wraps
from typing import Optional
from flask import request
from flask import current_app, request
from flask_login import user_logged_in
from flask_restful import reqparse
from pydantic import BaseModel
from sqlalchemy.orm import Session
from extensions.ext_database import db
from libs.login import _get_user
from models.account import Account, Tenant
from models.model import EndUser
from services.account_service import AccountService
@@ -30,6 +32,7 @@ def get_user(tenant_id: str, user_id: str | None) -> Account | EndUser:
)
session.add(user_model)
session.commit()
session.refresh(user_model)
else:
user_model = AccountService.load_user(user_id)
if not user_model:
@@ -80,7 +83,12 @@ def get_user_tenant(view: Optional[Callable] = None):
raise ValueError("tenant not found")
kwargs["tenant_model"] = tenant_model
kwargs["user_model"] = get_user(tenant_id, user_id)
user = get_user(tenant_id, user_id)
kwargs["user_model"] = user
current_app.login_manager._update_request_context_with_user(user) # type: ignore
user_logged_in.send(current_app._get_current_object(), user=_get_user()) # type: ignore
return view_func(*args, **kwargs)

View File

@@ -3,19 +3,19 @@ from flask_restful import Resource, marshal, marshal_with, reqparse
from werkzeug.exceptions import Forbidden
from controllers.service_api import api
from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
from controllers.service_api.wraps import validate_app_token
from extensions.ext_redis import redis_client
from fields.annotation_fields import (
annotation_fields,
)
from libs.login import current_user
from models.model import App, EndUser
from models.model import App
from services.annotation_service import AppAnnotationService
class AnnotationReplyActionApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
def post(self, app_model: App, end_user: EndUser, action):
@validate_app_token
def post(self, app_model: App, action):
parser = reqparse.RequestParser()
parser.add_argument("score_threshold", required=True, type=float, location="json")
parser.add_argument("embedding_provider_name", required=True, type=str, location="json")
@@ -31,8 +31,8 @@ class AnnotationReplyActionApi(Resource):
class AnnotationReplyActionStatusApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
def get(self, app_model: App, end_user: EndUser, job_id, action):
@validate_app_token
def get(self, app_model: App, job_id, action):
job_id = str(job_id)
app_annotation_job_key = "{}_app_annotation_job_{}".format(action, str(job_id))
cache_result = redis_client.get(app_annotation_job_key)
@@ -49,8 +49,8 @@ class AnnotationReplyActionStatusApi(Resource):
class AnnotationListApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
def get(self, app_model: App, end_user: EndUser):
@validate_app_token
def get(self, app_model: App):
page = request.args.get("page", default=1, type=int)
limit = request.args.get("limit", default=20, type=int)
keyword = request.args.get("keyword", default="", type=str)
@@ -65,9 +65,9 @@ class AnnotationListApi(Resource):
}
return response, 200
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
@validate_app_token
@marshal_with(annotation_fields)
def post(self, app_model: App, end_user: EndUser):
def post(self, app_model: App):
parser = reqparse.RequestParser()
parser.add_argument("question", required=True, type=str, location="json")
parser.add_argument("answer", required=True, type=str, location="json")
@@ -77,9 +77,9 @@ class AnnotationListApi(Resource):
class AnnotationUpdateDeleteApi(Resource):
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
@validate_app_token
@marshal_with(annotation_fields)
def put(self, app_model: App, end_user: EndUser, annotation_id):
def put(self, app_model: App, annotation_id):
if not current_user.is_editor:
raise Forbidden()
@@ -91,8 +91,8 @@ class AnnotationUpdateDeleteApi(Resource):
annotation = AppAnnotationService.update_app_annotation_directly(args, app_model.id, annotation_id)
return annotation
@validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.QUERY))
def delete(self, app_model: App, end_user: EndUser, annotation_id):
@validate_app_token
def delete(self, app_model: App, annotation_id):
if not current_user.is_editor:
raise Forbidden()

View File

@@ -24,12 +24,13 @@ from core.errors.error import (
QuotaExceededError,
)
from core.model_runtime.errors.invoke import InvokeError
from core.workflow.entities.workflow_execution import WorkflowExecutionStatus
from extensions.ext_database import db
from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
from libs import helper
from libs.helper import TimestampField
from models.model import App, AppMode, EndUser
from models.workflow import WorkflowRun, WorkflowRunStatus
from models.workflow import WorkflowRun
from services.app_generate_service import AppGenerateService
from services.errors.llm import InvokeRateLimitError
from services.workflow_app_service import WorkflowAppService
@@ -138,7 +139,7 @@ class WorkflowAppLogApi(Resource):
parser.add_argument("limit", type=int_range(1, 100), default=20, location="args")
args = parser.parse_args()
args.status = WorkflowRunStatus(args.status) if args.status else None
args.status = WorkflowExecutionStatus(args.status) if args.status else None
if args.created_at__before:
args.created_at__before = isoparse(args.created_at__before)

View File

@@ -1,19 +1,21 @@
from flask import request
from flask_restful import marshal, reqparse
from flask_restful import marshal, marshal_with, reqparse
from werkzeug.exceptions import Forbidden, NotFound
import services.dataset_service
from controllers.service_api import api
from controllers.service_api.dataset.error import DatasetInUseError, DatasetNameDuplicateError
from controllers.service_api.wraps import DatasetApiResource
from controllers.service_api.wraps import DatasetApiResource, validate_dataset_token
from core.model_runtime.entities.model_entities import ModelType
from core.plugin.entities.plugin import ModelProviderID
from core.provider_manager import ProviderManager
from fields.dataset_fields import dataset_detail_fields
from fields.tag_fields import tag_fields
from libs.login import current_user
from models.dataset import Dataset, DatasetPermissionEnum
from services.dataset_service import DatasetPermissionService, DatasetService
from services.entities.knowledge_entities.knowledge_entities import RetrievalModel
from services.tag_service import TagService
def _validate_name(name):
@@ -320,5 +322,135 @@ class DatasetApi(DatasetApiResource):
raise DatasetInUseError()
class DatasetTagsApi(DatasetApiResource):
@validate_dataset_token
@marshal_with(tag_fields)
def get(self, _, dataset_id):
"""Get all knowledge type tags."""
tags = TagService.get_tags("knowledge", current_user.current_tenant_id)
return tags, 200
@validate_dataset_token
def post(self, _, dataset_id):
"""Add a knowledge type tag."""
if not (current_user.is_editor or current_user.is_dataset_editor):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument(
"name",
nullable=False,
required=True,
help="Name must be between 1 to 50 characters.",
type=DatasetTagsApi._validate_tag_name,
)
args = parser.parse_args()
args["type"] = "knowledge"
tag = TagService.save_tags(args)
response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": 0}
return response, 200
@validate_dataset_token
def patch(self, _, dataset_id):
if not (current_user.is_editor or current_user.is_dataset_editor):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument(
"name",
nullable=False,
required=True,
help="Name must be between 1 to 50 characters.",
type=DatasetTagsApi._validate_tag_name,
)
parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
args = parser.parse_args()
args["type"] = "knowledge"
tag = TagService.update_tags(args, args.get("tag_id"))
binding_count = TagService.get_tag_binding_count(args.get("tag_id"))
response = {"id": tag.id, "name": tag.name, "type": tag.type, "binding_count": binding_count}
return response, 200
@validate_dataset_token
def delete(self, _, dataset_id):
"""Delete a knowledge type tag."""
if not current_user.is_editor:
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument("tag_id", nullable=False, required=True, help="Id of a tag.", type=str)
args = parser.parse_args()
TagService.delete_tag(args.get("tag_id"))
return 204
@staticmethod
def _validate_tag_name(name):
if not name or len(name) < 1 or len(name) > 50:
raise ValueError("Name must be between 1 to 50 characters.")
return name
class DatasetTagBindingApi(DatasetApiResource):
@validate_dataset_token
def post(self, _, dataset_id):
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
if not (current_user.is_editor or current_user.is_dataset_editor):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument(
"tag_ids", type=list, nullable=False, required=True, location="json", help="Tag IDs is required."
)
parser.add_argument(
"target_id", type=str, nullable=False, required=True, location="json", help="Target Dataset ID is required."
)
args = parser.parse_args()
args["type"] = "knowledge"
TagService.save_tag_binding(args)
return 204
class DatasetTagUnbindingApi(DatasetApiResource):
@validate_dataset_token
def post(self, _, dataset_id):
# The role of the current user in the ta table must be admin, owner, editor, or dataset_operator
if not (current_user.is_editor or current_user.is_dataset_editor):
raise Forbidden()
parser = reqparse.RequestParser()
parser.add_argument("tag_id", type=str, nullable=False, required=True, help="Tag ID is required.")
parser.add_argument("target_id", type=str, nullable=False, required=True, help="Target ID is required.")
args = parser.parse_args()
args["type"] = "knowledge"
TagService.delete_tag_binding(args)
return 204
class DatasetTagsBindingStatusApi(DatasetApiResource):
@validate_dataset_token
def get(self, _, *args, **kwargs):
"""Get all knowledge type tags."""
dataset_id = kwargs.get("dataset_id")
tags = TagService.get_tags_by_target_id("knowledge", current_user.current_tenant_id, str(dataset_id))
tags_list = [{"id": tag.id, "name": tag.name} for tag in tags]
response = {"data": tags_list, "total": len(tags)}
return response, 200
api.add_resource(DatasetListApi, "/datasets")
api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
api.add_resource(DatasetTagsApi, "/datasets/tags")
api.add_resource(DatasetTagBindingApi, "/datasets/tags/binding")
api.add_resource(DatasetTagUnbindingApi, "/datasets/tags/unbinding")
api.add_resource(DatasetTagsBindingStatusApi, "/datasets/<uuid:dataset_id>/tags")

View File

@@ -175,8 +175,11 @@ class DocumentAddByFileApi(DatasetApiResource):
if not dataset:
raise ValueError("Dataset does not exist.")
if not dataset.indexing_technique and not args.get("indexing_technique"):
indexing_technique = args.get("indexing_technique") or dataset.indexing_technique
if not indexing_technique:
raise ValueError("indexing_technique is required.")
args["indexing_technique"] = indexing_technique
# save file info
file = request.files["file"]
@@ -206,12 +209,16 @@ class DocumentAddByFileApi(DatasetApiResource):
knowledge_config = KnowledgeConfig(**args)
DocumentService.document_create_args_validate(knowledge_config)
dataset_process_rule = dataset.latest_process_rule if "process_rule" not in args else None
if not knowledge_config.original_document_id and not dataset_process_rule and not knowledge_config.process_rule:
raise ValueError("process_rule is required.")
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
knowledge_config=knowledge_config,
account=dataset.created_by_account,
dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
dataset_process_rule=dataset_process_rule,
created_from="api",
)
except ProviderTokenNotInitError as ex:
@@ -388,11 +395,22 @@ class DocumentIndexingStatusApi(DatasetApiResource):
.filter(DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment")
.count()
)
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused:
document.indexing_status = "paused"
documents_status.append(marshal(document, document_status_fields))
# Create a dictionary with document attributes and additional fields
document_dict = {
"id": document.id,
"indexing_status": "paused" if document.is_paused else document.indexing_status,
"processing_started_at": document.processing_started_at,
"parsing_completed_at": document.parsing_completed_at,
"cleaning_completed_at": document.cleaning_completed_at,
"splitting_completed_at": document.splitting_completed_at,
"completed_at": document.completed_at,
"paused_at": document.paused_at,
"error": document.error,
"stopped_at": document.stopped_at,
"completed_segments": completed_segments,
"total_segments": total_segments,
}
documents_status.append(marshal(document_dict, document_status_fields))
data = {"data": documents_status}
return data

View File

@@ -208,6 +208,28 @@ class DatasetSegmentApi(DatasetApiResource):
)
return {"data": marshal(updated_segment, segment_fields), "doc_form": document.doc_form}, 200
def get(self, tenant_id, dataset_id, document_id, segment_id):
# 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 user's model setting
DatasetService.check_dataset_model_setting(dataset)
# check document
document_id = str(document_id)
document = DocumentService.get_document(dataset_id, document_id)
if not document:
raise NotFound("Document not found.")
# check segment
segment_id = str(segment_id)
segment = SegmentService.get_segment_by_id(segment_id=segment_id, tenant_id=current_user.current_tenant_id)
if not segment:
raise NotFound("Segment not found.")
return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
class ChildChunkApi(DatasetApiResource):
"""Resource for child chunks."""

View File

@@ -99,7 +99,12 @@ def validate_app_token(view: Optional[Callable] = None, *, fetch_user_arg: Optio
if user_id:
user_id = str(user_id)
kwargs["end_user"] = create_or_update_end_user_for_user_id(app_model, user_id)
end_user = create_or_update_end_user_for_user_id(app_model, user_id)
kwargs["end_user"] = end_user
# Set EndUser as current logged-in user for flask_login.current_user
current_app.login_manager._update_request_context_with_user(end_user) # type: ignore
user_logged_in.send(current_app._get_current_object(), user=end_user) # type: ignore
return view_func(*args, **kwargs)

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,
)

View File

@@ -1,12 +1,17 @@
from flask_restful import marshal_with
from flask import request
from flask_restful import Resource, marshal_with, reqparse
from controllers.common import fields
from controllers.web import api
from controllers.web.error import AppUnavailableError
from controllers.web.wraps import WebApiResource
from core.app.app_config.common.parameters_mapping import get_parameters_from_feature_dict
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):
@@ -40,5 +45,69 @@ 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
features = FeatureService.get_system_features()
if not features.webapp_auth.enabled:
return {"result": True}
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")

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

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")

View File

@@ -0,0 +1,108 @@
from flask_restful import Resource, reqparse
from jwt import InvalidTokenError # type: ignore
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 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")

View File

@@ -1,16 +1,19 @@
import uuid
from datetime import UTC, datetime, timedelta
from flask import request
from flask_restful import Resource
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 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
class PassportResource(Resource):
@@ -20,14 +23,23 @@ class PassportResource(Resource):
system_features = FeatureService.get_system_features()
app_code = request.headers.get("X-App-Code")
user_id = request.args.get("user_id")
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()
@@ -84,6 +96,128 @@ 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.

View File

@@ -1,15 +1,17 @@
from datetime import UTC, datetime
from functools import wraps
from flask import request
from flask_restful import Resource
from werkzeug.exceptions import BadRequest, NotFound, Unauthorized
from controllers.web.error import WebSSOAuthRequiredError
from controllers.web.error import WebAppAuthAccessDeniedError, WebAppAuthRequiredError
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
def validate_jwt_token(view=None):
@@ -29,7 +31,7 @@ def validate_jwt_token(view=None):
def decode_jwt_token():
system_features = FeatureService.get_system_features()
app_code = request.headers.get("X-App-Code")
app_code = str(request.headers.get("X-App-Code"))
try:
auth_header = request.headers.get("Authorization")
if auth_header is None:
@@ -45,7 +47,8 @@ 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 +56,90 @@ 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=str(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):

View File

@@ -63,7 +63,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):
self._instruction = self._fill_in_inputs_from_external_data_tools(instruction, inputs)
iteration_step = 1
max_iteration_steps = min(app_config.agent.max_iteration if app_config.agent else 5, 5) + 1
max_iteration_steps = min(app_config.agent.max_iteration, 99) + 1
# convert tools into ModelRuntime Tool format
tool_instances, prompt_messages_tools = self._init_prompt_tools()

View File

@@ -82,7 +82,7 @@ class AgentEntity(BaseModel):
strategy: Strategy
prompt: Optional[AgentPromptEntity] = None
tools: Optional[list[AgentToolEntity]] = None
max_iteration: int = 5
max_iteration: int = 10
class AgentInvokeMessage(ToolInvokeMessage):

View File

@@ -48,7 +48,7 @@ class FunctionCallAgentRunner(BaseAgentRunner):
assert app_config.agent
iteration_step = 1
max_iteration_steps = min(app_config.agent.max_iteration, 5) + 1
max_iteration_steps = min(app_config.agent.max_iteration, 99) + 1
# continue to run until there is not any tool call
function_call_state = True

View File

@@ -75,7 +75,7 @@ class AgentConfigManager:
strategy=strategy,
prompt=agent_prompt_entity,
tools=agent_tools,
max_iteration=agent_dict.get("max_iteration", 5),
max_iteration=agent_dict.get("max_iteration", 10),
)
return None

View File

@@ -70,7 +70,7 @@ class ModelConfigConverter:
if not model_mode:
model_mode = LLMMode.CHAT.value
if model_schema and model_schema.model_properties.get(ModelPropertyKey.MODE):
model_mode = LLMMode.value_of(model_schema.model_properties[ModelPropertyKey.MODE]).value
model_mode = LLMMode(model_schema.model_properties[ModelPropertyKey.MODE]).value
if not model_schema:
raise ValueError(f"Model {model_name} not exist.")

View File

@@ -109,6 +109,7 @@ class VariableEntity(BaseModel):
description: str = ""
type: VariableEntityType
required: bool = False
hide: bool = False
max_length: Optional[int] = None
options: Sequence[str] = Field(default_factory=list)
allowed_file_types: Sequence[FileType] = Field(default_factory=list)

View File

@@ -5,7 +5,7 @@ import uuid
from collections.abc import Generator, Mapping
from typing import Any, Literal, Optional, Union, overload
from flask import Flask, current_app
from flask import Flask, copy_current_request_context, current_app, has_request_context
from pydantic import ValidationError
from sqlalchemy.orm import sessionmaker
@@ -26,12 +26,13 @@ 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 core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from extensions.ext_database import db
from factories import file_factory
from models.account import Account
from models.model import App, Conversation, EndUser, Message
from models.workflow import Workflow
from models import Account, App, Conversation, EndUser, Message, Workflow, WorkflowNodeExecutionTriggeredFrom
from models.enums import WorkflowRunTriggeredFrom
from services.conversation_service import ConversationService
from services.errors.message import MessageNotExistsError
@@ -157,16 +158,30 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
trace_manager=trace_manager,
workflow_run_id=workflow_run_id,
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create workflow node execution repository
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
if invoke_from == InvokeFrom.DEBUGGER:
workflow_triggered_from = WorkflowRunTriggeredFrom.DEBUGGING
else:
workflow_triggered_from = WorkflowRunTriggeredFrom.APP_RUN
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=workflow_triggered_from,
)
# Create workflow node execution repository
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
)
return self._generate(
@@ -174,6 +189,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
user=user,
invoke_from=invoke_from,
application_generate_entity=application_generate_entity,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
conversation=conversation,
stream=streaming,
@@ -223,16 +239,26 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
node_id=node_id, inputs=args["inputs"]
),
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create workflow node execution repository
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
)
# Create workflow node execution repository
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
return self._generate(
@@ -240,6 +266,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
user=user,
invoke_from=InvokeFrom.DEBUGGER,
application_generate_entity=application_generate_entity,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
conversation=None,
stream=streaming,
@@ -287,16 +314,26 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
extras={"auto_generate_conversation_name": False},
single_loop_run=AdvancedChatAppGenerateEntity.SingleLoopRunEntity(node_id=node_id, inputs=args["inputs"]),
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create workflow node execution repository
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
)
# Create workflow node execution repository
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
return self._generate(
@@ -304,6 +341,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
user=user,
invoke_from=InvokeFrom.DEBUGGER,
application_generate_entity=application_generate_entity,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
conversation=None,
stream=streaming,
@@ -316,6 +354,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
user: Union[Account, EndUser],
invoke_from: InvokeFrom,
application_generate_entity: AdvancedChatAppGenerateEntity,
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
conversation: Optional[Conversation] = None,
stream: bool = True,
@@ -357,18 +396,23 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
message_id=message.id,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"conversation_id": conversation.id,
"message_id": message.id,
"context": contextvars.copy_context(),
},
)
# new thread with request context and contextvars
context = contextvars.copy_context()
@copy_current_request_context
def worker_with_context():
# Run the worker within the copied context
return context.run(
self._generate_worker,
flask_app=current_app._get_current_object(), # type: ignore
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
conversation_id=conversation.id,
message_id=message.id,
context=context,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()
@@ -380,6 +424,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
conversation=conversation,
message=message,
user=user,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
stream=stream,
)
@@ -406,8 +451,22 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
"""
for var, val in context.items():
var.set(val)
# FIXME(-LAN-): Save current user before entering new app context
from flask import g
saved_user = None
if has_request_context() and hasattr(g, "_login_user"):
saved_user = g._login_user
with flask_app.app_context():
try:
# Restore user in new app context
if saved_user is not None:
from flask import g
g._login_user = saved_user
# get conversation and message
conversation = self._get_conversation(conversation_id)
message = self._get_message(message_id)
@@ -452,6 +511,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
conversation: Conversation,
message: Message,
user: Union[Account, EndUser],
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
stream: bool = False,
) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
@@ -475,9 +535,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
conversation=conversation,
message=message,
user=user,
stream=stream,
dialogue_count=self._dialogue_count,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
stream=stream,
)
try:

View File

@@ -140,7 +140,7 @@ class AdvancedChatAppRunner(WorkflowBasedAppRunner):
SystemVariableKey.DIALOGUE_COUNT: self._dialogue_count,
SystemVariableKey.APP_ID: app_config.app_id,
SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
SystemVariableKey.WORKFLOW_EXECUTION_ID: self.application_generate_entity.workflow_run_id,
}
# init variable pool

View File

@@ -1,4 +1,3 @@
import json
import logging
import time
from collections.abc import Generator, Mapping
@@ -10,6 +9,7 @@ from sqlalchemy.orm import Session
from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
from core.app.entities.app_invoke_entities import (
AdvancedChatAppGenerateEntity,
InvokeFrom,
@@ -56,25 +56,23 @@ from core.app.entities.task_entities import (
WorkflowTaskState,
)
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
from core.model_runtime.entities.llm_entities import LLMUsage
from core.model_runtime.utils.encoders import jsonable_encoder
from core.ops.ops_trace_manager import TraceQueueManager
from core.workflow.entities.workflow_execution import WorkflowExecutionStatus, WorkflowType
from core.workflow.enums import SystemVariableKey
from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
from core.workflow.nodes import NodeType
from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.workflow_cycle_manager import WorkflowCycleManager
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.workflow_cycle_manager import CycleManagerWorkflowInfo, WorkflowCycleManager
from events.message_event import message_was_created
from extensions.ext_database import db
from models import Conversation, EndUser, Message, MessageFile
from models.account import Account
from models.enums import CreatedByRole
from models.workflow import (
Workflow,
WorkflowRunStatus,
)
from models.enums import CreatorUserRole
from models.workflow import Workflow
logger = logging.getLogger(__name__)
@@ -94,6 +92,7 @@ class AdvancedChatAppGenerateTaskPipeline:
user: Union[Account, EndUser],
stream: bool,
dialogue_count: int,
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
) -> None:
self._base_task_pipeline = BasedGenerateTaskPipeline(
@@ -105,11 +104,11 @@ class AdvancedChatAppGenerateTaskPipeline:
if isinstance(user, EndUser):
self._user_id = user.id
user_session_id = user.session_id
self._created_by_role = CreatedByRole.END_USER
self._created_by_role = CreatorUserRole.END_USER
elif isinstance(user, Account):
self._user_id = user.id
user_session_id = user.id
self._created_by_role = CreatedByRole.ACCOUNT
self._created_by_role = CreatorUserRole.ACCOUNT
else:
raise NotImplementedError(f"User type not supported: {type(user)}")
@@ -123,13 +122,24 @@ class AdvancedChatAppGenerateTaskPipeline:
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,
SystemVariableKey.WORKFLOW_EXECUTION_ID: application_generate_entity.workflow_run_id,
},
workflow_info=CycleManagerWorkflowInfo(
workflow_id=workflow.id,
workflow_type=WorkflowType(workflow.type),
version=workflow.version,
graph_data=workflow.graph_dict,
),
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
)
self._workflow_response_converter = WorkflowResponseConverter(
application_generate_entity=application_generate_entity,
)
self._task_state = WorkflowTaskState()
self._message_cycle_manager = MessageCycleManage(
self._message_cycle_manager = MessageCycleManager(
application_generate_entity=application_generate_entity, task_state=self._task_state
)
@@ -150,7 +160,7 @@ class AdvancedChatAppGenerateTaskPipeline:
:return:
"""
# start generate conversation name thread
self._conversation_name_generate_thread = self._message_cycle_manager._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
)
@@ -294,19 +304,15 @@ class AdvancedChatAppGenerateTaskPipeline:
with Session(db.engine, expire_on_commit=False) as session:
# init workflow run
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
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_start()
self._workflow_run_id = workflow_execution.id_
message = self._get_message(session=session)
if not message:
raise ValueError(f"Message not found: {self._message_id}")
message.workflow_run_id = workflow_run.id
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
message.workflow_run_id = workflow_execution.id_
workflow_start_resp = self._workflow_response_converter.workflow_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
session.commit()
@@ -319,13 +325,10 @@ class AdvancedChatAppGenerateTaskPipeline:
raise ValueError("workflow run not initialized.")
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(
workflow_execution_id=self._workflow_run_id, event=event
)
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_retried(
workflow_run=workflow_run, event=event
)
node_retry_resp = self._workflow_cycle_manager._workflow_node_retry_to_stream_response(
node_retry_resp = self._workflow_response_converter.workflow_node_retry_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -338,20 +341,15 @@ class AdvancedChatAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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(
workflow_run=workflow_run, event=event
)
workflow_node_execution = self._workflow_cycle_manager.handle_node_execution_start(
workflow_execution_id=self._workflow_run_id, event=event
)
node_start_resp = self._workflow_cycle_manager._workflow_node_start_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
)
session.commit()
node_start_resp = self._workflow_response_converter.workflow_node_start_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
)
if node_start_resp:
yield node_start_resp
@@ -359,15 +357,15 @@ class AdvancedChatAppGenerateTaskPipeline:
# 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._workflow_cycle_manager._fetch_files_from_node_outputs(event.outputs or {})
self._workflow_response_converter.fetch_files_from_node_outputs(event.outputs or {})
)
with Session(db.engine, expire_on_commit=False) as session:
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_success(
workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_success(
event=event
)
node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -383,11 +381,11 @@ class AdvancedChatAppGenerateTaskPipeline:
| QueueNodeInLoopFailedEvent
| QueueNodeExceptionEvent,
):
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_failed(
workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_failed(
event=event
)
node_finish_resp = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
node_finish_resp = self._workflow_response_converter.workflow_node_finish_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -399,132 +397,92 @@ class AdvancedChatAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
)
parallel_start_resp = (
self._workflow_response_converter.workflow_parallel_branch_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
)
yield parallel_start_resp
elif isinstance(event, QueueParallelBranchRunSucceededEvent | QueueParallelBranchRunFailedEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
)
parallel_finish_resp = (
self._workflow_response_converter.workflow_parallel_branch_finished_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
)
yield parallel_finish_resp
elif isinstance(event, QueueIterationStartEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_start_resp = self._workflow_response_converter.workflow_iteration_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_start_resp
elif isinstance(event, QueueIterationNextEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_next_resp = self._workflow_response_converter.workflow_iteration_next_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_next_resp
elif isinstance(event, QueueIterationCompletedEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_finish_resp = self._workflow_response_converter.workflow_iteration_completed_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_finish_resp
elif isinstance(event, QueueLoopStartEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_start_resp = self._workflow_cycle_manager._workflow_loop_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_start_resp = self._workflow_response_converter.workflow_loop_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_start_resp
elif isinstance(event, QueueLoopNextEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_next_resp = self._workflow_cycle_manager._workflow_loop_next_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_next_resp = self._workflow_response_converter.workflow_loop_next_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_next_resp
elif isinstance(event, QueueLoopCompletedEvent):
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_finish_resp = self._workflow_cycle_manager._workflow_loop_completed_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_finish_resp = self._workflow_response_converter.workflow_loop_completed_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_finish_resp
elif isinstance(event, QueueWorkflowSucceededEvent):
@@ -535,10 +493,8 @@ class AdvancedChatAppGenerateTaskPipeline:
raise ValueError("workflow run not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_success(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_success(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
outputs=event.outputs,
@@ -546,10 +502,11 @@ class AdvancedChatAppGenerateTaskPipeline:
trace_manager=trace_manager,
)
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
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
session.commit()
yield workflow_finish_resp
self._base_task_pipeline._queue_manager.publish(
@@ -562,10 +519,8 @@ class AdvancedChatAppGenerateTaskPipeline:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_partial_success(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_partial_success(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
outputs=event.outputs,
@@ -573,10 +528,11 @@ class AdvancedChatAppGenerateTaskPipeline:
conversation_id=None,
trace_manager=trace_manager,
)
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
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
session.commit()
yield workflow_finish_resp
self._base_task_pipeline._queue_manager.publish(
@@ -589,26 +545,25 @@ class AdvancedChatAppGenerateTaskPipeline:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_failed(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
status=WorkflowRunStatus.FAILED,
error=event.error,
status=WorkflowExecutionStatus.FAILED,
error_message=event.error,
conversation_id=self._conversation_id,
trace_manager=trace_manager,
exceptions_count=event.exceptions_count,
)
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
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
err_event = QueueErrorEvent(error=ValueError(f"Run failed: {workflow_run.error}"))
err_event = QueueErrorEvent(error=ValueError(f"Run failed: {workflow_execution.error_message}"))
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._base_task_pipeline._error_to_stream_response(err)
@@ -616,21 +571,19 @@ class AdvancedChatAppGenerateTaskPipeline:
elif isinstance(event, QueueStopEvent):
if self._workflow_run_id and graph_runtime_state:
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_failed(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
status=WorkflowRunStatus.STOPPED,
error=event.get_stop_reason(),
status=WorkflowExecutionStatus.STOPPED,
error_message=event.get_stop_reason(),
conversation_id=self._conversation_id,
trace_manager=trace_manager,
)
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
workflow_execution=workflow_execution,
)
# Save message
self._save_message(session=session, graph_runtime_state=graph_runtime_state)
@@ -650,22 +603,18 @@ class AdvancedChatAppGenerateTaskPipeline:
yield self._message_end_to_stream_response()
break
elif isinstance(event, QueueRetrieverResourcesEvent):
self._message_cycle_manager._handle_retriever_resources(event)
self._message_cycle_manager.handle_retriever_resources(event)
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
)
message.message_metadata = self._task_state.metadata.model_dump_json()
session.commit()
elif isinstance(event, QueueAnnotationReplyEvent):
self._message_cycle_manager._handle_annotation_reply(event)
self._message_cycle_manager.handle_annotation_reply(event)
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
)
message.message_metadata = self._task_state.metadata.model_dump_json()
session.commit()
elif isinstance(event, QueueTextChunkEvent):
delta_text = event.text
@@ -682,12 +631,12 @@ class AdvancedChatAppGenerateTaskPipeline:
tts_publisher.publish(queue_message)
self._task_state.answer += delta_text
yield self._message_cycle_manager._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_cycle_manager._message_replace_to_stream_response(
yield self._message_cycle_manager.message_replace_to_stream_response(
answer=event.text, reason=event.reason
)
elif isinstance(event, QueueAdvancedChatMessageEndEvent):
@@ -699,7 +648,7 @@ class AdvancedChatAppGenerateTaskPipeline:
)
if output_moderation_answer:
self._task_state.answer = output_moderation_answer
yield self._message_cycle_manager._message_replace_to_stream_response(
yield self._message_cycle_manager.message_replace_to_stream_response(
answer=output_moderation_answer,
reason=QueueMessageReplaceEvent.MessageReplaceReason.OUTPUT_MODERATION,
)
@@ -711,7 +660,7 @@ class AdvancedChatAppGenerateTaskPipeline:
yield self._message_end_to_stream_response()
elif isinstance(event, QueueAgentLogEvent):
yield self._workflow_cycle_manager._handle_agent_log(
yield self._workflow_response_converter.handle_agent_log(
task_id=self._application_generate_entity.task_id, event=event
)
else:
@@ -728,9 +677,7 @@ class AdvancedChatAppGenerateTaskPipeline:
message = self._get_message(session=session)
message.answer = self._task_state.answer
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
)
message.message_metadata = self._task_state.metadata.model_dump_json()
message_files = [
MessageFile(
message_id=message.id,
@@ -739,9 +686,9 @@ class AdvancedChatAppGenerateTaskPipeline:
url=file["remote_url"],
belongs_to="assistant",
upload_file_id=file["related_id"],
created_by_role=CreatedByRole.ACCOUNT
created_by_role=CreatorUserRole.ACCOUNT
if message.invoke_from in {InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER}
else CreatedByRole.END_USER,
else CreatorUserRole.END_USER,
created_by=message.from_account_id or message.from_end_user_id or "",
)
for file in self._recorded_files
@@ -758,9 +705,9 @@ class AdvancedChatAppGenerateTaskPipeline:
message.answer_price_unit = usage.completion_price_unit
message.total_price = usage.total_price
message.currency = usage.currency
self._task_state.metadata["usage"] = jsonable_encoder(usage)
self._task_state.metadata.usage = usage
else:
self._task_state.metadata["usage"] = jsonable_encoder(LLMUsage.empty_usage())
self._task_state.metadata.usage = LLMUsage.empty_usage()
message_was_created.send(
message,
application_generate_entity=self._application_generate_entity,
@@ -771,18 +718,16 @@ class AdvancedChatAppGenerateTaskPipeline:
Message end to stream response.
:return:
"""
extras = {}
if self._task_state.metadata:
extras["metadata"] = self._task_state.metadata.copy()
extras = self._task_state.metadata.model_dump()
if "annotation_reply" in extras["metadata"]:
del extras["metadata"]["annotation_reply"]
if self._task_state.metadata.annotation_reply:
del extras["annotation_reply"]
return MessageEndStreamResponse(
task_id=self._application_generate_entity.task_id,
id=self._message_id,
files=self._recorded_files,
metadata=extras.get("metadata", {}),
metadata=extras,
)
def _handle_output_moderation_chunk(self, text: str) -> bool:

View File

@@ -5,7 +5,7 @@ import uuid
from collections.abc import Generator, Mapping
from typing import Any, Literal, Union, overload
from flask import Flask, current_app
from flask import Flask, copy_current_request_context, current_app, has_request_context
from pydantic import ValidationError
from configs import dify_config
@@ -179,18 +179,23 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
message_id=message.id,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"context": contextvars.copy_context(),
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"conversation_id": conversation.id,
"message_id": message.id,
},
)
# new thread with request context and contextvars
context = contextvars.copy_context()
@copy_current_request_context
def worker_with_context():
# Run the worker within the copied context
return context.run(
self._generate_worker,
flask_app=current_app._get_current_object(), # type: ignore
context=context,
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
conversation_id=conversation.id,
message_id=message.id,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()
@@ -227,8 +232,21 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
for var, val in context.items():
var.set(val)
# FIXME(-LAN-): Save current user before entering new app context
from flask import g
saved_user = None
if has_request_context() and hasattr(g, "_login_user"):
saved_user = g._login_user
with flask_app.app_context():
try:
# Restore user in new app context
if saved_user is not None:
from flask import g
g._login_user = saved_user
# get conversation and message
conversation = self._get_conversation(conversation_id)
message = self._get_message(message_id)

View File

@@ -4,7 +4,7 @@ import uuid
from collections.abc import Generator, Mapping
from typing import Any, Literal, Union, overload
from flask import Flask, current_app
from flask import Flask, copy_current_request_context, current_app
from pydantic import ValidationError
from configs import dify_config
@@ -170,17 +170,18 @@ class ChatAppGenerator(MessageBasedAppGenerator):
message_id=message.id,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"conversation_id": conversation.id,
"message_id": message.id,
},
)
# new thread with request context
@copy_current_request_context
def worker_with_context():
return self._generate_worker(
flask_app=current_app._get_current_object(), # type: ignore
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
conversation_id=conversation.id,
message_id=message.id,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()

View File

View File

@@ -0,0 +1,561 @@
import time
from collections.abc import Mapping, Sequence
from datetime import UTC, datetime
from typing import Any, Optional, Union, cast
from sqlalchemy import select
from sqlalchemy.orm import Session
from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity
from core.app.entities.queue_entities import (
QueueAgentLogEvent,
QueueIterationCompletedEvent,
QueueIterationNextEvent,
QueueIterationStartEvent,
QueueLoopCompletedEvent,
QueueLoopNextEvent,
QueueLoopStartEvent,
QueueNodeExceptionEvent,
QueueNodeFailedEvent,
QueueNodeInIterationFailedEvent,
QueueNodeInLoopFailedEvent,
QueueNodeRetryEvent,
QueueNodeStartedEvent,
QueueNodeSucceededEvent,
QueueParallelBranchRunFailedEvent,
QueueParallelBranchRunStartedEvent,
QueueParallelBranchRunSucceededEvent,
)
from core.app.entities.task_entities import (
AgentLogStreamResponse,
IterationNodeCompletedStreamResponse,
IterationNodeNextStreamResponse,
IterationNodeStartStreamResponse,
LoopNodeCompletedStreamResponse,
LoopNodeNextStreamResponse,
LoopNodeStartStreamResponse,
NodeFinishStreamResponse,
NodeRetryStreamResponse,
NodeStartStreamResponse,
ParallelBranchFinishedStreamResponse,
ParallelBranchStartStreamResponse,
WorkflowFinishStreamResponse,
WorkflowStartStreamResponse,
)
from core.file import FILE_MODEL_IDENTITY, File
from core.tools.tool_manager import ToolManager
from core.workflow.entities.workflow_execution import WorkflowExecution
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecution, WorkflowNodeExecutionStatus
from core.workflow.nodes import NodeType
from core.workflow.nodes.tool.entities import ToolNodeData
from models import (
Account,
CreatorUserRole,
EndUser,
WorkflowRun,
)
class WorkflowResponseConverter:
def __init__(
self,
*,
application_generate_entity: Union[AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity],
) -> None:
self._application_generate_entity = application_generate_entity
def workflow_start_to_stream_response(
self,
*,
task_id: str,
workflow_execution: WorkflowExecution,
) -> WorkflowStartStreamResponse:
return WorkflowStartStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution.id_,
data=WorkflowStartStreamResponse.Data(
id=workflow_execution.id_,
workflow_id=workflow_execution.workflow_id,
inputs=workflow_execution.inputs,
created_at=int(workflow_execution.started_at.timestamp()),
),
)
def workflow_finish_to_stream_response(
self,
*,
session: Session,
task_id: str,
workflow_execution: WorkflowExecution,
) -> WorkflowFinishStreamResponse:
created_by = None
workflow_run = session.scalar(select(WorkflowRun).where(WorkflowRun.id == workflow_execution.id_))
assert workflow_run is not None
if workflow_run.created_by_role == CreatorUserRole.ACCOUNT:
stmt = select(Account).where(Account.id == workflow_run.created_by)
account = session.scalar(stmt)
if account:
created_by = {
"id": account.id,
"name": account.name,
"email": account.email,
}
elif workflow_run.created_by_role == CreatorUserRole.END_USER:
stmt = select(EndUser).where(EndUser.id == workflow_run.created_by)
end_user = session.scalar(stmt)
if end_user:
created_by = {
"id": end_user.id,
"user": end_user.session_id,
}
else:
raise NotImplementedError(f"unknown created_by_role: {workflow_run.created_by_role}")
# Handle the case where finished_at is None by using current time as default
finished_at_timestamp = (
int(workflow_execution.finished_at.timestamp())
if workflow_execution.finished_at
else int(datetime.now(UTC).timestamp())
)
return WorkflowFinishStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution.id_,
data=WorkflowFinishStreamResponse.Data(
id=workflow_execution.id_,
workflow_id=workflow_execution.workflow_id,
status=workflow_execution.status,
outputs=workflow_execution.outputs,
error=workflow_execution.error_message,
elapsed_time=workflow_execution.elapsed_time,
total_tokens=workflow_execution.total_tokens,
total_steps=workflow_execution.total_steps,
created_by=created_by,
created_at=int(workflow_execution.started_at.timestamp()),
finished_at=finished_at_timestamp,
files=self.fetch_files_from_node_outputs(workflow_execution.outputs),
exceptions_count=workflow_execution.exceptions_count,
),
)
def workflow_node_start_to_stream_response(
self,
*,
event: QueueNodeStartedEvent,
task_id: str,
workflow_node_execution: WorkflowNodeExecution,
) -> Optional[NodeStartStreamResponse]:
if workflow_node_execution.node_type in {NodeType.ITERATION, NodeType.LOOP}:
return None
if not workflow_node_execution.workflow_execution_id:
return None
response = NodeStartStreamResponse(
task_id=task_id,
workflow_run_id=workflow_node_execution.workflow_execution_id,
data=NodeStartStreamResponse.Data(
id=workflow_node_execution.id,
node_id=workflow_node_execution.node_id,
node_type=workflow_node_execution.node_type,
title=workflow_node_execution.title,
index=workflow_node_execution.index,
predecessor_node_id=workflow_node_execution.predecessor_node_id,
inputs=workflow_node_execution.inputs,
created_at=int(workflow_node_execution.created_at.timestamp()),
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
parent_parallel_id=event.parent_parallel_id,
parent_parallel_start_node_id=event.parent_parallel_start_node_id,
iteration_id=event.in_iteration_id,
loop_id=event.in_loop_id,
parallel_run_id=event.parallel_mode_run_id,
agent_strategy=event.agent_strategy,
),
)
# extras logic
if event.node_type == NodeType.TOOL:
node_data = cast(ToolNodeData, event.node_data)
response.data.extras["icon"] = ToolManager.get_tool_icon(
tenant_id=self._application_generate_entity.app_config.tenant_id,
provider_type=node_data.provider_type,
provider_id=node_data.provider_id,
)
return response
def workflow_node_finish_to_stream_response(
self,
*,
event: QueueNodeSucceededEvent
| QueueNodeFailedEvent
| QueueNodeInIterationFailedEvent
| QueueNodeInLoopFailedEvent
| QueueNodeExceptionEvent,
task_id: str,
workflow_node_execution: WorkflowNodeExecution,
) -> Optional[NodeFinishStreamResponse]:
if workflow_node_execution.node_type in {NodeType.ITERATION, NodeType.LOOP}:
return None
if not workflow_node_execution.workflow_execution_id:
return None
if not workflow_node_execution.finished_at:
return None
return NodeFinishStreamResponse(
task_id=task_id,
workflow_run_id=workflow_node_execution.workflow_execution_id,
data=NodeFinishStreamResponse.Data(
id=workflow_node_execution.id,
node_id=workflow_node_execution.node_id,
node_type=workflow_node_execution.node_type,
index=workflow_node_execution.index,
title=workflow_node_execution.title,
predecessor_node_id=workflow_node_execution.predecessor_node_id,
inputs=workflow_node_execution.inputs,
process_data=workflow_node_execution.process_data,
outputs=workflow_node_execution.outputs,
status=workflow_node_execution.status,
error=workflow_node_execution.error,
elapsed_time=workflow_node_execution.elapsed_time,
execution_metadata=workflow_node_execution.metadata,
created_at=int(workflow_node_execution.created_at.timestamp()),
finished_at=int(workflow_node_execution.finished_at.timestamp()),
files=self.fetch_files_from_node_outputs(workflow_node_execution.outputs or {}),
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
parent_parallel_id=event.parent_parallel_id,
parent_parallel_start_node_id=event.parent_parallel_start_node_id,
iteration_id=event.in_iteration_id,
loop_id=event.in_loop_id,
),
)
def workflow_node_retry_to_stream_response(
self,
*,
event: QueueNodeRetryEvent,
task_id: str,
workflow_node_execution: WorkflowNodeExecution,
) -> Optional[Union[NodeRetryStreamResponse, NodeFinishStreamResponse]]:
if workflow_node_execution.node_type in {NodeType.ITERATION, NodeType.LOOP}:
return None
if not workflow_node_execution.workflow_execution_id:
return None
if not workflow_node_execution.finished_at:
return None
return NodeRetryStreamResponse(
task_id=task_id,
workflow_run_id=workflow_node_execution.workflow_execution_id,
data=NodeRetryStreamResponse.Data(
id=workflow_node_execution.id,
node_id=workflow_node_execution.node_id,
node_type=workflow_node_execution.node_type,
index=workflow_node_execution.index,
title=workflow_node_execution.title,
predecessor_node_id=workflow_node_execution.predecessor_node_id,
inputs=workflow_node_execution.inputs,
process_data=workflow_node_execution.process_data,
outputs=workflow_node_execution.outputs,
status=workflow_node_execution.status,
error=workflow_node_execution.error,
elapsed_time=workflow_node_execution.elapsed_time,
execution_metadata=workflow_node_execution.metadata,
created_at=int(workflow_node_execution.created_at.timestamp()),
finished_at=int(workflow_node_execution.finished_at.timestamp()),
files=self.fetch_files_from_node_outputs(workflow_node_execution.outputs or {}),
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
parent_parallel_id=event.parent_parallel_id,
parent_parallel_start_node_id=event.parent_parallel_start_node_id,
iteration_id=event.in_iteration_id,
loop_id=event.in_loop_id,
retry_index=event.retry_index,
),
)
def workflow_parallel_branch_start_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueParallelBranchRunStartedEvent,
) -> ParallelBranchStartStreamResponse:
return ParallelBranchStartStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=ParallelBranchStartStreamResponse.Data(
parallel_id=event.parallel_id,
parallel_branch_id=event.parallel_start_node_id,
parent_parallel_id=event.parent_parallel_id,
parent_parallel_start_node_id=event.parent_parallel_start_node_id,
iteration_id=event.in_iteration_id,
loop_id=event.in_loop_id,
created_at=int(time.time()),
),
)
def workflow_parallel_branch_finished_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueParallelBranchRunSucceededEvent | QueueParallelBranchRunFailedEvent,
) -> ParallelBranchFinishedStreamResponse:
return ParallelBranchFinishedStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=ParallelBranchFinishedStreamResponse.Data(
parallel_id=event.parallel_id,
parallel_branch_id=event.parallel_start_node_id,
parent_parallel_id=event.parent_parallel_id,
parent_parallel_start_node_id=event.parent_parallel_start_node_id,
iteration_id=event.in_iteration_id,
loop_id=event.in_loop_id,
status="succeeded" if isinstance(event, QueueParallelBranchRunSucceededEvent) else "failed",
error=event.error if isinstance(event, QueueParallelBranchRunFailedEvent) else None,
created_at=int(time.time()),
),
)
def workflow_iteration_start_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueIterationStartEvent,
) -> IterationNodeStartStreamResponse:
return IterationNodeStartStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=IterationNodeStartStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},
metadata=event.metadata or {},
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
),
)
def workflow_iteration_next_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueIterationNextEvent,
) -> IterationNodeNextStreamResponse:
return IterationNodeNextStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=IterationNodeNextStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
index=event.index,
pre_iteration_output=event.output,
created_at=int(time.time()),
extras={},
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
parallel_mode_run_id=event.parallel_mode_run_id,
duration=event.duration,
),
)
def workflow_iteration_completed_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueIterationCompletedEvent,
) -> IterationNodeCompletedStreamResponse:
return IterationNodeCompletedStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=IterationNodeCompletedStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
outputs=event.outputs,
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},
status=WorkflowNodeExecutionStatus.SUCCEEDED
if event.error is None
else WorkflowNodeExecutionStatus.FAILED,
error=None,
elapsed_time=(datetime.now(UTC).replace(tzinfo=None) - event.start_at).total_seconds(),
total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,
execution_metadata=event.metadata,
finished_at=int(time.time()),
steps=event.steps,
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
),
)
def workflow_loop_start_to_stream_response(
self, *, task_id: str, workflow_execution_id: str, event: QueueLoopStartEvent
) -> LoopNodeStartStreamResponse:
return LoopNodeStartStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=LoopNodeStartStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},
metadata=event.metadata or {},
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
),
)
def workflow_loop_next_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueLoopNextEvent,
) -> LoopNodeNextStreamResponse:
return LoopNodeNextStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=LoopNodeNextStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
index=event.index,
pre_loop_output=event.output,
created_at=int(time.time()),
extras={},
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
parallel_mode_run_id=event.parallel_mode_run_id,
duration=event.duration,
),
)
def workflow_loop_completed_to_stream_response(
self,
*,
task_id: str,
workflow_execution_id: str,
event: QueueLoopCompletedEvent,
) -> LoopNodeCompletedStreamResponse:
return LoopNodeCompletedStreamResponse(
task_id=task_id,
workflow_run_id=workflow_execution_id,
data=LoopNodeCompletedStreamResponse.Data(
id=event.node_id,
node_id=event.node_id,
node_type=event.node_type.value,
title=event.node_data.title,
outputs=event.outputs,
created_at=int(time.time()),
extras={},
inputs=event.inputs or {},
status=WorkflowNodeExecutionStatus.SUCCEEDED
if event.error is None
else WorkflowNodeExecutionStatus.FAILED,
error=None,
elapsed_time=(datetime.now(UTC).replace(tzinfo=None) - event.start_at).total_seconds(),
total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,
execution_metadata=event.metadata,
finished_at=int(time.time()),
steps=event.steps,
parallel_id=event.parallel_id,
parallel_start_node_id=event.parallel_start_node_id,
),
)
def fetch_files_from_node_outputs(self, outputs_dict: Mapping[str, Any] | None) -> Sequence[Mapping[str, Any]]:
"""
Fetch files from node outputs
:param outputs_dict: node outputs dict
:return:
"""
if not outputs_dict:
return []
files = [self._fetch_files_from_variable_value(output_value) for output_value in outputs_dict.values()]
# Remove None
files = [file for file in files if file]
# Flatten list
# Flatten the list of sequences into a single list of mappings
flattened_files = [file for sublist in files if sublist for file in sublist]
# Convert to tuple to match Sequence type
return tuple(flattened_files)
def _fetch_files_from_variable_value(self, value: Union[dict, list]) -> Sequence[Mapping[str, Any]]:
"""
Fetch files from variable value
:param value: variable value
:return:
"""
if not value:
return []
files = []
if isinstance(value, list):
for item in value:
file = self._get_file_var_from_value(item)
if file:
files.append(file)
elif isinstance(value, dict):
file = self._get_file_var_from_value(value)
if file:
files.append(file)
return files
def _get_file_var_from_value(self, value: Union[dict, list]) -> Mapping[str, Any] | None:
"""
Get file var from value
:param value: variable value
:return:
"""
if not value:
return None
if isinstance(value, dict) and value.get("dify_model_identity") == FILE_MODEL_IDENTITY:
return value
elif isinstance(value, File):
return value.to_dict()
return None
def handle_agent_log(self, task_id: str, event: QueueAgentLogEvent) -> AgentLogStreamResponse:
"""
Handle agent log
:param task_id: task id
:param event: agent log event
:return:
"""
return AgentLogStreamResponse(
task_id=task_id,
data=AgentLogStreamResponse.Data(
node_execution_id=event.node_execution_id,
id=event.id,
parent_id=event.parent_id,
label=event.label,
error=event.error,
status=event.status,
data=event.data,
metadata=event.metadata,
node_id=event.node_id,
),
)

View File

@@ -4,7 +4,7 @@ import uuid
from collections.abc import Generator, Mapping
from typing import Any, Literal, Union, overload
from flask import Flask, current_app
from flask import Flask, copy_current_request_context, current_app
from pydantic import ValidationError
from configs import dify_config
@@ -151,16 +151,17 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
message_id=message.id,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"message_id": message.id,
},
)
# new thread with request context
@copy_current_request_context
def worker_with_context():
return self._generate_worker(
flask_app=current_app._get_current_object(), # type: ignore
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
message_id=message.id,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()
@@ -313,16 +314,17 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
message_id=message.id,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"message_id": message.id,
},
)
# new thread with request context
@copy_current_request_context
def worker_with_context():
return self._generate_worker(
flask_app=current_app._get_current_object(), # type: ignore
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
message_id=message.id,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()

View File

@@ -25,7 +25,7 @@ from core.app.task_pipeline.easy_ui_based_generate_task_pipeline import EasyUIBa
from core.prompt.utils.prompt_template_parser import PromptTemplateParser
from extensions.ext_database import db
from models import Account
from models.enums import CreatedByRole
from models.enums import CreatorUserRole
from models.model import App, AppMode, AppModelConfig, Conversation, EndUser, Message, MessageFile
from services.errors.app_model_config import AppModelConfigBrokenError
from services.errors.conversation import ConversationNotExistsError
@@ -223,7 +223,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
belongs_to="user",
url=file.remote_url,
upload_file_id=file.related_id,
created_by_role=(CreatedByRole.ACCOUNT if account_id else CreatedByRole.END_USER),
created_by_role=(CreatorUserRole.ACCOUNT if account_id else CreatorUserRole.END_USER),
created_by=account_id or end_user_id or "",
)
db.session.add(message_file)

View File

@@ -5,7 +5,7 @@ import uuid
from collections.abc import Generator, Mapping, Sequence
from typing import Any, Literal, Optional, Union, overload
from flask import Flask, current_app
from flask import Flask, copy_current_request_context, current_app, has_request_context
from pydantic import ValidationError
from sqlalchemy.orm import sessionmaker
@@ -18,16 +18,19 @@ from core.app.apps.workflow.app_config_manager import WorkflowAppConfigManager
from core.app.apps.workflow.app_queue_manager import WorkflowAppQueueManager
from core.app.apps.workflow.app_runner import WorkflowAppRunner
from core.app.apps.workflow.generate_response_converter import WorkflowAppGenerateResponseConverter
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
from core.ops.ops_trace_manager import TraceQueueManager
from core.repositories import SQLAlchemyWorkflowNodeExecutionRepository
from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.workflow_app_generate_task_pipeline import WorkflowAppGenerateTaskPipeline
from core.repositories.sqlalchemy_workflow_execution_repository import SQLAlchemyWorkflowExecutionRepository
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from extensions.ext_database import db
from factories import file_factory
from models import Account, App, EndUser, Workflow
from models import Account, App, EndUser, Workflow, WorkflowNodeExecutionTriggeredFrom
from models.enums import WorkflowRunTriggeredFrom
logger = logging.getLogger(__name__)
@@ -129,19 +132,33 @@ class WorkflowAppGenerator(BaseAppGenerator):
invoke_from=invoke_from,
call_depth=call_depth,
trace_manager=trace_manager,
workflow_run_id=workflow_run_id,
workflow_execution_id=workflow_run_id,
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create workflow node execution repository
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
if invoke_from == InvokeFrom.DEBUGGER:
workflow_triggered_from = WorkflowRunTriggeredFrom.DEBUGGING
else:
workflow_triggered_from = WorkflowRunTriggeredFrom.APP_RUN
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=workflow_triggered_from,
)
# Create workflow node execution repository
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.WORKFLOW_RUN,
)
return self._generate(
@@ -150,6 +167,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
user=user,
application_generate_entity=application_generate_entity,
invoke_from=invoke_from,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
streaming=streaming,
workflow_thread_pool_id=workflow_thread_pool_id,
@@ -163,6 +181,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
user: Union[Account, EndUser],
application_generate_entity: WorkflowAppGenerateEntity,
invoke_from: InvokeFrom,
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
streaming: bool = True,
workflow_thread_pool_id: Optional[str] = None,
@@ -187,17 +206,22 @@ class WorkflowAppGenerator(BaseAppGenerator):
app_mode=app_model.mode,
)
# new thread
worker_thread = threading.Thread(
target=self._generate_worker,
kwargs={
"flask_app": current_app._get_current_object(), # type: ignore
"application_generate_entity": application_generate_entity,
"queue_manager": queue_manager,
"context": contextvars.copy_context(),
"workflow_thread_pool_id": workflow_thread_pool_id,
},
)
# new thread with request context and contextvars
context = contextvars.copy_context()
@copy_current_request_context
def worker_with_context():
# Run the worker within the copied context
return context.run(
self._generate_worker,
flask_app=current_app._get_current_object(), # type: ignore
application_generate_entity=application_generate_entity,
queue_manager=queue_manager,
context=context,
workflow_thread_pool_id=workflow_thread_pool_id,
)
worker_thread = threading.Thread(target=worker_with_context)
worker_thread.start()
@@ -207,6 +231,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow=workflow,
queue_manager=queue_manager,
user=user,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
stream=streaming,
)
@@ -254,18 +279,30 @@ class WorkflowAppGenerator(BaseAppGenerator):
single_iteration_run=WorkflowAppGenerateEntity.SingleIterationRunEntity(
node_id=node_id, inputs=args["inputs"]
),
workflow_run_id=str(uuid.uuid4()),
workflow_execution_id=str(uuid.uuid4()),
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
)
# Create workflow node execution repository
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
return self._generate(
@@ -274,6 +311,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
user=user,
invoke_from=InvokeFrom.DEBUGGER,
application_generate_entity=application_generate_entity,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
streaming=streaming,
)
@@ -317,18 +355,30 @@ class WorkflowAppGenerator(BaseAppGenerator):
invoke_from=InvokeFrom.DEBUGGER,
extras={"auto_generate_conversation_name": False},
single_loop_run=WorkflowAppGenerateEntity.SingleLoopRunEntity(node_id=node_id, inputs=args["inputs"]),
workflow_run_id=str(uuid.uuid4()),
workflow_execution_id=str(uuid.uuid4()),
)
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
contexts.plugin_tool_providers.set({})
contexts.plugin_tool_providers_lock.set(threading.Lock())
# Create repositories
#
# Create session factory
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
# Create workflow execution(aka workflow run) repository
workflow_execution_repository = SQLAlchemyWorkflowExecutionRepository(
session_factory=session_factory,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowRunTriggeredFrom.DEBUGGING,
)
# Create workflow node execution repository
session_factory = sessionmaker(bind=db.engine, expire_on_commit=False)
workflow_node_execution_repository = SQLAlchemyWorkflowNodeExecutionRepository(
session_factory=session_factory,
tenant_id=application_generate_entity.app_config.tenant_id,
user=user,
app_id=application_generate_entity.app_config.app_id,
triggered_from=WorkflowNodeExecutionTriggeredFrom.SINGLE_STEP,
)
return self._generate(
@@ -337,6 +387,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
user=user,
invoke_from=InvokeFrom.DEBUGGER,
application_generate_entity=application_generate_entity,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
streaming=streaming,
)
@@ -359,8 +410,22 @@ class WorkflowAppGenerator(BaseAppGenerator):
"""
for var, val in context.items():
var.set(val)
# FIXME(-LAN-): Save current user before entering new app context
from flask import g
saved_user = None
if has_request_context() and hasattr(g, "_login_user"):
saved_user = g._login_user
with flask_app.app_context():
try:
# Restore user in new app context
if saved_user is not None:
from flask import g
g._login_user = saved_user
# workflow app
runner = WorkflowAppRunner(
application_generate_entity=application_generate_entity,
@@ -394,6 +459,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow: Workflow,
queue_manager: AppQueueManager,
user: Union[Account, EndUser],
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
stream: bool = False,
) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
@@ -413,8 +479,9 @@ class WorkflowAppGenerator(BaseAppGenerator):
workflow=workflow,
queue_manager=queue_manager,
user=user,
stream=stream,
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
stream=stream,
)
try:

View File

@@ -95,7 +95,7 @@ class WorkflowAppRunner(WorkflowBasedAppRunner):
SystemVariableKey.USER_ID: user_id,
SystemVariableKey.APP_ID: app_config.app_id,
SystemVariableKey.WORKFLOW_ID: app_config.workflow_id,
SystemVariableKey.WORKFLOW_RUN_ID: self.application_generate_entity.workflow_run_id,
SystemVariableKey.WORKFLOW_EXECUTION_ID: self.application_generate_entity.workflow_execution_id,
}
variable_pool = VariablePool(

View File

@@ -3,10 +3,12 @@ import time
from collections.abc import Generator
from typing import Optional, Union
from sqlalchemy import select
from sqlalchemy.orm import Session
from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.apps.common.workflow_response_converter import WorkflowResponseConverter
from core.app.entities.app_invoke_entities import (
InvokeFrom,
WorkflowAppGenerateEntity,
@@ -48,24 +50,24 @@ from core.app.entities.task_entities import (
WorkflowAppStreamResponse,
WorkflowFinishStreamResponse,
WorkflowStartStreamResponse,
WorkflowTaskState,
)
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
from core.ops.ops_trace_manager import TraceQueueManager
from core.workflow.entities.workflow_execution import WorkflowExecution, WorkflowExecutionStatus, WorkflowType
from core.workflow.enums import SystemVariableKey
from core.workflow.repository.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.workflow_cycle_manager import WorkflowCycleManager
from core.workflow.repositories.workflow_execution_repository import WorkflowExecutionRepository
from core.workflow.repositories.workflow_node_execution_repository import WorkflowNodeExecutionRepository
from core.workflow.workflow_cycle_manager import CycleManagerWorkflowInfo, WorkflowCycleManager
from extensions.ext_database import db
from models.account import Account
from models.enums import CreatedByRole
from models.enums import CreatorUserRole
from models.model import EndUser
from models.workflow import (
Workflow,
WorkflowAppLog,
WorkflowAppLogCreatedFrom,
WorkflowRun,
WorkflowRunStatus,
)
logger = logging.getLogger(__name__)
@@ -83,6 +85,7 @@ class WorkflowAppGenerateTaskPipeline:
queue_manager: AppQueueManager,
user: Union[Account, EndUser],
stream: bool,
workflow_execution_repository: WorkflowExecutionRepository,
workflow_node_execution_repository: WorkflowNodeExecutionRepository,
) -> None:
self._base_task_pipeline = BasedGenerateTaskPipeline(
@@ -94,11 +97,11 @@ class WorkflowAppGenerateTaskPipeline:
if isinstance(user, EndUser):
self._user_id = user.id
user_session_id = user.session_id
self._created_by_role = CreatedByRole.END_USER
self._created_by_role = CreatorUserRole.END_USER
elif isinstance(user, Account):
self._user_id = user.id
user_session_id = user.id
self._created_by_role = CreatedByRole.ACCOUNT
self._created_by_role = CreatorUserRole.ACCOUNT
else:
raise ValueError(f"Invalid user type: {type(user)}")
@@ -109,15 +112,24 @@ class WorkflowAppGenerateTaskPipeline:
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,
SystemVariableKey.WORKFLOW_EXECUTION_ID: application_generate_entity.workflow_execution_id,
},
workflow_info=CycleManagerWorkflowInfo(
workflow_id=workflow.id,
workflow_type=WorkflowType(workflow.type),
version=workflow.version,
graph_data=workflow.graph_dict,
),
workflow_execution_repository=workflow_execution_repository,
workflow_node_execution_repository=workflow_node_execution_repository,
)
self._workflow_response_converter = WorkflowResponseConverter(
application_generate_entity=application_generate_entity,
)
self._application_generate_entity = application_generate_entity
self._workflow_id = workflow.id
self._workflow_features_dict = workflow.features_dict
self._task_state = WorkflowTaskState()
self._workflow_run_id = ""
def process(self) -> Union[WorkflowAppBlockingResponse, Generator[WorkflowAppStreamResponse, None, None]]:
@@ -256,19 +268,13 @@ class WorkflowAppGenerateTaskPipeline:
# override graph runtime state
graph_runtime_state = event.graph_runtime_state
with Session(db.engine, expire_on_commit=False) as session:
# init workflow run
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_cycle_manager._workflow_start_to_stream_response(
session=session, task_id=self._application_generate_entity.task_id, workflow_run=workflow_run
)
session.commit()
# init workflow run
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_start()
self._workflow_run_id = workflow_execution.id_
start_resp = self._workflow_response_converter.workflow_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
yield start_resp
elif isinstance(
@@ -278,13 +284,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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(
workflow_execution_id=self._workflow_run_id,
event=event,
)
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_retried(
workflow_run=workflow_run, event=event
)
response = self._workflow_cycle_manager._workflow_node_retry_to_stream_response(
response = self._workflow_response_converter.workflow_node_retry_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -297,27 +301,22 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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(
workflow_run=workflow_run, event=event
)
node_start_response = self._workflow_cycle_manager._workflow_node_start_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
)
session.commit()
workflow_node_execution = self._workflow_cycle_manager.handle_node_execution_start(
workflow_execution_id=self._workflow_run_id, event=event
)
node_start_response = self._workflow_response_converter.workflow_node_start_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
)
if node_start_response:
yield node_start_response
elif isinstance(event, QueueNodeSucceededEvent):
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_success(
workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_success(
event=event
)
node_success_response = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
node_success_response = self._workflow_response_converter.workflow_node_finish_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -332,10 +331,10 @@ class WorkflowAppGenerateTaskPipeline:
| QueueNodeInLoopFailedEvent
| QueueNodeExceptionEvent,
):
workflow_node_execution = self._workflow_cycle_manager._handle_workflow_node_execution_failed(
workflow_node_execution = self._workflow_cycle_manager.handle_workflow_node_execution_failed(
event=event,
)
node_failed_response = self._workflow_cycle_manager._workflow_node_finish_to_stream_response(
node_failed_response = self._workflow_response_converter.workflow_node_finish_to_stream_response(
event=event,
task_id=self._application_generate_entity.task_id,
workflow_node_execution=workflow_node_execution,
@@ -348,18 +347,13 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
)
parallel_start_resp = (
self._workflow_response_converter.workflow_parallel_branch_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
)
yield parallel_start_resp
@@ -367,18 +361,13 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
)
parallel_finish_resp = (
self._workflow_response_converter.workflow_parallel_branch_finished_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
)
yield parallel_finish_resp
@@ -386,16 +375,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_start_resp = self._workflow_response_converter.workflow_iteration_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_start_resp
@@ -403,16 +387,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_next_resp = self._workflow_response_converter.workflow_iteration_next_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_next_resp
@@ -420,16 +399,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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,
event=event,
)
iter_finish_resp = self._workflow_response_converter.workflow_iteration_completed_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield iter_finish_resp
@@ -437,16 +411,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_start_resp = self._workflow_cycle_manager._workflow_loop_start_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_start_resp = self._workflow_response_converter.workflow_loop_start_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_start_resp
@@ -454,16 +423,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_next_resp = self._workflow_cycle_manager._workflow_loop_next_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_next_resp = self._workflow_response_converter.workflow_loop_next_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_next_resp
@@ -471,16 +435,11 @@ class WorkflowAppGenerateTaskPipeline:
if not self._workflow_run_id:
raise ValueError("workflow run not initialized.")
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
)
loop_finish_resp = self._workflow_cycle_manager._workflow_loop_completed_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
event=event,
)
loop_finish_resp = self._workflow_response_converter.workflow_loop_completed_to_stream_response(
task_id=self._application_generate_entity.task_id,
workflow_execution_id=self._workflow_run_id,
event=event,
)
yield loop_finish_resp
@@ -491,10 +450,8 @@ class WorkflowAppGenerateTaskPipeline:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_success(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_success(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
outputs=event.outputs,
@@ -503,12 +460,12 @@ class WorkflowAppGenerateTaskPipeline:
)
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
self._save_workflow_app_log(session=session, workflow_execution=workflow_execution)
workflow_finish_resp = self._workflow_cycle_manager._workflow_finish_to_stream_response(
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_run=workflow_run,
workflow_execution=workflow_execution,
)
session.commit()
@@ -520,10 +477,8 @@ class WorkflowAppGenerateTaskPipeline:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_partial_success(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_partial_success(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
outputs=event.outputs,
@@ -533,10 +488,12 @@ class WorkflowAppGenerateTaskPipeline:
)
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
self._save_workflow_app_log(session=session, workflow_execution=workflow_execution)
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
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
session.commit()
@@ -548,26 +505,28 @@ class WorkflowAppGenerateTaskPipeline:
raise ValueError("graph runtime state not initialized.")
with Session(db.engine, expire_on_commit=False) as session:
workflow_run = self._workflow_cycle_manager._handle_workflow_run_failed(
session=session,
workflow_execution = self._workflow_cycle_manager.handle_workflow_run_failed(
workflow_run_id=self._workflow_run_id,
start_at=graph_runtime_state.start_at,
total_tokens=graph_runtime_state.total_tokens,
total_steps=graph_runtime_state.node_run_steps,
status=WorkflowRunStatus.FAILED
status=WorkflowExecutionStatus.FAILED
if isinstance(event, QueueWorkflowFailedEvent)
else WorkflowRunStatus.STOPPED,
error=event.error if isinstance(event, QueueWorkflowFailedEvent) else event.get_stop_reason(),
else WorkflowExecutionStatus.STOPPED,
error_message=event.error
if isinstance(event, QueueWorkflowFailedEvent)
else event.get_stop_reason(),
conversation_id=None,
trace_manager=trace_manager,
exceptions_count=event.exceptions_count if isinstance(event, QueueWorkflowFailedEvent) else 0,
)
# save workflow app log
self._save_workflow_app_log(session=session, workflow_run=workflow_run)
self._save_workflow_app_log(session=session, workflow_execution=workflow_execution)
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
workflow_finish_resp = self._workflow_response_converter.workflow_finish_to_stream_response(
session=session,
task_id=self._application_generate_entity.task_id,
workflow_execution=workflow_execution,
)
session.commit()
@@ -581,12 +540,11 @@ class WorkflowAppGenerateTaskPipeline:
if tts_publisher:
tts_publisher.publish(queue_message)
self._task_state.answer += delta_text
yield self._text_chunk_to_stream_response(
delta_text, from_variable_selector=event.from_variable_selector
)
elif isinstance(event, QueueAgentLogEvent):
yield self._workflow_cycle_manager._handle_agent_log(
yield self._workflow_response_converter.handle_agent_log(
task_id=self._application_generate_entity.task_id, event=event
)
else:
@@ -595,11 +553,9 @@ class WorkflowAppGenerateTaskPipeline:
if tts_publisher:
tts_publisher.publish(None)
def _save_workflow_app_log(self, *, session: Session, workflow_run: WorkflowRun) -> None:
"""
Save workflow app log.
:return:
"""
def _save_workflow_app_log(self, *, session: Session, workflow_execution: WorkflowExecution) -> None:
workflow_run = session.scalar(select(WorkflowRun).where(WorkflowRun.id == workflow_execution.id_))
assert workflow_run is not None
invoke_from = self._application_generate_entity.invoke_from
if invoke_from == InvokeFrom.SERVICE_API:
created_from = WorkflowAppLogCreatedFrom.SERVICE_API

View File

@@ -29,8 +29,8 @@ from core.app.entities.queue_entities import (
QueueWorkflowStartedEvent,
QueueWorkflowSucceededEvent,
)
from core.workflow.entities.node_entities import NodeRunMetadataKey
from core.workflow.entities.variable_pool import VariablePool
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
from core.workflow.graph_engine.entities.event import (
AgentLogEvent,
GraphEngineEvent,
@@ -295,7 +295,7 @@ class WorkflowBasedAppRunner(AppRunner):
inputs: Mapping[str, Any] | None = {}
process_data: Mapping[str, Any] | None = {}
outputs: Mapping[str, Any] | None = {}
execution_metadata: Mapping[NodeRunMetadataKey, Any] | None = {}
execution_metadata: Mapping[WorkflowNodeExecutionMetadataKey, Any] | None = {}
if node_run_result:
inputs = node_run_result.inputs
process_data = node_run_result.process_data

View File

@@ -76,6 +76,8 @@ class AppGenerateEntity(BaseModel):
App Generate Entity.
"""
model_config = ConfigDict(arbitrary_types_allowed=True)
task_id: str
# app config
@@ -99,9 +101,6 @@ class AppGenerateEntity(BaseModel):
# tracing instance
trace_manager: Optional[TraceQueueManager] = None
class Config:
arbitrary_types_allowed = True
class EasyUIBasedAppGenerateEntity(AppGenerateEntity):
"""
@@ -205,7 +204,7 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
# app config
app_config: WorkflowUIBasedAppConfig
workflow_run_id: str
workflow_execution_id: str
class SingleIterationRunEntity(BaseModel):
"""

View File

@@ -1,4 +1,4 @@
from collections.abc import Mapping
from collections.abc import Mapping, Sequence
from datetime import datetime
from enum import Enum, StrEnum
from typing import Any, Optional
@@ -6,7 +6,9 @@ from typing import Any, Optional
from pydantic import BaseModel
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
from core.workflow.entities.node_entities import AgentNodeStrategyInit, NodeRunMetadataKey
from core.rag.entities.citation_metadata import RetrievalSourceMetadata
from core.workflow.entities.node_entities import AgentNodeStrategyInit
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey
from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
from core.workflow.nodes import NodeType
from core.workflow.nodes.base import BaseNodeData
@@ -282,7 +284,7 @@ class QueueRetrieverResourcesEvent(AppQueueEvent):
"""
event: QueueEvent = QueueEvent.RETRIEVER_RESOURCES
retriever_resources: list[dict]
retriever_resources: Sequence[RetrievalSourceMetadata]
in_iteration_id: Optional[str] = None
"""iteration id if node is in iteration"""
in_loop_id: Optional[str] = None
@@ -412,7 +414,7 @@ class QueueNodeSucceededEvent(AppQueueEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: Optional[str] = None
"""single iteration duration map"""
@@ -446,7 +448,7 @@ class QueueNodeRetryEvent(QueueNodeStartedEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: str
retry_index: int # retry index
@@ -480,7 +482,7 @@ class QueueNodeInIterationFailedEvent(AppQueueEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: str
@@ -513,7 +515,7 @@ class QueueNodeInLoopFailedEvent(AppQueueEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: str
@@ -546,7 +548,7 @@ class QueueNodeExceptionEvent(AppQueueEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: str
@@ -579,7 +581,7 @@ class QueueNodeFailedEvent(AppQueueEvent):
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
execution_metadata: Optional[Mapping[NodeRunMetadataKey, Any]] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
error: str

View File

@@ -2,12 +2,29 @@ from collections.abc import Mapping, Sequence
from enum import Enum
from typing import Any, Optional
from pydantic import BaseModel, ConfigDict
from pydantic import BaseModel, ConfigDict, Field
from core.model_runtime.entities.llm_entities import LLMResult
from core.model_runtime.entities.llm_entities import LLMResult, LLMUsage
from core.model_runtime.utils.encoders import jsonable_encoder
from core.rag.entities.citation_metadata import RetrievalSourceMetadata
from core.workflow.entities.node_entities import AgentNodeStrategyInit
from models.workflow import WorkflowNodeExecutionStatus
from core.workflow.entities.workflow_node_execution import WorkflowNodeExecutionMetadataKey, WorkflowNodeExecutionStatus
class AnnotationReplyAccount(BaseModel):
id: str
name: str
class AnnotationReply(BaseModel):
id: str
account: AnnotationReplyAccount
class TaskStateMetadata(BaseModel):
annotation_reply: AnnotationReply | None = None
retriever_resources: Sequence[RetrievalSourceMetadata] = Field(default_factory=list)
usage: LLMUsage | None = None
class TaskState(BaseModel):
@@ -15,7 +32,7 @@ class TaskState(BaseModel):
TaskState entity
"""
metadata: dict = {}
metadata: TaskStateMetadata = Field(default_factory=TaskStateMetadata)
class EasyUITaskState(TaskState):
@@ -189,8 +206,7 @@ class WorkflowStartStreamResponse(StreamResponse):
id: str
workflow_id: str
sequence_number: int
inputs: dict
inputs: Mapping[str, Any]
created_at: int
event: StreamEvent = StreamEvent.WORKFLOW_STARTED
@@ -210,9 +226,8 @@ class WorkflowFinishStreamResponse(StreamResponse):
id: str
workflow_id: str
sequence_number: int
status: str
outputs: Optional[dict] = None
outputs: Optional[Mapping[str, Any]] = None
error: Optional[str] = None
elapsed_time: float
total_tokens: int
@@ -244,7 +259,7 @@ class NodeStartStreamResponse(StreamResponse):
title: str
index: int
predecessor_node_id: Optional[str] = None
inputs: Optional[dict] = None
inputs: Optional[Mapping[str, Any]] = None
created_at: int
extras: dict = {}
parallel_id: Optional[str] = None
@@ -301,13 +316,13 @@ class NodeFinishStreamResponse(StreamResponse):
title: str
index: int
predecessor_node_id: Optional[str] = None
inputs: Optional[dict] = None
process_data: Optional[dict] = None
outputs: Optional[dict] = None
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
status: str
error: Optional[str] = None
elapsed_time: float
execution_metadata: Optional[dict] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
created_at: int
finished_at: int
files: Optional[Sequence[Mapping[str, Any]]] = []
@@ -370,13 +385,13 @@ class NodeRetryStreamResponse(StreamResponse):
title: str
index: int
predecessor_node_id: Optional[str] = None
inputs: Optional[dict] = None
process_data: Optional[dict] = None
outputs: Optional[dict] = None
inputs: Optional[Mapping[str, Any]] = None
process_data: Optional[Mapping[str, Any]] = None
outputs: Optional[Mapping[str, Any]] = None
status: str
error: Optional[str] = None
elapsed_time: float
execution_metadata: Optional[dict] = None
execution_metadata: Optional[Mapping[WorkflowNodeExecutionMetadataKey, Any]] = None
created_at: int
finished_at: int
files: Optional[Sequence[Mapping[str, Any]]] = []
@@ -788,7 +803,7 @@ class WorkflowAppBlockingResponse(AppBlockingResponse):
id: str
workflow_id: str
status: str
outputs: Optional[dict] = None
outputs: Optional[Mapping[str, Any]] = None
error: Optional[str] = None
elapsed_time: float
total_tokens: int

View File

@@ -1,4 +1,3 @@
import json
import logging
import time
from collections.abc import Generator
@@ -43,7 +42,7 @@ from core.app.entities.task_entities import (
StreamResponse,
)
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
from core.app.task_pipeline.message_cycle_manage import MessageCycleManage
from core.app.task_pipeline.message_cycle_manager import MessageCycleManager
from core.base.tts import AppGeneratorTTSPublisher, AudioTrunk
from core.model_manager import ModelInstance
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
@@ -51,7 +50,6 @@ from core.model_runtime.entities.message_entities import (
AssistantPromptMessage,
)
from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
from core.model_runtime.utils.encoders import jsonable_encoder
from core.ops.entities.trace_entity import TraceTaskName
from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
from core.prompt.utils.prompt_message_util import PromptMessageUtil
@@ -63,7 +61,7 @@ from models.model import AppMode, Conversation, Message, MessageAgentThought
logger = logging.getLogger(__name__)
class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleManage):
class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline):
"""
EasyUIBasedGenerateTaskPipeline is a class that generate stream output and state management for Application.
"""
@@ -104,6 +102,11 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
)
)
self._message_cycle_manager = MessageCycleManager(
application_generate_entity=application_generate_entity,
task_state=self._task_state,
)
self._conversation_name_generate_thread: Optional[Thread] = None
def process(
@@ -115,7 +118,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
]:
if self._application_generate_entity.app_config.app_mode != AppMode.COMPLETION:
# 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 or ""
)
@@ -136,9 +139,9 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
if isinstance(stream_response, ErrorStreamResponse):
raise stream_response.err
elif isinstance(stream_response, MessageEndStreamResponse):
extras = {"usage": jsonable_encoder(self._task_state.llm_result.usage)}
extras = {"usage": self._task_state.llm_result.usage.model_dump()}
if self._task_state.metadata:
extras["metadata"] = self._task_state.metadata
extras["metadata"] = self._task_state.metadata.model_dump()
response: Union[ChatbotAppBlockingResponse, CompletionAppBlockingResponse]
if self._conversation_mode == AppMode.COMPLETION.value:
response = CompletionAppBlockingResponse(
@@ -277,7 +280,9 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
)
if output_moderation_answer:
self._task_state.llm_result.message.content = 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
)
with Session(db.engine) as session:
# Save message
@@ -286,9 +291,9 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
message_end_resp = self._message_end_to_stream_response()
yield message_end_resp
elif isinstance(event, QueueRetrieverResourcesEvent):
self._handle_retriever_resources(event)
self._message_cycle_manager.handle_retriever_resources(event)
elif isinstance(event, QueueAnnotationReplyEvent):
annotation = self._handle_annotation_reply(event)
annotation = self._message_cycle_manager.handle_annotation_reply(event)
if annotation:
self._task_state.llm_result.message.content = annotation.content
elif isinstance(event, QueueAgentThoughtEvent):
@@ -296,7 +301,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
if agent_thought_response is not None:
yield agent_thought_response
elif isinstance(event, QueueMessageFileEvent):
response = self._message_file_to_stream_response(event)
response = self._message_cycle_manager.message_file_to_stream_response(event)
if response:
yield response
elif isinstance(event, QueueLLMChunkEvent | QueueAgentMessageEvent):
@@ -318,7 +323,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
self._task_state.llm_result.message.content = current_content
if isinstance(event, QueueLLMChunkEvent):
yield self._message_to_stream_response(
yield self._message_cycle_manager.message_to_stream_response(
answer=cast(str, delta_text),
message_id=self._message_id,
)
@@ -328,7 +333,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
message_id=self._message_id,
)
elif isinstance(event, QueueMessageReplaceEvent):
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, QueuePingEvent):
yield self._ping_stream_response()
else:
@@ -372,9 +377,7 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
message.provider_response_latency = time.perf_counter() - self._start_at
message.total_price = usage.total_price
message.currency = usage.currency
message.message_metadata = (
json.dumps(jsonable_encoder(self._task_state.metadata)) if self._task_state.metadata else None
)
message.message_metadata = self._task_state.metadata.model_dump_json()
if trace_manager:
trace_manager.add_trace_task(
@@ -423,16 +426,12 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
Message end to stream response.
:return:
"""
self._task_state.metadata["usage"] = jsonable_encoder(self._task_state.llm_result.usage)
extras = {}
if self._task_state.metadata:
extras["metadata"] = self._task_state.metadata
self._task_state.metadata.usage = self._task_state.llm_result.usage
metadata_dict = self._task_state.metadata.model_dump()
return MessageEndStreamResponse(
task_id=self._application_generate_entity.task_id,
id=self._message_id,
metadata=extras.get("metadata", {}),
metadata=metadata_dict,
)
def _agent_message_to_stream_response(self, answer: str, message_id: str) -> AgentMessageStreamResponse:
@@ -455,8 +454,6 @@ class EasyUIBasedGenerateTaskPipeline(BasedGenerateTaskPipeline, MessageCycleMan
agent_thought: Optional[MessageAgentThought] = (
db.session.query(MessageAgentThought).filter(MessageAgentThought.id == event.agent_thought_id).first()
)
db.session.refresh(agent_thought)
db.session.close()
if agent_thought:
return AgentThoughtStreamResponse(

View File

@@ -17,6 +17,8 @@ from core.app.entities.queue_entities import (
QueueRetrieverResourcesEvent,
)
from core.app.entities.task_entities import (
AnnotationReply,
AnnotationReplyAccount,
EasyUITaskState,
MessageFileStreamResponse,
MessageReplaceStreamResponse,
@@ -30,7 +32,7 @@ from models.model import AppMode, Conversation, MessageAnnotation, MessageFile
from services.annotation_service import AppAnnotationService
class MessageCycleManage:
class MessageCycleManager:
def __init__(
self,
*,
@@ -45,7 +47,7 @@ class MessageCycleManage:
self._application_generate_entity = application_generate_entity
self._task_state = task_state
def _generate_conversation_name(self, *, conversation_id: str, query: str) -> Optional[Thread]:
def generate_conversation_name(self, *, conversation_id: str, query: str) -> Optional[Thread]:
"""
Generate conversation name.
:param conversation_id: conversation id
@@ -102,7 +104,7 @@ class MessageCycleManage:
db.session.commit()
db.session.close()
def _handle_annotation_reply(self, event: QueueAnnotationReplyEvent) -> Optional[MessageAnnotation]:
def handle_annotation_reply(self, event: QueueAnnotationReplyEvent) -> Optional[MessageAnnotation]:
"""
Handle annotation reply.
:param event: event
@@ -111,25 +113,28 @@ class MessageCycleManage:
annotation = AppAnnotationService.get_annotation_by_id(event.message_annotation_id)
if annotation:
account = annotation.account
self._task_state.metadata["annotation_reply"] = {
"id": annotation.id,
"account": {"id": annotation.account_id, "name": account.name if account else "Dify user"},
}
self._task_state.metadata.annotation_reply = AnnotationReply(
id=annotation.id,
account=AnnotationReplyAccount(
id=annotation.account_id,
name=account.name if account else "Dify user",
),
)
return annotation
return None
def _handle_retriever_resources(self, event: QueueRetrieverResourcesEvent) -> None:
def handle_retriever_resources(self, event: QueueRetrieverResourcesEvent) -> None:
"""
Handle retriever resources.
:param event: event
:return:
"""
if self._application_generate_entity.app_config.additional_features.show_retrieve_source:
self._task_state.metadata["retriever_resources"] = event.retriever_resources
self._task_state.metadata.retriever_resources = event.retriever_resources
def _message_file_to_stream_response(self, event: QueueMessageFileEvent) -> Optional[MessageFileStreamResponse]:
def message_file_to_stream_response(self, event: QueueMessageFileEvent) -> Optional[MessageFileStreamResponse]:
"""
Message file to stream response.
:param event: event
@@ -166,7 +171,7 @@ class MessageCycleManage:
return None
def _message_to_stream_response(
def message_to_stream_response(
self, answer: str, message_id: str, from_variable_selector: Optional[list[str]] = None
) -> MessageStreamResponse:
"""
@@ -182,7 +187,7 @@ class MessageCycleManage:
from_variable_selector=from_variable_selector,
)
def _message_replace_to_stream_response(self, answer: str, reason: str = "") -> MessageReplaceStreamResponse:
def message_replace_to_stream_response(self, answer: str, reason: str = "") -> MessageReplaceStreamResponse:
"""
Message replace to stream response.
:param answer: answer

View File

@@ -1,8 +1,10 @@
import logging
from collections.abc import Sequence
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
from core.app.entities.app_invoke_entities import InvokeFrom
from core.app.entities.queue_entities import QueueRetrieverResourcesEvent
from core.rag.entities.citation_metadata import RetrievalSourceMetadata
from core.rag.index_processor.constant.index_type import IndexType
from core.rag.models.document import Document
from extensions.ext_database import db
@@ -85,7 +87,8 @@ class DatasetIndexToolCallbackHandler:
db.session.commit()
def return_retriever_resource_info(self, resource: list):
# TODO(-LAN-): Improve type check
def return_retriever_resource_info(self, resource: Sequence[RetrievalSourceMetadata]):
"""Handle return_retriever_resource_info."""
self._queue_manager.publish(
QueueRetrieverResourcesEvent(retriever_resources=resource), PublishFrom.APPLICATION_MANAGER

View File

@@ -55,6 +55,25 @@ class ProviderModelWithStatusEntity(ProviderModel):
status: ModelStatus
load_balancing_enabled: bool = False
def raise_for_status(self) -> None:
"""
Check model status and raise ValueError if not active.
:raises ValueError: When model status is not active, with a descriptive message
"""
if self.status == ModelStatus.ACTIVE:
return
error_messages = {
ModelStatus.NO_CONFIGURE: "Model is not configured",
ModelStatus.QUOTA_EXCEEDED: "Model quota has been exceeded",
ModelStatus.NO_PERMISSION: "No permission to use this model",
ModelStatus.DISABLED: "Model is disabled",
}
if self.status in error_messages:
raise ValueError(error_messages[self.status])
class ModelWithProviderEntity(ProviderModelWithStatusEntity):
"""

View File

@@ -754,7 +754,7 @@ class ProviderConfiguration(BaseModel):
:param only_active: return active model only
:return:
"""
provider_models = self.get_provider_models(model_type, only_active)
provider_models = self.get_provider_models(model_type, only_active, model)
for provider_model in provider_models:
if provider_model.model == model:
@@ -763,12 +763,13 @@ class ProviderConfiguration(BaseModel):
return None
def get_provider_models(
self, model_type: Optional[ModelType] = None, only_active: bool = False
self, model_type: Optional[ModelType] = None, only_active: bool = False, model: Optional[str] = None
) -> list[ModelWithProviderEntity]:
"""
Get provider models.
:param model_type: model type
:param only_active: only active models
:param model: model name
:return:
"""
model_provider_factory = ModelProviderFactory(self.tenant_id)
@@ -791,7 +792,10 @@ class ProviderConfiguration(BaseModel):
)
else:
provider_models = self._get_custom_provider_models(
model_types=model_types, provider_schema=provider_schema, model_setting_map=model_setting_map
model_types=model_types,
provider_schema=provider_schema,
model_setting_map=model_setting_map,
model=model,
)
if only_active:
@@ -943,6 +947,7 @@ class ProviderConfiguration(BaseModel):
model_types: Sequence[ModelType],
provider_schema: ProviderEntity,
model_setting_map: dict[ModelType, dict[str, ModelSettings]],
model: Optional[str] = None,
) -> list[ModelWithProviderEntity]:
"""
Get custom provider models.
@@ -995,7 +1000,8 @@ class ProviderConfiguration(BaseModel):
for model_configuration in self.custom_configuration.models:
if model_configuration.model_type not in model_types:
continue
if model and model != model_configuration.model:
continue
try:
custom_model_schema = self.get_model_schema(
model_type=model_configuration.model_type,

View File

@@ -41,45 +41,53 @@ class Extensible:
extensions = []
position_map: dict[str, int] = {}
# get the path of the current class
current_path = os.path.abspath(cls.__module__.replace(".", os.path.sep) + ".py")
current_dir_path = os.path.dirname(current_path)
# Get the package name from the module path
package_name = ".".join(cls.__module__.split(".")[:-1])
# traverse subdirectories
for subdir_name in os.listdir(current_dir_path):
if subdir_name.startswith("__"):
continue
try:
# Get package directory path
package_spec = importlib.util.find_spec(package_name)
if not package_spec or not package_spec.origin:
raise ImportError(f"Could not find package {package_name}")
subdir_path = os.path.join(current_dir_path, subdir_name)
extension_name = subdir_name
if os.path.isdir(subdir_path):
package_dir = os.path.dirname(package_spec.origin)
# Traverse subdirectories
for subdir_name in os.listdir(package_dir):
if subdir_name.startswith("__"):
continue
subdir_path = os.path.join(package_dir, subdir_name)
if not os.path.isdir(subdir_path):
continue
extension_name = subdir_name
file_names = os.listdir(subdir_path)
# is builtin extension, builtin extension
# in the front-end page and business logic, there are special treatments.
# Check for extension module file
if (extension_name + ".py") not in file_names:
logging.warning(f"Missing {extension_name}.py file in {subdir_path}, Skip.")
continue
# Check for builtin flag and position
builtin = False
# default position is 0 can not be None for sort_to_dict_by_position_map
position = 0
if "__builtin__" in file_names:
builtin = True
builtin_file_path = os.path.join(subdir_path, "__builtin__")
if os.path.exists(builtin_file_path):
position = int(Path(builtin_file_path).read_text(encoding="utf-8").strip())
position_map[extension_name] = position
if (extension_name + ".py") not in file_names:
logging.warning(f"Missing {extension_name}.py file in {subdir_path}, Skip.")
continue
# Dynamic loading {subdir_name}.py file and find the subclass of Extensible
py_path = os.path.join(subdir_path, extension_name + ".py")
spec = importlib.util.spec_from_file_location(extension_name, py_path)
# Import the extension module
module_name = f"{package_name}.{extension_name}.{extension_name}"
spec = importlib.util.find_spec(module_name)
if not spec or not spec.loader:
raise Exception(f"Failed to load module {extension_name} from {py_path}")
raise ImportError(f"Failed to load module {module_name}")
mod = importlib.util.module_from_spec(spec)
spec.loader.exec_module(mod)
# Find extension class
extension_class = None
for name, obj in vars(mod).items():
if isinstance(obj, type) and issubclass(obj, cls) and obj != cls:
@@ -87,21 +95,21 @@ class Extensible:
break
if not extension_class:
logging.warning(f"Missing subclass of {cls.__name__} in {py_path}, Skip.")
logging.warning(f"Missing subclass of {cls.__name__} in {module_name}, Skip.")
continue
# Load schema if not builtin
json_data: dict[str, Any] = {}
if not builtin:
if "schema.json" not in file_names:
json_path = os.path.join(subdir_path, "schema.json")
if not os.path.exists(json_path):
logging.warning(f"Missing schema.json file in {subdir_path}, Skip.")
continue
json_path = os.path.join(subdir_path, "schema.json")
json_data = {}
if os.path.exists(json_path):
with open(json_path, encoding="utf-8") as f:
json_data = json.load(f)
with open(json_path, encoding="utf-8") as f:
json_data = json.load(f)
# Create extension
extensions.append(
ModuleExtension(
extension_class=extension_class,
@@ -113,6 +121,11 @@ class Extensible:
)
)
except Exception as e:
logging.exception("Error scanning extensions")
raise
# Sort extensions by position
sorted_extensions = sort_to_dict_by_position_map(
position_map=position_map, data=extensions, name_func=lambda x: x.name
)

View File

@@ -15,6 +15,7 @@ from core.helper.code_executor.python3.python3_transformer import Python3Templat
from core.helper.code_executor.template_transformer import TemplateTransformer
logger = logging.getLogger(__name__)
code_execution_endpoint_url = URL(str(dify_config.CODE_EXECUTION_ENDPOINT))
class CodeExecutionError(Exception):
@@ -64,7 +65,7 @@ class CodeExecutor:
:param code: code
:return:
"""
url = URL(str(dify_config.CODE_EXECUTION_ENDPOINT)) / "v1" / "sandbox" / "run"
url = code_execution_endpoint_url / "v1" / "sandbox" / "run"
headers = {"X-Api-Key": dify_config.CODE_EXECUTION_API_KEY}

View File

@@ -7,29 +7,28 @@ from configs import dify_config
from core.helper.download import download_with_size_limit
from core.plugin.entities.marketplace import MarketplacePluginDeclaration
marketplace_api_url = URL(str(dify_config.MARKETPLACE_API_URL))
def get_plugin_pkg_url(plugin_unique_identifier: str):
return (URL(str(dify_config.MARKETPLACE_API_URL)) / "api/v1/plugins/download").with_query(
unique_identifier=plugin_unique_identifier
)
def get_plugin_pkg_url(plugin_unique_identifier: str) -> str:
return str((marketplace_api_url / "api/v1/plugins/download").with_query(unique_identifier=plugin_unique_identifier))
def download_plugin_pkg(plugin_unique_identifier: str):
url = str(get_plugin_pkg_url(plugin_unique_identifier))
return download_with_size_limit(url, dify_config.PLUGIN_MAX_PACKAGE_SIZE)
return download_with_size_limit(get_plugin_pkg_url(plugin_unique_identifier), dify_config.PLUGIN_MAX_PACKAGE_SIZE)
def batch_fetch_plugin_manifests(plugin_ids: list[str]) -> Sequence[MarketplacePluginDeclaration]:
if len(plugin_ids) == 0:
return []
url = str(URL(str(dify_config.MARKETPLACE_API_URL)) / "api/v1/plugins/batch")
url = str(marketplace_api_url / "api/v1/plugins/batch")
response = requests.post(url, json={"plugin_ids": plugin_ids})
response.raise_for_status()
return [MarketplacePluginDeclaration(**plugin) for plugin in response.json()["data"]["plugins"]]
def record_install_plugin_event(plugin_unique_identifier: str):
url = str(URL(str(dify_config.MARKETPLACE_API_URL)) / "api/v1/stats/plugins/install_count")
url = str(marketplace_api_url / "api/v1/stats/plugins/install_count")
response = requests.post(url, json={"unique_identifier": plugin_unique_identifier})
response.raise_for_status()

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