Compare commits

..

259 Commits

Author SHA1 Message Date
pablodanswer
49b1a456c2 functioning well 2025-01-19 18:44:40 -08:00
pablodanswer
22626bd131 toggling 2025-01-19 16:35:20 -08:00
pablodanswer
b3c2818a2c update 2025-01-19 16:28:54 -08:00
pablodanswer
4de1277e31 additional improvements 2025-01-19 16:16:18 -08:00
pablodanswer
c937a9d084 functional summarization 2025-01-19 15:41:43 -08:00
pablodanswer
713d66ff97 k 2025-01-19 14:28:09 -08:00
pablodanswer
7e4f4cf534 proper streaming 2025-01-19 14:23:55 -08:00
pablodanswer
babf7067dc copy update 2025-01-19 13:41:52 -08:00
pablodanswer
ab03aa9330 k 2025-01-19 13:39:45 -08:00
pablodanswer
2f154972ed decrease padding 2025-01-19 13:17:09 -08:00
pablodanswer
9430eae83f additional steps, values, etc. 2025-01-19 13:12:16 -08:00
pablodanswer
424ef41e95 remove debugging 2025-01-19 08:31:47 -08:00
pablodanswer
8191210432 quick reversion of break 2025-01-19 08:31:20 -08:00
pablodanswer
33832eea4a ensure local changes pushed 2025-01-18 21:56:01 -08:00
pablodanswer
30fdf02f3b mostly cleaned up 2025-01-18 19:23:29 -08:00
pablodanswer
0b266a75bb looking good (mlst) 2025-01-18 18:30:57 -08:00
pablodanswer
a1d0ab8328 quick nit 2025-01-18 18:13:33 -08:00
pablodanswer
cdbbcf505f push updates 2025-01-18 18:04:12 -08:00
pablodanswer
9d46e62181 add toggle + various improvements 2025-01-18 17:43:05 -08:00
pablodanswer
c2ba042bda misc 2025-01-18 17:43:05 -08:00
pablodanswer
8d7b6a50d8 misc improvements 2025-01-18 17:43:05 -08:00
pablodanswer
955ec3c779 remove double click 2025-01-18 17:43:05 -08:00
pablodanswer
9ff5f52a48 hide red overlay (temporary) 2025-01-18 17:43:05 -08:00
pablodanswer
34b9beaefd remove minor debugging 2025-01-18 17:43:04 -08:00
pablodanswer
c69219a92c quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
61b3f36ce6 quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
8b965eebfd additional debugging 2025-01-18 17:43:04 -08:00
pablodanswer
4c60a64dbd quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
a0fe5c8cb0 quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
f95b1e9bfd fix api persona arg 2025-01-18 17:43:04 -08:00
pablodanswer
9739844e87 k 2025-01-18 17:43:04 -08:00
pablodanswer
cfb0438770 clean up 2025-01-18 17:43:04 -08:00
pablodanswer
8ba27d1f4e nit 2025-01-18 17:43:04 -08:00
pablodanswer
dd14c0bf32 nit 2025-01-18 17:43:04 -08:00
pablodanswer
8c8634b1b3 nit 2025-01-18 17:43:04 -08:00
pablodanswer
645cb93da4 fix typo 2025-01-18 17:43:04 -08:00
pablodanswer
664f483b84 citation processing nit 2025-01-18 17:43:04 -08:00
pablodanswer
82a7e56a3b minor cleanup 2025-01-18 17:43:04 -08:00
pablodanswer
a1f20efa9e additional expansion logic 2025-01-18 17:43:04 -08:00
pablodanswer
49663757ae k 2025-01-18 17:43:04 -08:00
pablodanswer
b6bfc612a6 k 2025-01-18 17:43:04 -08:00
pablodanswer
e1831734c7 remove debugging 2025-01-18 17:43:04 -08:00
pablodanswer
9541fe2362 k 2025-01-18 17:43:04 -08:00
pablodanswer
ceee5c5ba3 k 2025-01-18 17:43:04 -08:00
pablodanswer
d34cbaa6c2 debugging 2025-01-18 17:43:04 -08:00
pablodanswer
b56411507e k 2025-01-18 17:43:04 -08:00
pablodanswer
2c63997206 fix typo 2025-01-18 17:43:04 -08:00
pablodanswer
65871a5bda potential fix 2025-01-18 17:43:04 -08:00
pablodanswer
9ef6b01add debugging 2025-01-18 17:43:04 -08:00
pablodanswer
a4e86923b8 push changes 2025-01-18 17:43:04 -08:00
pablodanswer
fcb0fdb6ca post rebase 2025-01-18 17:43:04 -08:00
pablodanswer
9961234c77 very clean 2025-01-18 17:43:04 -08:00
pablodanswer
c8437422fe k 2025-01-18 17:43:04 -08:00
pablodanswer
03b1af4bcd local 2025-01-18 17:43:04 -08:00
pablodanswer
3eae8db035 k 2025-01-18 17:43:04 -08:00
pablodanswer
e8983b033b push citations 2025-01-18 17:43:04 -08:00
pablodanswer
12ad4a06fa fully functional 2025-01-18 17:43:04 -08:00
pablodanswer
24cc208648 fix citations 2025-01-18 17:43:04 -08:00
pablodanswer
4786f453f7 update display 2025-01-18 17:43:04 -08:00
pablodanswer
a461207f1c nit 2025-01-18 17:43:04 -08:00
pablodanswer
5d45193033 cleaner flow + refinement 2025-01-18 17:43:04 -08:00
pablodanswer
d57413d849 update various components 2025-01-18 17:43:04 -08:00
pablodanswer
72322fae5d push local changes 2025-01-18 17:43:04 -08:00
pablodanswer
909198d63b update values 2025-01-18 17:43:04 -08:00
pablodanswer
61f424db0a k 2025-01-18 17:43:04 -08:00
pablodanswer
1dd51cb83b persistence + non-agentic indicators 2025-01-18 17:43:04 -08:00
pablodanswer
20aa2b1eaf k 2025-01-18 17:43:04 -08:00
pablodanswer
6977ffa806 fix up streaming 2025-01-18 17:43:04 -08:00
pablodanswer
f3dfae0a30 push reversion 2025-01-18 17:43:04 -08:00
pablodanswer
7349a71bb7 k 2025-01-18 17:43:04 -08:00
pablodanswer
324f036e33 nits 2025-01-18 17:43:04 -08:00
pablodanswer
030f295be2 post rebase fix 2025-01-18 17:43:04 -08:00
pablodanswer
1078119395 k 2025-01-18 17:43:04 -08:00
pablodanswer
534cddf06f various nits 2025-01-18 17:43:04 -08:00
pablodanswer
b8a20d4d8f various small nits 2025-01-18 17:43:04 -08:00
pablodanswer
b43703c5cb in a good place 2025-01-18 17:43:04 -08:00
pablodanswer
9fde1dad75 clean processing 2025-01-18 17:43:04 -08:00
pablodanswer
2644aabd2d updated streaming 2025-01-18 17:43:04 -08:00
pablodanswer
ae0bfb771e nit 2025-01-18 17:43:04 -08:00
pablodanswer
ee6f40cd1a looking good! persistence + streaming 2025-01-18 17:43:04 -08:00
pablodanswer
06ea2f4da9 quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
1028931179 improved streaming 2025-01-18 17:43:04 -08:00
pablodanswer
870deeea41 smooth streaming 2025-01-18 17:43:04 -08:00
pablodanswer
03700d23cd quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
18edc247bd additional doc streaming 2025-01-18 17:43:04 -08:00
pablodanswer
95c5ccda46 quick nits 2025-01-18 17:43:04 -08:00
pablodanswer
d08928212c nit 2025-01-18 17:43:04 -08:00
pablodanswer
8fdf93fd08 proper persistence streaming ux 2025-01-18 17:43:04 -08:00
pablodanswer
b69022d6ef nit 2025-01-18 17:43:04 -08:00
pablodanswer
910a9583e9 update fe 2025-01-18 17:43:04 -08:00
pablodanswer
6a6ecf0899 quick nit 2025-01-18 17:43:04 -08:00
pablodanswer
a0d2f299dd nit 2025-01-18 17:43:04 -08:00
pablodanswer
0a1df800b1 update values 2025-01-18 17:43:04 -08:00
pablodanswer
b6ea45ac28 k 2025-01-18 17:43:04 -08:00
Evan Lohn
e955279186 fixed pro search config creation 2025-01-18 17:42:07 -08:00
joachim-danswer
a48611ef57 Updated initial search flags for UI flows
- may need tweaking
2025-01-18 16:49:44 -08:00
Evan Lohn
6fe4ce1dd6 fix non updated key issue 2025-01-18 16:15:19 -08:00
Evan Lohn
640f64d5de fixed pro search flag and unnecessary/incorrect streaming 2025-01-18 15:59:29 -08:00
Evan Lohn
a0517a8da7 finish pro->agentic rename 2025-01-18 15:10:55 -08:00
joachim-danswer
afeb7f2dd8 prompt update to suggest doc citations vs question citations 2025-01-18 15:10:13 -08:00
joachim-danswer
91ee90b00d added 'Agent Search' decision 2025-01-18 14:39:00 -08:00
joachim-danswer
5d5a8b2218 Changed "I don't know" to a more appropriate response
And some other small prompt modifications.
2025-01-18 10:38:58 -08:00
joachim-danswer
7ef928794d optional search to inform decomposition
New Agent Search parameter:
  - perform_initial_search (default: False)
2025-01-18 10:16:00 -08:00
Evan Lohn
0df0b7147a name cleanup and WIP unifying input types 2025-01-17 19:54:15 -08:00
Evan Lohn
fb3bc2f259 working version with cleanup 2025-01-17 17:16:41 -08:00
Evan Lohn
e8fd57a1ac WIP 2025-01-17 17:06:43 -08:00
Evan Lohn
9d7c337ee6 skip answer verification for idk answers 2025-01-16 17:04:31 -08:00
Evan Lohn
38fd061ed5 cleanup hardcoded idks 2025-01-16 16:41:00 -08:00
Evan Lohn
7282447186 clean run_graph 2025-01-16 16:15:59 -08:00
joachim-danswer
b6da896240 removal of citations from previous answers 2025-01-16 14:26:41 -08:00
joachim-danswer
4dad841bfc new refined prompt 2025-01-16 14:25:44 -08:00
joachim-danswer
755b7579b5 sub_question number handling 2025-01-16 14:25:38 -08:00
Evan Lohn
42257244d9 finished checks for llm context window before invoking or streaming 2025-01-16 14:10:05 -08:00
joachim-danswer
3991eac4c0 new citation format 2025-01-15 17:17:04 -08:00
Evan Lohn
fabc9f7e4b attempted fix for early exit from langgraph event loop 2025-01-15 17:05:47 -08:00
Evan Lohn
7987a3a75e mypy error on unbound locals 2025-01-15 15:43:55 -08:00
Evan Lohn
ff24f82d52 unbound local error 2025-01-15 15:32:24 -08:00
Evan Lohn
563513698b fixed no good subquestions error 2025-01-15 15:23:59 -08:00
Evan Lohn
b2208195ce fixed streaming and persistence of answer docs 2025-01-15 14:55:52 -08:00
Evan Lohn
ac9ce7ca68 added back saved docs for agentic search 2025-01-15 14:23:24 -08:00
joachim-danswer
c9b34ed583 Updated citation handling on backend + citations for refined answer 2025-01-15 14:16:04 -08:00
Evan Lohn
2bc948fa73 dispatch initial question as dummy subquestion 2025-01-15 11:51:13 -08:00
Evan Lohn
8ea987e068 remove empty expanded subquestions 2025-01-15 11:35:00 -08:00
Evan Lohn
43e488275f context length fix 2025-01-15 11:35:00 -08:00
joachim-danswer
09d0820882 Question numbering fix (logging temp to info) 2025-01-15 11:30:46 -08:00
Evan Lohn
2c0ef2ea47 better separated dispatch 2025-01-15 10:26:38 -08:00
Evan Lohn
7cca660a93 handle prompts that exceed context window 2025-01-14 18:58:12 -08:00
Evan Lohn
ab70b7c303 persistence of refined agent answer and top-level handling of fine grained citations (WIP) 2025-01-14 17:28:40 -08:00
pablodanswer
0ff212a2b4 alembic migration 2025-01-14 14:41:14 -08:00
pablodanswer
5c31171b37 Merge branch 'pro-search' of github.com:onyx-dot-app/onyx into pro-search 2025-01-14 14:38:27 -08:00
pablodanswer
1669a5d69f alembic migration 2025-01-14 14:37:59 -08:00
pablodanswer
60db37fac1 alembic migration 2025-01-14 14:35:43 -08:00
joachim-danswer
48a4e2c76b refined prompt fix 2025-01-14 14:35:43 -08:00
Evan Lohn
e1175e15da stream refined answer 2025-01-14 14:35:43 -08:00
Evan Lohn
27b044c030 fix local variable access issue 2025-01-14 14:35:43 -08:00
Evan Lohn
4a7c6a6561 subquestion numbers start at 1 2025-01-14 14:35:43 -08:00
Evan Lohn
78df113c7f un-break refinement flow and stream answer 2025-01-14 14:35:43 -08:00
Evan Lohn
113767a061 stream stop info consistency 2025-01-14 14:35:43 -08:00
pablodanswer
1851c836dc alembic migration 2025-01-14 14:35:43 -08:00
Evan Lohn
413a4e55f5 use correct doc id 2025-01-14 14:35:43 -08:00
Evan Lohn
dfcf8791e7 tool call kickoffs for starting agentic, starting refined 2025-01-14 14:35:43 -08:00
Evan Lohn
1b9f128851 verified docs for persisted info 2025-01-14 14:35:43 -08:00
Evan Lohn
d38b9bd194 cleanup run_graph and added stream stopping for sub_answers 2025-01-14 14:35:43 -08:00
Evan Lohn
ee304c9c35 improved no-subquestion-gen handling 2025-01-14 14:35:43 -08:00
joachim-danswer
4c75b73fa8 Pro_search B + fix for no docs retrieved 2025-01-14 14:35:43 -08:00
Evan Lohn
70509fbe7e attach persisted agent search info to assistant message 2025-01-14 14:35:43 -08:00
Evan Lohn
6bea880695 added subquestion info to streamed docs, removed extra deduping 2025-01-14 14:35:43 -08:00
Evan Lohn
249dd96f25 tentative fix for not persisting search docs 2025-01-14 14:35:43 -08:00
Evan Lohn
f0e74618e2 fixed issue when tool call unnecessary 2025-01-14 14:35:43 -08:00
Evan Lohn
3e27b79040 better answer persistence 2025-01-14 14:35:43 -08:00
Evan Lohn
91a37ef345 save agent answers 2025-01-14 14:35:43 -08:00
Evan Lohn
6c2f4e4775 fix citation processing in basic search 2025-01-14 14:35:43 -08:00
Evan Lohn
87101c8c74 fix run_graph testing script 2025-01-14 14:35:43 -08:00
Evan Lohn
9887be3dfc fixed issues with standard flow 2025-01-14 14:35:43 -08:00
Evan Lohn
22e209afc8 add back old citation processing temporarily 2025-01-14 14:35:43 -08:00
Evan Lohn
05a4792575 fix heads issue 2025-01-14 14:35:43 -08:00
Evan Lohn
f79d44bd6e Pro search clean commmit. See evan_answer_rework branch for prior history 2025-01-14 14:35:43 -08:00
pablonyx
5081d240ce Proper anonymous user restricting (#3645) 2025-01-14 14:35:42 -08:00
pablodanswer
a570d39301 validated 2025-01-14 14:15:41 -08:00
pablodanswer
cd9279f0e1 additional label filtering 2025-01-14 13:49:12 -08:00
pablodanswer
72d1928b8f label editing / deletion 2025-01-14 13:45:49 -08:00
pablodanswer
086bba6454 fully cleaned assistant editor 2025-01-14 13:40:41 -08:00
pablodanswer
289be0a423 user settings etc. 2025-01-14 13:31:37 -08:00
pablodanswer
862a62483c various improvements 2025-01-14 13:19:25 -08:00
pablodanswer
694925d81d k 2025-01-14 12:33:34 -08:00
pablodanswer
478eb511fa add shortcuts, reorganize various pages,update seeding, starter messages, etc. 2025-01-14 12:30:05 -08:00
pablodanswer
a259f92f39 alembic migration 2025-01-13 20:55:52 -08:00
joachim-danswer
9592f0a494 refined prompt fix 2025-01-13 20:54:39 -08:00
Evan Lohn
07c2336c08 stream refined answer 2025-01-13 20:54:39 -08:00
Evan Lohn
7350dd73d1 fix local variable access issue 2025-01-13 20:54:39 -08:00
Evan Lohn
8f428cfcec subquestion numbers start at 1 2025-01-13 20:54:39 -08:00
Evan Lohn
3610a51222 un-break refinement flow and stream answer 2025-01-13 20:54:39 -08:00
Evan Lohn
e0654c2209 stream stop info consistency 2025-01-13 20:54:39 -08:00
pablodanswer
99d7c09433 alembic migration 2025-01-13 20:54:39 -08:00
Evan Lohn
6803702ca3 use correct doc id 2025-01-13 20:54:39 -08:00
Evan Lohn
4ea0ca5a78 tool call kickoffs for starting agentic, starting refined 2025-01-13 20:54:39 -08:00
Evan Lohn
561e44e443 verified docs for persisted info 2025-01-13 20:54:39 -08:00
Evan Lohn
931a119498 cleanup run_graph and added stream stopping for sub_answers 2025-01-13 20:54:39 -08:00
Evan Lohn
fddc1882d1 improved no-subquestion-gen handling 2025-01-13 20:54:39 -08:00
joachim-danswer
086d70a085 Pro_search B + fix for no docs retrieved 2025-01-13 20:54:39 -08:00
Evan Lohn
5a832628e2 attach persisted agent search info to assistant message 2025-01-13 20:54:39 -08:00
Evan Lohn
dfe1ed4c66 added subquestion info to streamed docs, removed extra deduping 2025-01-13 20:54:39 -08:00
Evan Lohn
5761557c19 tentative fix for not persisting search docs 2025-01-13 20:54:39 -08:00
Evan Lohn
29c479f496 fixed issue when tool call unnecessary 2025-01-13 20:54:39 -08:00
Evan Lohn
b60002c791 better answer persistence 2025-01-13 20:54:39 -08:00
Evan Lohn
b49c5afb09 save agent answers 2025-01-13 20:54:39 -08:00
Evan Lohn
b15e29619a fix citation processing in basic search 2025-01-13 20:54:39 -08:00
Evan Lohn
119336035e fix run_graph testing script 2025-01-13 20:54:39 -08:00
Evan Lohn
25bb5983af fixed issues with standard flow 2025-01-13 20:54:39 -08:00
Evan Lohn
ca1c12f122 add back old citation processing temporarily 2025-01-13 20:54:39 -08:00
Evan Lohn
9b55643e55 fix heads issue 2025-01-13 20:54:39 -08:00
Evan Lohn
233bbfa4e4 Pro search clean commmit. See evan_answer_rework branch for prior history 2025-01-13 20:54:36 -08:00
pablonyx
8c67288197 Proper anonymous user restricting (#3645) 2025-01-13 20:54:05 -08:00
pablodanswer
26c5c57ddb quick v1 labels 2025-01-13 19:45:00 -08:00
pablodanswer
ac15d0002a k 2025-01-13 18:01:19 -08:00
pablodanswer
8cca29eeab fix width + editors 2025-01-13 17:58:25 -08:00
pablodanswer
a365ab0c7d remove some whitespace 2025-01-13 17:55:29 -08:00
pablodanswer
fd89d1e141 quick nit 2025-01-13 17:53:38 -08:00
pablodanswer
7e32d21236 push quick changes from diff 2025-01-13 17:52:08 -08:00
pablodanswer
71eab9c740 push 2025-01-13 17:47:36 -08:00
pablodanswer
5c4451c084 :wMerge branch 'new_ux_branch' of github.com:onyx-dot-app/onyx into new_ux_branch 2025-01-13 17:34:37 -08:00
pablodanswer
2c894aaf07 quick nit 2025-01-13 17:32:04 -08:00
Yuhong Sun
bf3da9f9cf k 2025-01-13 17:25:31 -08:00
Yuhong Sun
4506770dd9 Yuhong 2025-01-13 17:16:15 -08:00
pablodanswer
25e2dfa5df k 2025-01-13 13:45:20 -08:00
pablodanswer
ba2d5fcc7d add input prompts 2025-01-13 13:43:41 -08:00
pablodanswer
f9be71ff24 l 2025-01-13 12:44:21 -08:00
pablodanswer
b92485223b sidebar 2025-01-13 12:44:04 -08:00
pablodanswer
5790f37648 quick nit 2025-01-13 12:41:32 -08:00
pablodanswer
b641cfc3e4 Merge branch 'new_ux_branch' of github.com:onyx-dot-app/onyx into new_ux_branch 2025-01-13 12:39:36 -08:00
pablodanswer
a2dfbb5b9c update assistant editor 2025-01-13 12:39:16 -08:00
Yuhong Sun
570ba9f0b6 Yuhong 2025-01-13 12:17:21 -08:00
pablodanswer
650fee6e2c quick updates 2025-01-13 12:00:47 -08:00
pablodanswer
8aa7fb5027 Merge branch 'new_ux_branch' of github.com:onyx-dot-app/onyx into new_ux_branch 2025-01-13 10:04:39 -08:00
pablodanswer
e4bf04fd94 update chat banner 2025-01-13 10:04:31 -08:00
Yuhong Sun
70de4708d0 Yuhong 2025-01-13 10:03:57 -08:00
pablodanswer
4ed9f0ffc7 editor changes 2025-01-12 21:22:35 -08:00
pablodanswer
7b67546199 k 2025-01-12 19:17:38 -08:00
pablodanswer
6c68a53c62 nit 2025-01-12 19:14:19 -08:00
pablodanswer
9e3b1d29aa nit 2025-01-12 18:25:40 -08:00
pablodanswer
ec7a606f4c popover within a popover > modal within a modal 2025-01-12 18:08:00 -08:00
pablodanswer
4e5bc7a4ba quick nit 2025-01-12 17:46:52 -08:00
pablodanswer
55d3b0f271 Merge branch 'new_ux_branch' of github.com:onyx-dot-app/onyx into new_ux_branch 2025-01-12 17:45:18 -08:00
pablodanswer
565bfa4e88 address all but modal within modal 2025-01-12 17:42:34 -08:00
Yuhong Sun
9ad10d1f60 Yuhong 2025-01-12 17:10:38 -08:00
pablodanswer
ad19e9aee7 k 2025-01-12 16:47:57 -08:00
pablodanswer
b11641c2bc most new fixes 2025-01-12 16:32:52 -08:00
pablodanswer
b7307813d5 quick nits 2025-01-12 16:22:21 -08:00
Yuhong Sun
3e8e544086 Yuhong 2025-01-12 14:03:36 -08:00
pablodanswer
7ba00f8b48 quick nit 2025-01-12 12:17:56 -08:00
pablodanswer
19204b49a7 final updates 2025-01-12 12:13:05 -08:00
pablodanswer
7254cb642d fully updated - groups 2025-01-12 12:01:39 -08:00
pablodanswer
da27c8be6d k 2025-01-11 20:28:12 -08:00
pablodanswer
9d0272fe62 minor nit 2025-01-11 19:13:45 -08:00
pablodanswer
167b5bad49 additioanl nits 2025-01-11 17:14:01 -08:00
pablodanswer
3acf235c84 quick nit 2025-01-11 17:07:53 -08:00
pablodanswer
0d9441da88 draggables 2025-01-11 17:02:59 -08:00
pablodanswer
a915e4dfa7 k 2025-01-11 11:45:50 -08:00
pablodanswer
7f2610e7d4 looking good 2025-01-11 11:24:09 -08:00
pablodanswer
19323472e6 nit 2025-01-10 19:24:33 -08:00
pablodanswer
be84cf95bf fix the hydra 2025-01-10 14:15:17 -08:00
pablodanswer
79d847f660 nit 2025-01-10 13:08:50 -08:00
pablodanswer
b06f56102e quick nit 2025-01-10 12:55:25 -08:00
pablodanswer
078ae4b9c7 add new ux 2025-01-10 12:54:00 -08:00
pablodanswer
5d034e08fc nit 2025-01-10 12:07:27 -08:00
pablodanswer
cafa0aac0d push minor changes 2025-01-10 12:07:27 -08:00
pablodanswer
f61864c36e nit 2025-01-10 12:07:27 -08:00
pablodanswer
5b0a1ccc31 minor nit 2025-01-10 12:07:27 -08:00
pablodanswer
acb9cca1e8 quick nits 2025-01-10 12:07:27 -08:00
pablodanswer
e22918e31d v3 2025-01-10 12:07:27 -08:00
pablodanswer
e5c430178d quick nits 2025-01-10 12:07:27 -08:00
pablodanswer
35f379b093 validate 2025-01-10 12:07:27 -08:00
pablodanswer
c85900e4f8 nit 2025-01-10 12:07:27 -08:00
pablodanswer
bf6b6342a1 quick addition 2025-01-10 12:07:27 -08:00
pablodanswer
9adbfc1b81 organize components 2025-01-10 12:07:27 -08:00
pablodanswer
b5dd5df36f quick nit 2025-01-10 12:07:27 -08:00
pablodanswer
6b0a2e11b5 k 2025-01-10 12:07:27 -08:00
pablodanswer
169f3fd0dc v2 2025-01-10 12:07:27 -08:00
pablodanswer
c15a828576 add chrome extension
minor clean up

additional handling

post rebase fixes

nit

quick bump

finalize

minor cleanup

organizational

Revert changes in backend directory

Revert changes in deployment directory

push misc changes

improve shortcut display + general nrf page layout

minor clean up

quick nit

update chrome

k

build fix

k

update

k
2025-01-10 12:07:26 -08:00
1503 changed files with 42650 additions and 102932 deletions

1
.github/CODEOWNERS vendored
View File

@@ -1 +0,0 @@
* @onyx-dot-app/onyx-core-team

View File

@@ -1,14 +1,11 @@
## Description
[Provide a brief description of the changes in this PR]
## How Has This Been Tested?
## How Has This Been Tested?
[Describe the tests you ran to verify your changes]
## Backporting (check the box to trigger backport action)
Note: You have to check that the action passes, otherwise resolve the conflicts manually and tag the patches.
- [ ] This PR should be backported (make sure to check that the backport attempt succeeds)
- [ ] [Optional] Override Linear Check

View File

@@ -65,11 +65,8 @@ jobs:
NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
NEXT_PUBLIC_GTM_ENABLED=true
NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true
NODE_OPTIONS=--max-old-space-size=8192
# needed due to weird interactions with the builds for different platforms
no-cache: true
labels: ${{ steps.meta.outputs.labels }}

View File

@@ -12,43 +12,7 @@ env:
BUILDKIT_PROGRESS: plain
jobs:
# Bypassing this for now as the idea of not building is glitching
# releases and builds that depends on everything being tagged in docker
# 1) Preliminary job to check if the changed files are relevant
# check_model_server_changes:
# runs-on: ubuntu-latest
# outputs:
# changed: ${{ steps.check.outputs.changed }}
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
#
# - name: Check if relevant files changed
# id: check
# run: |
# # Default to "false"
# echo "changed=false" >> $GITHUB_OUTPUT
#
# # Compare the previous commit (github.event.before) to the current one (github.sha)
# # If any file in backend/model_server/** or backend/Dockerfile.model_server is changed,
# # set changed=true
# if git diff --name-only ${{ github.event.before }} ${{ github.sha }} \
# | grep -E '^backend/model_server/|^backend/Dockerfile.model_server'; then
# echo "changed=true" >> $GITHUB_OUTPUT
# fi
check_model_server_changes:
runs-on: ubuntu-latest
outputs:
changed: "true"
steps:
- name: Bypass check and set output
run: echo "changed=true" >> $GITHUB_OUTPUT
build-amd64:
needs: [check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
runs-on:
[runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
steps:
@@ -88,8 +52,6 @@ jobs:
provenance: false
build-arm64:
needs: [check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
runs-on:
[runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
steps:
@@ -129,8 +91,7 @@ jobs:
provenance: false
merge-and-scan:
needs: [build-amd64, build-arm64, check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
needs: [build-amd64, build-arm64]
runs-on: ubuntu-latest
steps:
- name: Login to Docker Hub

View File

@@ -60,8 +60,6 @@ jobs:
push: true
build-args: |
ONYX_VERSION=${{ github.ref_name }}
NODE_OPTIONS=--max-old-space-size=8192
# needed due to weird interactions with the builds for different platforms
no-cache: true
labels: ${{ steps.meta.outputs.labels }}

View File

@@ -53,90 +53,24 @@ jobs:
exclude: '(?i)^(pylint|aio[-_]*).*'
- name: Print report
if: always()
if: ${{ always() }}
run: echo "${{ steps.license_check_report.outputs.report }}"
- name: Install npm dependencies
working-directory: ./web
run: npm ci
- name: Run Trivy vulnerability scanner in repo mode
uses: aquasecurity/trivy-action@0.28.0
with:
scan-type: fs
scanners: license
format: table
# format: sarif
# output: trivy-results.sarif
severity: HIGH,CRITICAL
# be careful enabling the sarif and upload as it may spam the security tab
# with a huge amount of items. Work out the issues before enabling upload.
# - name: Run Trivy vulnerability scanner in repo mode
# if: always()
# uses: aquasecurity/trivy-action@0.29.0
# - name: Upload Trivy scan results to GitHub Security tab
# uses: github/codeql-action/upload-sarif@v3
# with:
# scan-type: fs
# scan-ref: .
# scanners: license
# format: table
# severity: HIGH,CRITICAL
# # format: sarif
# # output: trivy-results.sarif
#
# # - name: Upload Trivy scan results to GitHub Security tab
# # uses: github/codeql-action/upload-sarif@v3
# # with:
# # sarif_file: trivy-results.sarif
scan-trivy:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
steps:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# Backend
- name: Pull backend docker image
run: docker pull onyxdotapp/onyx-backend:latest
- name: Run Trivy vulnerability scanner on backend
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-backend:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0 # Set to 1 if we want a failed scan to fail the workflow
# Web server
- name: Pull web server docker image
run: docker pull onyxdotapp/onyx-web-server:latest
- name: Run Trivy vulnerability scanner on web server
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-web-server:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0
# Model server
- name: Pull model server docker image
run: docker pull onyxdotapp/onyx-model-server:latest
- name: Run Trivy vulnerability scanner
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-model-server:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0
# sarif_file: trivy-results.sarif

View File

@@ -1,6 +1,6 @@
name: Run Playwright Tests
name: Run Chromatic Tests
concurrency:
group: Run-Playwright-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
cancel-in-progress: true
on: push
@@ -8,8 +8,6 @@ on: push
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
GEN_AI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
MOCK_LLM_RESPONSE: true
jobs:
playwright-tests:
@@ -198,47 +196,43 @@ jobs:
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p danswer-stack down -v
# NOTE: Chromatic UI diff testing is currently disabled.
# We are using Playwright for local and CI testing without visual regression checks.
# Chromatic may be reintroduced in the future for UI diff testing if needed.
chromatic-tests:
name: Chromatic Tests
# chromatic-tests:
# name: Chromatic Tests
needs: playwright-tests
runs-on:
[
runs-on,
runner=32cpu-linux-x64,
disk=large,
"run-id=${{ github.run_id }}",
]
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0
# needs: playwright-tests
# runs-on:
# [
# runs-on,
# runner=32cpu-linux-x64,
# disk=large,
# "run-id=${{ github.run_id }}",
# ]
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
# with:
# fetch-depth: 0
- name: Setup node
uses: actions/setup-node@v4
with:
node-version: 22
# - name: Setup node
# uses: actions/setup-node@v4
# with:
# node-version: 22
- name: Install node dependencies
working-directory: ./web
run: npm ci
# - name: Install node dependencies
# working-directory: ./web
# run: npm ci
- name: Download Playwright test results
uses: actions/download-artifact@v4
with:
name: test-results
path: ./web/test-results
# - name: Download Playwright test results
# uses: actions/download-artifact@v4
# with:
# name: test-results
# path: ./web/test-results
# - name: Run Chromatic
# uses: chromaui/action@latest
# with:
# playwright: true
# projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
# workingDir: ./web
# env:
# CHROMATIC_ARCHIVE_LOCATION: ./test-results
- name: Run Chromatic
uses: chromaui/action@latest
with:
playwright: true
projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
workingDir: ./web
env:
CHROMATIC_ARCHIVE_LOCATION: ./test-results

View File

@@ -21,10 +21,10 @@ jobs:
- name: Set up Helm
uses: azure/setup-helm@v4.2.0
with:
version: v3.17.0
version: v3.14.4
- name: Set up chart-testing
uses: helm/chart-testing-action@v2.7.0
uses: helm/chart-testing-action@v2.6.1
# even though we specify chart-dirs in ct.yaml, it isn't used by ct for the list-changed command...
- name: Run chart-testing (list-changed)
@@ -37,6 +37,22 @@ jobs:
echo "changed=true" >> "$GITHUB_OUTPUT"
fi
# rkuo: I don't think we need python?
# - name: Set up Python
# uses: actions/setup-python@v5
# with:
# python-version: '3.11'
# cache: 'pip'
# cache-dependency-path: |
# backend/requirements/default.txt
# backend/requirements/dev.txt
# backend/requirements/model_server.txt
# - run: |
# python -m pip install --upgrade pip
# pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
# pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
# pip install --retries 5 --timeout 30 -r backend/requirements/model_server.txt
# lint all charts if any changes were detected
- name: Run chart-testing (lint)
if: steps.list-changed.outputs.changed == 'true'
@@ -46,7 +62,7 @@ jobs:
- name: Create kind cluster
if: steps.list-changed.outputs.changed == 'true'
uses: helm/kind-action@v1.12.0
uses: helm/kind-action@v1.10.0
- name: Run chart-testing (install)
if: steps.list-changed.outputs.changed == 'true'

View File

@@ -94,27 +94,23 @@ jobs:
cd deployment/docker_compose
ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
MULTI_TENANT=true \
AUTH_TYPE=cloud \
AUTH_TYPE=basic \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
DEV_MODE=true \
docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack up -d
docker compose -f docker-compose.dev.yml -p danswer-stack up -d
id: start_docker_multi_tenant
# In practice, `cloud` Auth type would require OAUTH credentials to be set.
- name: Run Multi-Tenant Integration Tests
run: |
echo "Waiting for 3 minutes to ensure API server is ready..."
sleep 180
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
docker run --rm --network danswer-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
@@ -123,10 +119,6 @@ jobs:
-e TEST_WEB_HOSTNAME=test-runner \
-e AUTH_TYPE=cloud \
-e MULTI_TENANT=true \
-e REQUIRE_EMAIL_VERIFICATION=false \
-e DISABLE_TELEMETRY=true \
-e IMAGE_TAG=test \
-e DEV_MODE=true \
onyxdotapp/onyx-integration:test \
/app/tests/integration/multitenant_tests
continue-on-error: true
@@ -134,38 +126,34 @@ jobs:
- name: Check multi-tenant test results
run: |
if [ ${{ steps.run_multitenant_tests.outcome }} == 'failure' ]; then
echo "Multi-tenant integration tests failed. Exiting with error."
if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
echo "Integration tests failed. Exiting with error."
exit 1
else
echo "All multi-tenant integration tests passed successfully."
echo "All integration tests passed successfully."
fi
- name: Stop multi-tenant Docker containers
run: |
cd deployment/docker_compose
docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack down -v
docker compose -f docker-compose.dev.yml -p danswer-stack down -v
# NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
- name: Start Docker containers
run: |
cd deployment/docker_compose
ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
AUTH_TYPE=basic \
POSTGRES_POOL_PRE_PING=true \
POSTGRES_USE_NULL_POOL=true \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
INTEGRATION_TESTS_MODE=true \
docker compose -f docker-compose.dev.yml -p onyx-stack up -d
docker compose -f docker-compose.dev.yml -p danswer-stack up -d
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
docker logs -f onyx-stack-api_server-1 &
docker logs -f danswer-stack-api_server-1 &
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
@@ -195,24 +183,15 @@ jobs:
done
echo "Finished waiting for service."
- name: Start Mock Services
run: |
cd backend/tests/integration/mock_services
docker compose -f docker-compose.mock-it-services.yml \
-p mock-it-services-stack up -d
# NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
- name: Run Standard Integration Tests
run: |
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
docker run --rm --network danswer-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_POOL_PRE_PING=true \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
@@ -222,8 +201,6 @@ jobs:
-e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-e TEST_WEB_HOSTNAME=test-runner \
-e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
-e MOCK_CONNECTOR_SERVER_PORT=8001 \
onyxdotapp/onyx-integration:test \
/app/tests/integration/tests \
/app/tests/integration/connector_job_tests
@@ -239,30 +216,27 @@ jobs:
echo "All integration tests passed successfully."
fi
# ------------------------------------------------------------
# Always gather logs BEFORE "down":
- name: Dump API server logs
if: always()
# save before stopping the containers so the logs can be captured
- name: Save Docker logs
if: success() || failure()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-all-logs
path: ${{ github.workspace }}/docker-compose.log
# ------------------------------------------------------------
docker compose -f docker-compose.dev.yml -p danswer-stack logs > docker-compose.log
mv docker-compose.log ${{ github.workspace }}/docker-compose.log
- name: Stop Docker containers
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack down -v
docker compose -f docker-compose.dev.yml -p danswer-stack down -v
- name: Upload logs
if: success() || failure()
uses: actions/upload-artifact@v4
with:
name: docker-logs
path: ${{ github.workspace }}/docker-compose.log
- name: Stop Docker containers
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p danswer-stack down -v

View File

@@ -1,29 +0,0 @@
name: Ensure PR references Linear
on:
pull_request:
types: [opened, edited, reopened, synchronize]
jobs:
linear-check:
runs-on: ubuntu-latest
steps:
- name: Check PR body for Linear link or override
env:
PR_BODY: ${{ github.event.pull_request.body }}
run: |
# Looking for "https://linear.app" in the body
if echo "$PR_BODY" | grep -qE "https://linear\.app"; then
echo "Found a Linear link. Check passed."
exit 0
fi
# Looking for a checked override: "[x] Override Linear Check"
if echo "$PR_BODY" | grep -q "\[x\].*Override Linear Check"; then
echo "Override box is checked. Check passed."
exit 0
fi
# Otherwise, fail the run
echo "No Linear link or override found in the PR description."
exit 1

View File

@@ -1,209 +0,0 @@
name: Run MIT Integration Tests v2
concurrency:
group: Run-MIT-Integration-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
cancel-in-progress: true
on:
merge_group:
pull_request:
branches:
- main
- "release/**"
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
jobs:
integration-tests-mit:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on, runner=32cpu-linux-x64, "run-id=${{ github.run_id }}"]
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# tag every docker image with "test" so that we can spin up the correct set
# of images during testing
# We don't need to build the Web Docker image since it's not yet used
# in the integration tests. We have a separate action to verify that it builds
# successfully.
- name: Pull Web Docker image
run: |
docker pull onyxdotapp/onyx-web-server:latest
docker tag onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:test
# we use the runs-on cache for docker builds
# in conjunction with runs-on runners, it has better speed and unlimited caching
# https://runs-on.com/caching/s3-cache-for-github-actions/
# https://runs-on.com/caching/docker/
# https://github.com/moby/buildkit#s3-cache-experimental
# images are built and run locally for testing purposes. Not pushed.
- name: Build Backend Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/Dockerfile
platforms: linux/amd64
tags: onyxdotapp/onyx-backend:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
- name: Build Model Server Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/Dockerfile.model_server
platforms: linux/amd64
tags: onyxdotapp/onyx-model-server:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
- name: Build integration test Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/tests/integration/Dockerfile
platforms: linux/amd64
tags: onyxdotapp/onyx-integration:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
# NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
- name: Start Docker containers
run: |
cd deployment/docker_compose
AUTH_TYPE=basic \
POSTGRES_POOL_PRE_PING=true \
POSTGRES_USE_NULL_POOL=true \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
INTEGRATION_TESTS_MODE=true \
docker compose -f docker-compose.dev.yml -p onyx-stack up -d
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
docker logs -f onyx-stack-api_server-1 &
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
while true; do
current_time=$(date +%s)
elapsed_time=$((current_time - start_time))
if [ $elapsed_time -ge $timeout ]; then
echo "Timeout reached. Service did not become ready in 5 minutes."
exit 1
fi
# Use curl with error handling to ignore specific exit code 56
response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
if [ "$response" = "200" ]; then
echo "Service is ready!"
break
elif [ "$response" = "curl_error" ]; then
echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
else
echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
fi
sleep 5
done
echo "Finished waiting for service."
- name: Start Mock Services
run: |
cd backend/tests/integration/mock_services
docker compose -f docker-compose.mock-it-services.yml \
-p mock-it-services-stack up -d
# NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
- name: Run Standard Integration Tests
run: |
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_POOL_PRE_PING=true \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
-e OPENAI_API_KEY=${OPENAI_API_KEY} \
-e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
-e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
-e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-e TEST_WEB_HOSTNAME=test-runner \
-e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
-e MOCK_CONNECTOR_SERVER_PORT=8001 \
onyxdotapp/onyx-integration:test \
/app/tests/integration/tests \
/app/tests/integration/connector_job_tests
continue-on-error: true
id: run_tests
- name: Check test results
run: |
if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
echo "Integration tests failed. Exiting with error."
exit 1
else
echo "All integration tests passed successfully."
fi
# ------------------------------------------------------------
# Always gather logs BEFORE "down":
- name: Dump API server logs
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-all-logs
path: ${{ github.workspace }}/docker-compose.log
# ------------------------------------------------------------
- name: Stop Docker containers
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack down -v

View File

@@ -44,7 +44,7 @@ jobs:
- name: Check import order with reorder-python-imports
run: |
cd backend
find ./onyx -name "*.py" | xargs reorder-python-imports --py311-plus
find ./danswer -name "*.py" | xargs reorder-python-imports --py311-plus
- name: Check code formatting with Black
run: |

View File

@@ -1,7 +1,6 @@
name: Connector Tests
on:
merge_group:
pull_request:
branches: [main]
schedule:
@@ -9,10 +8,6 @@ on:
- cron: "0 16 * * *"
env:
# AWS
AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS }}
# Confluence
CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
CONFLUENCE_TEST_SPACE: ${{ secrets.CONFLUENCE_TEST_SPACE }}
@@ -23,10 +18,6 @@ env:
# Jira
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
GONG_ACCESS_KEY: ${{ secrets.GONG_ACCESS_KEY }}
GONG_ACCESS_KEY_SECRET: ${{ secrets.GONG_ACCESS_KEY_SECRET }}
# Google
GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1 }}
@@ -48,26 +39,10 @@ env:
AIRTABLE_TEST_TABLE_ID: ${{ secrets.AIRTABLE_TEST_TABLE_ID }}
AIRTABLE_TEST_TABLE_NAME: ${{ secrets.AIRTABLE_TEST_TABLE_NAME }}
AIRTABLE_ACCESS_TOKEN: ${{ secrets.AIRTABLE_ACCESS_TOKEN }}
# Sharepoint
SHAREPOINT_CLIENT_ID: ${{ secrets.SHAREPOINT_CLIENT_ID }}
SHAREPOINT_CLIENT_SECRET: ${{ secrets.SHAREPOINT_CLIENT_SECRET }}
SHAREPOINT_CLIENT_DIRECTORY_ID: ${{ secrets.SHAREPOINT_CLIENT_DIRECTORY_ID }}
SHAREPOINT_SITE: ${{ secrets.SHAREPOINT_SITE }}
# Github
ACCESS_TOKEN_GITHUB: ${{ secrets.ACCESS_TOKEN_GITHUB }}
# Gitbook
GITBOOK_SPACE_ID: ${{ secrets.GITBOOK_SPACE_ID }}
GITBOOK_API_KEY: ${{ secrets.GITBOOK_API_KEY }}
# Notion
NOTION_INTEGRATION_TOKEN: ${{ secrets.NOTION_INTEGRATION_TOKEN }}
# Highspot
HIGHSPOT_KEY: ${{ secrets.HIGHSPOT_KEY }}
HIGHSPOT_SECRET: ${{ secrets.HIGHSPOT_SECRET }}
jobs:
connectors-check:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
env:
PYTHONPATH: ./backend
@@ -90,8 +65,6 @@ jobs:
python -m pip install --upgrade pip
pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
playwright install chromium
playwright install-deps chromium
- name: Run Tests
shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"

View File

@@ -1,29 +1,18 @@
name: Model Server Tests
name: Connector Tests
on:
schedule:
# This cron expression runs the job daily at 16:00 UTC (9am PT)
- cron: "0 16 * * *"
workflow_dispatch:
inputs:
branch:
description: 'Branch to run the workflow on'
required: false
default: 'main'
env:
# Bedrock
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
# API keys for testing
COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
LITELLM_API_KEY: ${{ secrets.LITELLM_API_KEY }}
LITELLM_API_URL: ${{ secrets.LITELLM_API_URL }}
# OpenAI
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
AZURE_API_URL: ${{ secrets.AZURE_API_URL }}
jobs:
model-check:
@@ -37,23 +26,6 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# tag every docker image with "test" so that we can spin up the correct set
# of images during testing
# We don't need to build the Web Docker image since it's not yet used
# in the integration tests. We have a separate action to verify that it builds
# successfully.
- name: Pull Model Server Docker image
run: |
docker pull onyxdotapp/onyx-model-server:latest
docker tag onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:test
- name: Set up Python
uses: actions/setup-python@v5
with:
@@ -69,49 +41,6 @@ jobs:
pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
- name: Start Docker containers
run: |
cd deployment/docker_compose
ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
AUTH_TYPE=basic \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
docker compose -f docker-compose.model-server-test.yml -p onyx-stack up -d indexing_model_server
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
while true; do
current_time=$(date +%s)
elapsed_time=$((current_time - start_time))
if [ $elapsed_time -ge $timeout ]; then
echo "Timeout reached. Service did not become ready in 5 minutes."
exit 1
fi
# Use curl with error handling to ignore specific exit code 56
response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/api/health || echo "curl_error")
if [ "$response" = "200" ]; then
echo "Service is ready!"
break
elif [ "$response" = "curl_error" ]; then
echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
else
echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
fi
sleep 5
done
echo "Finished waiting for service."
- name: Run Tests
shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
run: |
@@ -127,23 +56,3 @@ jobs:
-H 'Content-type: application/json' \
--data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
$SLACK_WEBHOOK
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.model-server-test.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-all-logs
path: ${{ github.workspace }}/docker-compose.log
- name: Stop Docker containers
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.model-server-test.yml -p onyx-stack down -v

23
.gitignore vendored
View File

@@ -1,25 +1,12 @@
# editors
.vscode
.zed
# macos
.env
.DS_store
# python
.venv
.mypy_cache
.idea
# testing
/deployment/data/nginx/app.conf
.vscode/
*.sw?
/backend/tests/regression/answer_quality/search_test_config.yaml
/web/test-results/
backend/onyx/agent_search/main/test_data.json
backend/tests/regression/answer_quality/test_data.json
# secret files
.env
jira_test_env
# others
/deployment/data/nginx/app.conf
*.sw?
/backend/tests/regression/answer_quality/search_test_config.yaml

View File

@@ -1,13 +1,12 @@
repos:
- repo: https://github.com/psf/black
rev: 25.1.0
rev: 23.3.0
hooks:
- id: black
language_version: python3.11
# this is a fork which keeps compatibility with black
- repo: https://github.com/wimglenn/reorder-python-imports-black
rev: v3.14.0
- repo: https://github.com/asottile/reorder_python_imports
rev: v3.9.0
hooks:
- id: reorder-python-imports
args: ['--py311-plus', '--application-directories=backend/']
@@ -19,14 +18,14 @@ repos:
# These settings will remove unused imports with side effects
# Note: The repo currently does not and should not have imports with side effects
- repo: https://github.com/PyCQA/autoflake
rev: v2.3.1
rev: v2.2.0
hooks:
- id: autoflake
args: [ '--remove-all-unused-imports', '--remove-unused-variables', '--in-place' , '--recursive']
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.11.4
rev: v0.0.286
hooks:
- id: ruff
- repo: https://github.com/pre-commit/mirrors-prettier

View File

@@ -29,7 +29,6 @@ REQUIRE_EMAIL_VERIFICATION=False
# Set these so if you wipe the DB, you don't end up having to go through the UI every time
GEN_AI_API_KEY=<REPLACE THIS>
OPENAI_API_KEY=<REPLACE THIS>
# If answer quality isn't important for dev, use gpt-4o-mini since it's cheaper
GEN_AI_MODEL_VERSION=gpt-4o
FAST_GEN_AI_MODEL_VERSION=gpt-4o

View File

@@ -6,419 +6,369 @@
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"compounds": [
{
// Dummy entry used to label the group
"name": "--- Compound ---",
"configurations": ["--- Individual ---"],
"presentation": {
"group": "1"
}
},
{
"name": "Run All Onyx Services",
"configurations": [
"Web Server",
"Model Server",
"API Server",
"Slack Bot",
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery user files indexing",
"Celery beat",
"Celery monitoring"
],
"presentation": {
"group": "1"
}
},
{
"name": "Web / Model / API",
"configurations": ["Web Server", "Model Server", "API Server"],
"presentation": {
"group": "1"
}
},
{
"name": "Celery (all)",
"configurations": [
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery user files indexing",
"Celery beat",
"Celery monitoring"
],
"presentation": {
"group": "1"
}
}
{
// Dummy entry used to label the group
"name": "--- Compound ---",
"configurations": [
"--- Individual ---"
],
"presentation": {
"group": "1",
}
},
{
"name": "Run All Onyx Services",
"configurations": [
"Web Server",
"Model Server",
"API Server",
"Slack Bot",
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery beat",
],
"presentation": {
"group": "1",
}
},
{
"name": "Web / Model / API",
"configurations": [
"Web Server",
"Model Server",
"API Server",
],
"presentation": {
"group": "1",
}
},
{
"name": "Celery (all)",
"configurations": [
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery beat"
],
"presentation": {
"group": "1",
}
}
],
"configurations": [
{
// Dummy entry used to label the group
"name": "--- Individual ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "2",
"order": 0
}
},
{
"name": "Web Server",
"type": "node",
"request": "launch",
"cwd": "${workspaceRoot}/web",
"runtimeExecutable": "npm",
"envFile": "${workspaceFolder}/.vscode/.env",
"runtimeArgs": ["run", "dev"],
"presentation": {
"group": "2"
{
// Dummy entry used to label the group
"name": "--- Individual ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "2",
"order": 0
}
},
{
"name": "Web Server",
"type": "node",
"request": "launch",
"cwd": "${workspaceRoot}/web",
"runtimeExecutable": "npm",
"envFile": "${workspaceFolder}/.vscode/.env",
"runtimeArgs": [
"run", "dev"
],
"presentation": {
"group": "2",
},
"console": "integratedTerminal",
"consoleTitle": "Web Server Console"
},
"console": "integratedTerminal",
"consoleTitle": "Web Server Console"
},
{
"name": "Model Server",
"consoleName": "Model Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
{
"name": "Model Server",
"consoleName": "Model Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
},
"args": [
"model_server.main:app",
"--reload",
"--port",
"9000"
],
"presentation": {
"group": "2",
},
"consoleTitle": "Model Server Console"
},
"args": ["model_server.main:app", "--reload", "--port", "9000"],
"presentation": {
"group": "2"
{
"name": "API Server",
"consoleName": "API Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
},
"args": [
"onyx.main:app",
"--reload",
"--port",
"8080"
],
"presentation": {
"group": "2",
},
"consoleTitle": "API Server Console"
},
"consoleTitle": "Model Server Console"
},
{
"name": "API Server",
"consoleName": "API Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
// For the listener to access the Slack API,
// DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
{
"name": "Slack Bot",
"consoleName": "Slack Bot",
"type": "debugpy",
"request": "launch",
"program": "onyx/onyxbot/slack/listener.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"presentation": {
"group": "2",
},
"consoleTitle": "Slack Bot Console"
},
"args": ["onyx.main:app", "--reload", "--port", "8080"],
"presentation": {
"group": "2"
{
"name": "Celery primary",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.primary",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=primary@%n",
"-Q",
"celery",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery primary Console"
},
"consoleTitle": "API Server Console"
},
// For the listener to access the Slack API,
// DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
{
"name": "Slack Bot",
"consoleName": "Slack Bot",
"type": "debugpy",
"request": "launch",
"program": "onyx/onyxbot/slack/listener.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Celery light",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.light",
"worker",
"--pool=threads",
"--concurrency=64",
"--prefetch-multiplier=8",
"--loglevel=INFO",
"--hostname=light@%n",
"-Q",
"vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery light Console"
},
"presentation": {
"group": "2"
{
"name": "Celery heavy",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.heavy",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=heavy@%n",
"-Q",
"connector_pruning,connector_doc_permissions_sync,connector_external_group_sync",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery heavy Console"
},
"consoleTitle": "Slack Bot Console"
},
{
"name": "Celery primary",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Celery indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"ENABLE_MULTIPASS_INDEXING": "false",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=indexing@%n",
"-Q",
"connector_indexing",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery indexing Console"
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.primary",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=primary@%n",
"-Q",
"celery"
],
"presentation": {
"group": "2"
{
"name": "Celery beat",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.beat",
"beat",
"--loglevel=INFO",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery beat Console"
},
"consoleTitle": "Celery primary Console"
},
{
"name": "Celery light",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Pytest",
"consoleName": "Pytest",
"type": "debugpy",
"request": "launch",
"module": "pytest",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-v"
// Specify a sepcific module/test to run or provide nothing to run all tests
//"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
],
"presentation": {
"group": "2",
},
"consoleTitle": "Pytest Console"
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.light",
"worker",
"--pool=threads",
"--concurrency=64",
"--prefetch-multiplier=8",
"--loglevel=INFO",
"--hostname=light@%n",
"-Q",
"vespa_metadata_sync,connector_deletion,doc_permissions_upsert"
],
"presentation": {
"group": "2"
{
// Dummy entry used to label the group
"name": "--- Tasks ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "3",
"order": 0
}
},
{
"name": "Clear and Restart External Volumes and Containers",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": ["${workspaceFolder}/backend/scripts/restart_containers.sh"],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"stopOnEntry": true,
"presentation": {
"group": "3",
},
},
"consoleTitle": "Celery light Console"
},
{
"name": "Celery heavy",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
// Celery jobs launched through a single background script (legacy)
// Recommend using the "Celery (all)" compound launch instead.
"name": "Background Jobs",
"consoleName": "Background Jobs",
"type": "debugpy",
"request": "launch",
"program": "scripts/dev_run_background_jobs.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.heavy",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=heavy@%n",
"-Q",
"connector_pruning,connector_doc_permissions_sync,connector_external_group_sync"
],
"presentation": {
"group": "2"
{
"name": "Install Python Requirements",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"-c",
"pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"presentation": {
"group": "3"
}
},
"consoleTitle": "Celery heavy Console"
},
{
"name": "Celery indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"ENABLE_MULTIPASS_INDEXING": "false",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=indexing@%n",
"-Q",
"connector_indexing"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery indexing Console"
},
{
"name": "Celery monitoring",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {},
"args": [
"-A",
"onyx.background.celery.versioned_apps.monitoring",
"worker",
"--pool=solo",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=monitoring@%n",
"-Q",
"monitoring"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery monitoring Console"
},
{
"name": "Celery beat",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.beat",
"beat",
"--loglevel=INFO"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery beat Console"
},
{
"name": "Celery user files indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=user_files_indexing@%n",
"-Q",
"user_files_indexing"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery user files indexing Console"
},
{
"name": "Pytest",
"consoleName": "Pytest",
"type": "debugpy",
"request": "launch",
"module": "pytest",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-v"
// Specify a sepcific module/test to run or provide nothing to run all tests
//"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Pytest Console"
},
{
// Dummy entry used to label the group
"name": "--- Tasks ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "3",
"order": 0
}
},
{
"name": "Clear and Restart External Volumes and Containers",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"${workspaceFolder}/backend/scripts/restart_containers.sh"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"stopOnEntry": true,
"presentation": {
"group": "3"
}
},
{
// Celery jobs launched through a single background script (legacy)
// Recommend using the "Celery (all)" compound launch instead.
"name": "Background Jobs",
"consoleName": "Background Jobs",
"type": "debugpy",
"request": "launch",
"program": "scripts/dev_run_background_jobs.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
}
},
{
"name": "Install Python Requirements",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"-c",
"pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"presentation": {
"group": "3"
}
},
{
"name": "Debug React Web App in Chrome",
"type": "chrome",
"request": "launch",
"url": "http://localhost:3000",
"webRoot": "${workspaceFolder}/web"
}
]
}
}

View File

@@ -17,10 +17,9 @@ Before starting, make sure the Docker Daemon is running.
1. Open the Debug view in VSCode (Cmd+Shift+D on macOS)
2. From the dropdown at the top, select "Clear and Restart External Volumes and Containers" and press the green play button
3. From the dropdown at the top, select "Run All Onyx Services" and press the green play button
4. CD into web, run "npm i" followed by npm run dev.
5. Now, you can navigate to onyx in your browser (default is http://localhost:3000) and start using the app
6. You can set breakpoints by clicking to the left of line numbers to help debug while the app is running
7. Use the debug toolbar to step through code, inspect variables, etc.
4. Now, you can navigate to onyx in your browser (default is http://localhost:3000) and start using the app
5. You can set breakpoints by clicking to the left of line numbers to help debug while the app is running
6. Use the debug toolbar to step through code, inspect variables, etc.
## Features

122
README.md
View File

@@ -24,94 +24,112 @@
</a>
</p>
<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI platform connected to your company's docs, apps, and people.
Onyx provides a feature rich Chat interface and plugs into any LLM of your choice.
Keep knowledge and access controls sync-ed across over 40 connectors like Google Drive, Slack, Confluence, Salesforce, etc.
Create custom AI agents with unique prompts, knowledge, and actions that the agents can take.
Onyx can be deployed securely anywhere and for any scale - on a laptop, on-premise, or to cloud.
<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI Assistant connected to your company's docs, apps, and people.
Onyx provides a Chat interface and plugs into any LLM of your choice. Onyx can be deployed anywhere and for any
scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your
own control. Onyx is dual Licensed with most of it under MIT license and designed to be modular and easily extensible. The system also comes fully ready
for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for
configuring AI Assistants.
Onyx also serves as a Enterprise Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
By combining LLMs and team specific knowledge, Onyx becomes a subject matter expert for the team. Imagine ChatGPT if
it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
supported?" or "Where's the pull request for feature Y?"
<h3>Feature Highlights</h3>
<h3>Usage</h3>
**Deep research over your team's knowledge:**
Onyx Web App:
https://private-user-images.githubusercontent.com/32520769/414509312-48392e83-95d0-4fb5-8650-a396e05e0a32.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.a9D8A0sgKE9AoaoE-mfFbJ6_OKYeqaf7TZ4Han2JfW8
https://github.com/onyx-dot-app/onyx/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
Or, plug Onyx into your existing Slack workflows (more integrations to come 😁):
**Use Onyx as a secure AI Chat with any LLM:**
![Onyx Chat Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxChatSilentDemo.gif)
**Easily set up connectors to your apps:**
![Onyx Connector Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxConnectorSilentDemo.gif)
**Access Onyx where your team already works:**
![Onyx Bot Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxBot.png)
https://github.com/onyx-dot-app/onyx/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
For more details on the Admin UI to manage connectors and users, check out our
<strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
## Deployment
**To try it out for free and get started in seconds, check out [Onyx Cloud](https://cloud.onyx.app/signup)**.
Onyx can also be run locally (even on a laptop) or deployed on a virtual machine with a single
Onyx can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
`docker compose` command. Checkout our [docs](https://docs.onyx.app/quickstart) to learn more.
We also have built-in support for high-availability/scalable deployment on Kubernetes.
References [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment).
We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment/kubernetes).
## 💃 Main Features
## 🔍 Other Notable Benefits of Onyx
- Custom deep learning models for indexing and inference time, only through Onyx + learning from user feedback.
- Flexible security features like SSO (OIDC/SAML/OAuth2), RBAC, encryption of credentials, etc.
- Knowledge curation features like document-sets, query history, usage analytics, etc.
- Scalable deployment options tested up to many tens of thousands users and hundreds of millions of documents.
- Chat UI with the ability to select documents to chat with.
- Create custom AI Assistants with different prompts and backing knowledge sets.
- Connect Onyx with LLM of your choice (self-host for a fully airgapped solution).
- Document Search + AI Answers for natural language queries.
- Connectors to all common workplace tools like Google Drive, Confluence, Slack, etc.
- Slack integration to get answers and search results directly in Slack.
## 🚧 Roadmap
- New methods in information retrieval (StructRAG, LightGraphRAG, etc.)
- Personalized Search
- Organizational understanding and ability to locate and suggest experts from your team.
- Code Search
- SQL and Structured Query Language
- Chat/Prompt sharing with specific teammates and user groups.
- Multimodal model support, chat with images, video etc.
- Choosing between LLMs and parameters during chat session.
- Tool calling and agent configurations options.
- Organizational understanding and ability to locate and suggest experts from your team.
## Other Notable Benefits of Onyx
- User Authentication with document level access management.
- Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
- Admin Dashboard to configure connectors, document-sets, access, etc.
- Custom deep learning models + learn from user feedback.
- Easy deployment and ability to host Onyx anywhere of your choosing.
## 🔌 Connectors
Keep knowledge and access up to sync across 40+ connectors:
Efficiently pulls the latest changes from:
- Slack
- GitHub
- Google Drive
- Confluence
- Slack
- Gmail
- Salesforce
- Microsoft Sharepoint
- Github
- Jira
- Zendesk
- Gmail
- Notion
- Gong
- Microsoft Teams
- Dropbox
- Slab
- Linear
- Productboard
- Guru
- Bookstack
- Document360
- Sharepoint
- Hubspot
- Local Files
- Websites
- And more ...
See the full list [here](https://docs.onyx.app/connectors).
## 📚 Editions
## 📚 Licensing
There are two editions of Onyx:
- Onyx Community Edition (CE) is available freely under the MIT Expat license. Simply follow the Deployment guide above.
- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations.
For feature details, check out [our website](https://www.onyx.app/pricing).
- Onyx Community Edition (CE) is available freely under the MIT Expat license. This version has ALL the core features discussed above. This is the version of Onyx you will get if you follow the Deployment guide above.
- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations. Specifically, this includes:
- Single Sign-On (SSO), with support for both SAML and OIDC
- Role-based access control
- Document permission inheritance from connected sources
- Usage analytics and query history accessible to admins
- Whitelabeling
- API key authentication
- Encryption of secrets
- Any many more! Checkout [our website](https://www.onyx.app/) for the latest.
To try the Onyx Enterprise Edition:
1. Checkout [Onyx Cloud](https://cloud.onyx.app/signup).
2. For self-hosting the Enterprise Edition, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/onyx/founders).
1. Checkout our [Cloud product](https://cloud.onyx.app/signup).
2. For self-hosting, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/danswer/founders).
## 💡 Contributing
Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.
## ⭐Star History
[![Star History Chart](https://api.star-history.com/svg?repos=onyx-dot-app/onyx&type=Date)](https://star-history.com/#onyx-dot-app/onyx&Date)

View File

@@ -8,11 +8,9 @@ Edition features outside of personal development or testing purposes. Please rea
founders@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
ARG ONYX_VERSION=0.0.0-dev
# DO_NOT_TRACK is used to disable telemetry for Unstructured
ARG ONYX_VERSION=0.8-dev
ENV ONYX_VERSION=${ONYX_VERSION} \
DANSWER_RUNNING_IN_DOCKER="true" \
DO_NOT_TRACK="true"
DANSWER_RUNNING_IN_DOCKER="true"
RUN echo "ONYX_VERSION: ${ONYX_VERSION}"
@@ -28,16 +26,14 @@ RUN apt-get update && \
curl \
zip \
ca-certificates \
libgnutls30 \
libblkid1 \
libmount1 \
libsmartcols1 \
libuuid1 \
libgnutls30=3.7.9-2+deb12u3 \
libblkid1=2.38.1-5+deb12u1 \
libmount1=2.38.1-5+deb12u1 \
libsmartcols1=2.38.1-5+deb12u1 \
libuuid1=2.38.1-5+deb12u1 \
libxmlsec1-dev \
pkg-config \
gcc \
nano \
vim && \
gcc && \
rm -rf /var/lib/apt/lists/* && \
apt-get clean
@@ -102,10 +98,8 @@ COPY ./alembic /app/alembic
COPY ./alembic_tenants /app/alembic_tenants
COPY ./alembic.ini /app/alembic.ini
COPY supervisord.conf /usr/etc/supervisord.conf
COPY ./static /app/static
# Escape hatch scripts
COPY ./scripts/debugging /app/scripts/debugging
# Escape hatch
COPY ./scripts/force_delete_connector_by_id.py /app/scripts/force_delete_connector_by_id.py
# Put logo in assets

View File

@@ -7,7 +7,7 @@ You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more det
visit https://github.com/onyx-dot-app/onyx."
# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
ARG ONYX_VERSION=0.0.0-dev
ARG ONYX_VERSION=0.8-dev
ENV ONYX_VERSION=${ONYX_VERSION} \
DANSWER_RUNNING_IN_DOCKER="true"
@@ -31,8 +31,7 @@ RUN python -c "from transformers import AutoTokenizer; \
AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
from huggingface_hub import snapshot_download; \
snapshot_download(repo_id='onyx-dot-app/hybrid-intent-token-classifier'); \
snapshot_download(repo_id='onyx-dot-app/information-content-model'); \
snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
snapshot_download('nomic-ai/nomic-embed-text-v1'); \
snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
from sentence_transformers import SentenceTransformer; \
@@ -46,7 +45,6 @@ WORKDIR /app
# Utils used by model server
COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
COPY ./onyx/utils/middleware.py /app/onyx/utils/middleware.py
# Place to fetch version information
COPY ./onyx/__init__.py /app/onyx/__init__.py

View File

@@ -84,7 +84,7 @@ keys = console
keys = generic
[logger_root]
level = INFO
level = WARN
handlers = console
qualname =

View File

@@ -25,9 +25,6 @@ from shared_configs.configs import MULTI_TENANT, POSTGRES_DEFAULT_SCHEMA
from onyx.db.models import Base
from celery.backends.database.session import ResultModelBase # type: ignore
# Make sure in alembic.ini [logger_root] level=INFO is set or most logging will be
# hidden! (defaults to level=WARN)
# Alembic Config object
config = context.config
@@ -39,7 +36,6 @@ if config.config_file_name is not None and config.attributes.get(
target_metadata = [Base.metadata, ResultModelBase.metadata]
EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
logger = logging.getLogger(__name__)
ssl_context: ssl.SSLContext | None = None
@@ -68,7 +64,7 @@ def include_object(
return True
def get_schema_options() -> tuple[str, bool, bool, bool]:
def get_schema_options() -> tuple[str, bool, bool]:
x_args_raw = context.get_x_argument()
x_args = {}
for arg in x_args_raw:
@@ -80,10 +76,6 @@ def get_schema_options() -> tuple[str, bool, bool, bool]:
create_schema = x_args.get("create_schema", "true").lower() == "true"
upgrade_all_tenants = x_args.get("upgrade_all_tenants", "false").lower() == "true"
# continue on error with individual tenant
# only applies to online migrations
continue_on_error = x_args.get("continue", "false").lower() == "true"
if (
MULTI_TENANT
and schema_name == POSTGRES_DEFAULT_SCHEMA
@@ -94,12 +86,14 @@ def get_schema_options() -> tuple[str, bool, bool, bool]:
"Please specify a tenant-specific schema."
)
return schema_name, create_schema, upgrade_all_tenants, continue_on_error
return schema_name, create_schema, upgrade_all_tenants
def do_run_migrations(
connection: Connection, schema_name: str, create_schema: bool
) -> None:
logger.info(f"About to migrate schema: {schema_name}")
if create_schema:
connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
connection.execute(text("COMMIT"))
@@ -140,12 +134,7 @@ def provide_iam_token_for_alembic(
async def run_async_migrations() -> None:
(
schema_name,
create_schema,
upgrade_all_tenants,
continue_on_error,
) = get_schema_options()
schema_name, create_schema, upgrade_all_tenants = get_schema_options()
engine = create_async_engine(
build_connection_string(),
@@ -162,15 +151,9 @@ async def run_async_migrations() -> None:
if upgrade_all_tenants:
tenant_schemas = get_all_tenant_ids()
i_tenant = 0
num_tenants = len(tenant_schemas)
for schema in tenant_schemas:
i_tenant += 1
logger.info(
f"Migrating schema: index={i_tenant} num_tenants={num_tenants} schema={schema}"
)
try:
logger.info(f"Migrating schema: {schema}")
async with engine.connect() as connection:
await connection.run_sync(
do_run_migrations,
@@ -179,12 +162,7 @@ async def run_async_migrations() -> None:
)
except Exception as e:
logger.error(f"Error migrating schema {schema}: {e}")
if not continue_on_error:
logger.error("--continue is not set, raising exception!")
raise
logger.warning("--continue is set, continuing to next schema.")
raise
else:
try:
logger.info(f"Migrating schema: {schema_name}")
@@ -202,11 +180,7 @@ async def run_async_migrations() -> None:
def run_migrations_offline() -> None:
"""This doesn't really get used when we migrate in the cloud."""
logger.info("run_migrations_offline starting.")
schema_name, _, upgrade_all_tenants, continue_on_error = get_schema_options()
schema_name, _, upgrade_all_tenants = get_schema_options()
url = build_connection_string()
if upgrade_all_tenants:
@@ -256,7 +230,6 @@ def run_migrations_offline() -> None:
def run_migrations_online() -> None:
logger.info("run_migrations_online starting.")
asyncio.run(run_async_migrations())

View File

@@ -5,7 +5,6 @@ Revises: 6fc7886d665d
Create Date: 2025-01-14 12:14:00.814390
"""
from alembic import op
import sqlalchemy as sa
@@ -21,7 +20,7 @@ def upgrade() -> None:
op.add_column(
"user",
sa.Column(
"shortcut_enabled", sa.Boolean(), nullable=False, server_default="false"
"shortcut_enabled", sa.Boolean(), nullable=False, server_default="true"
),
)

View File

@@ -5,7 +5,6 @@ Revises: 8a87bd6ec550
Create Date: 2024-07-23 11:12:39.462397
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5f4b8568a221
Create Date: 2024-03-02 23:23:49.960309
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 570282d33c49
Create Date: 2024-05-05 19:30:34.317972
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.sql import table

View File

@@ -5,7 +5,6 @@ Revises: 52a219fb5233
Create Date: 2024-09-10 15:03:48.233926
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,37 +0,0 @@
"""add index to index_attempt.time_created
Revision ID: 0f7ff6d75b57
Revises: 369644546676
Create Date: 2025-01-10 14:01:14.067144
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "0f7ff6d75b57"
down_revision = "fec3db967bf7"
branch_labels: None = None
depends_on: None = None
def upgrade() -> None:
op.create_index(
op.f("ix_index_attempt_status"),
"index_attempt",
["status"],
unique=False,
)
op.create_index(
op.f("ix_index_attempt_time_created"),
"index_attempt",
["time_created"],
unique=False,
)
def downgrade() -> None:
op.drop_index(op.f("ix_index_attempt_time_created"), table_name="index_attempt")
op.drop_index(op.f("ix_index_attempt_status"), table_name="index_attempt")

View File

@@ -5,7 +5,6 @@ Revises: 77d07dffae64
Create Date: 2023-11-11 20:51:24.228999
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e50154680a5c
Create Date: 2024-03-19 15:30:44.425436
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 4ee1287bd26a
Create Date: 2024-11-21 11:49:04.488677
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -1,28 +0,0 @@
"""Add indexes to document__tag
Revision ID: 1a03d2c2856b
Revises: 9c00a2bccb83
Create Date: 2025-02-18 10:45:13.957807
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "1a03d2c2856b"
down_revision = "9c00a2bccb83"
branch_labels: None = None
depends_on: None = None
def upgrade() -> None:
op.create_index(
op.f("ix_document__tag_tag_id"),
"document__tag",
["tag_id"],
unique=False,
)
def downgrade() -> None:
op.drop_index(op.f("ix_document__tag_tag_id"), table_name="document__tag")

View File

@@ -0,0 +1,29 @@
"""agent_doc_result_col
Revision ID: 1adf5ea20d2b
Revises: e9cf2bd7baed
Create Date: 2025-01-05 13:14:58.344316
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql
# revision identifiers, used by Alembic.
revision = "1adf5ea20d2b"
down_revision = "e9cf2bd7baed"
branch_labels = None
depends_on = None
def upgrade() -> None:
# Add the new column with JSONB type
op.add_column(
"sub_question",
sa.Column("sub_question_doc_results", postgresql.JSONB(), nullable=True),
)
def downgrade() -> None:
# Drop the column
op.drop_column("sub_question", "sub_question_doc_results")

View File

@@ -5,7 +5,6 @@ Revises: 6756efa39ada
Create Date: 2024-10-15 19:26:44.071259
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 35e6853a51d5
Create Date: 2024-09-18 11:48:59.418726
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 5fc1f54cc252
Create Date: 2024-08-10 11:13:36.070790
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: bc9771dccadf
Create Date: 2024-06-27 16:04:51.480437
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 6d387b3196c2
Create Date: 2023-05-05 15:49:35.716016
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 2daa494a0851
Create Date: 2024-11-12 13:23:29.858995
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 2666d766cb9b
Create Date: 2023-05-24 18:45:17.244495
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: c0aab6edb6dd
Create Date: 2025-01-04 11:39:43.268612
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,33 +0,0 @@
"""set built in to default
Revision ID: 2cdeff6d8c93
Revises: f5437cc136c5
Create Date: 2025-02-11 14:57:51.308775
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "2cdeff6d8c93"
down_revision = "f5437cc136c5"
branch_labels = None
depends_on = None
def upgrade() -> None:
# Prior to this migration / point in the codebase history,
# built in personas were implicitly treated as default personas (with no option to change this)
# This migration makes that explicit
op.execute(
"""
UPDATE persona
SET is_default_persona = TRUE
WHERE builtin_persona = TRUE
"""
)
def downgrade() -> None:
pass

View File

@@ -5,7 +5,6 @@ Revises: 4b08d97e175a
Create Date: 2024-08-21 19:15:15.762948
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: c0fd6e4da83a
Create Date: 2024-11-11 10:57:22.991157
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,37 +0,0 @@
"""add chat session specific temperature override
Revision ID: 2f80c6a2550f
Revises: 33ea50e88f24
Create Date: 2025-01-31 10:30:27.289646
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = "2f80c6a2550f"
down_revision = "33ea50e88f24"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.add_column(
"chat_session", sa.Column("temperature_override", sa.Float(), nullable=True)
)
op.add_column(
"user",
sa.Column(
"temperature_override_enabled",
sa.Boolean(),
nullable=False,
server_default=sa.false(),
),
)
def downgrade() -> None:
op.drop_column("chat_session", "temperature_override")
op.drop_column("user", "temperature_override_enabled")

View File

@@ -5,7 +5,6 @@ Revises: 7f99be1cb9f5
Create Date: 2023-10-16 23:21:01.283424
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 91ffac7e65b3
Create Date: 2024-07-24 21:29:31.784562
"""
import random
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5b29123cd710
Create Date: 2024-11-01 12:51:01.535003
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,81 +0,0 @@
"""foreign key input prompts
Revision ID: 33ea50e88f24
Revises: a6df6b88ef81
Create Date: 2025-01-29 10:54:22.141765
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "33ea50e88f24"
down_revision = "a6df6b88ef81"
branch_labels = None
depends_on = None
def upgrade() -> None:
# Safely drop constraints if exists
op.execute(
"""
ALTER TABLE inputprompt__user
DROP CONSTRAINT IF EXISTS inputprompt__user_input_prompt_id_fkey
"""
)
op.execute(
"""
ALTER TABLE inputprompt__user
DROP CONSTRAINT IF EXISTS inputprompt__user_user_id_fkey
"""
)
# Recreate with ON DELETE CASCADE
op.create_foreign_key(
"inputprompt__user_input_prompt_id_fkey",
"inputprompt__user",
"inputprompt",
["input_prompt_id"],
["id"],
ondelete="CASCADE",
)
op.create_foreign_key(
"inputprompt__user_user_id_fkey",
"inputprompt__user",
"user",
["user_id"],
["id"],
ondelete="CASCADE",
)
def downgrade() -> None:
# Drop the new FKs with ondelete
op.drop_constraint(
"inputprompt__user_input_prompt_id_fkey",
"inputprompt__user",
type_="foreignkey",
)
op.drop_constraint(
"inputprompt__user_user_id_fkey",
"inputprompt__user",
type_="foreignkey",
)
# Recreate them without cascading
op.create_foreign_key(
"inputprompt__user_input_prompt_id_fkey",
"inputprompt__user",
"inputprompt",
["input_prompt_id"],
["id"],
)
op.create_foreign_key(
"inputprompt__user_user_id_fkey",
"inputprompt__user",
"user",
["user_id"],
["id"],
)

View File

@@ -5,7 +5,6 @@ Revises: ee3f4b47fad5
Create Date: 2024-08-15 22:37:08.397052
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 91a0a4d62b14
Create Date: 2024-09-20 21:24:04.891018
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: c99d76fcd298
Create Date: 2024-09-13 13:20:32.885317
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 2955778aa44c
Create Date: 2025-01-08 15:38:17.224380
"""
from alembic import op
from sqlalchemy import text

View File

@@ -1,52 +0,0 @@
"""add chunk stats table
Revision ID: 3781a5eb12cb
Revises: df46c75b714e
Create Date: 2025-03-10 10:02:30.586666
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = "3781a5eb12cb"
down_revision = "df46c75b714e"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.create_table(
"chunk_stats",
sa.Column("id", sa.String(), primary_key=True, index=True),
sa.Column(
"document_id",
sa.String(),
sa.ForeignKey("document.id"),
nullable=False,
index=True,
),
sa.Column("chunk_in_doc_id", sa.Integer(), nullable=False),
sa.Column("information_content_boost", sa.Float(), nullable=True),
sa.Column(
"last_modified",
sa.DateTime(timezone=True),
nullable=False,
index=True,
server_default=sa.func.now(),
),
sa.Column("last_synced", sa.DateTime(timezone=True), nullable=True, index=True),
sa.UniqueConstraint(
"document_id", "chunk_in_doc_id", name="uq_chunk_stats_doc_chunk"
),
)
op.create_index(
"ix_chunk_sync_status", "chunk_stats", ["last_modified", "last_synced"]
)
def downgrade() -> None:
op.drop_index("ix_chunk_sync_status", table_name="chunk_stats")
op.drop_table("chunk_stats")

View File

@@ -5,7 +5,6 @@ Revises: f1c6478c3fd8
Create Date: 2024-05-11 16:11:23.718084
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 776b3bbe9092
Create Date: 2024-03-27 19:41:29.073594
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,126 +0,0 @@
"""Update GitHub connector repo_name to repositories
Revision ID: 3934b1bc7b62
Revises: b7c2b63c4a03
Create Date: 2025-03-05 10:50:30.516962
"""
from alembic import op
import sqlalchemy as sa
import json
import logging
# revision identifiers, used by Alembic.
revision = "3934b1bc7b62"
down_revision = "b7c2b63c4a03"
branch_labels = None
depends_on = None
logger = logging.getLogger("alembic.runtime.migration")
def upgrade() -> None:
# Get all GitHub connectors
conn = op.get_bind()
# First get all GitHub connectors
github_connectors = conn.execute(
sa.text(
"""
SELECT id, connector_specific_config
FROM connector
WHERE source = 'GITHUB'
"""
)
).fetchall()
# Update each connector's config
updated_count = 0
for connector_id, config in github_connectors:
try:
if not config:
logger.warning(f"Connector {connector_id} has no config, skipping")
continue
# Parse the config if it's a string
if isinstance(config, str):
config = json.loads(config)
if "repo_name" not in config:
continue
# Create new config with repositories instead of repo_name
new_config = dict(config)
repo_name_value = new_config.pop("repo_name")
new_config["repositories"] = repo_name_value
# Update the connector with the new config
conn.execute(
sa.text(
"""
UPDATE connector
SET connector_specific_config = :new_config
WHERE id = :connector_id
"""
),
{"connector_id": connector_id, "new_config": json.dumps(new_config)},
)
updated_count += 1
except Exception as e:
logger.error(f"Error updating connector {connector_id}: {str(e)}")
def downgrade() -> None:
# Get all GitHub connectors
conn = op.get_bind()
logger.debug(
"Starting rollback of GitHub connectors from repositories to repo_name"
)
github_connectors = conn.execute(
sa.text(
"""
SELECT id, connector_specific_config
FROM connector
WHERE source = 'GITHUB'
"""
)
).fetchall()
logger.debug(f"Found {len(github_connectors)} GitHub connectors to rollback")
# Revert each GitHub connector to use repo_name instead of repositories
reverted_count = 0
for connector_id, config in github_connectors:
try:
if not config:
continue
# Parse the config if it's a string
if isinstance(config, str):
config = json.loads(config)
if "repositories" not in config:
continue
# Create new config with repo_name instead of repositories
new_config = dict(config)
repositories_value = new_config.pop("repositories")
new_config["repo_name"] = repositories_value
# Update the connector with the new config
conn.execute(
sa.text(
"""
UPDATE connector
SET connector_specific_config = :new_config
WHERE id = :connector_id
"""
),
{"new_config": json.dumps(new_config), "connector_id": connector_id},
)
reverted_count += 1
except Exception as e:
logger.error(f"Error reverting connector {connector_id}: {str(e)}")

View File

@@ -5,7 +5,6 @@ Revises: e0a68a81d434
Create Date: 2023-10-05 18:47:09.582849
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,99 +0,0 @@
"""improved index
Revision ID: 3bd4c84fe72f
Revises: 8f43500ee275
Create Date: 2025-02-26 13:07:56.217791
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "3bd4c84fe72f"
down_revision = "8f43500ee275"
branch_labels = None
depends_on = None
# NOTE:
# This migration addresses issues with the previous migration (8f43500ee275) which caused
# an outage by creating an index without using CONCURRENTLY. This migration:
#
# 1. Creates more efficient full-text search capabilities using tsvector columns and GIN indexes
# 2. Uses CONCURRENTLY for all index creation to prevent table locking
# 3. Explicitly manages transactions with COMMIT statements to allow CONCURRENTLY to work
# (see: https://www.postgresql.org/docs/9.4/sql-createindex.html#SQL-CREATEINDEX-CONCURRENTLY)
# (see: https://github.com/sqlalchemy/alembic/issues/277)
# 4. Adds indexes to both chat_message and chat_session tables for comprehensive search
def upgrade() -> None:
# First, drop any existing indexes to avoid conflicts
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")
# Drop existing columns if they exist
op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
# Create a GIN index for full-text search on chat_message.message
op.execute(
"""
ALTER TABLE chat_message
ADD COLUMN message_tsv tsvector
GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
"""
)
# Commit the current transaction before creating concurrent indexes
op.execute("COMMIT")
op.execute(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
ON chat_message
USING GIN (message_tsv)
"""
)
# Also add a stored tsvector column for chat_session.description
op.execute(
"""
ALTER TABLE chat_session
ADD COLUMN description_tsv tsvector
GENERATED ALWAYS AS (to_tsvector('english', coalesce(description, ''))) STORED;
"""
)
# Commit again before creating the second concurrent index
op.execute("COMMIT")
op.execute(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
ON chat_session
USING GIN (description_tsv)
"""
)
def downgrade() -> None:
# Drop the indexes first (use CONCURRENTLY for dropping too)
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
# Then drop the columns
op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")

View File

@@ -5,7 +5,6 @@ Revises: 27c6ecc08586
Create Date: 2023-06-14 23:45:51.760440
"""
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: aeda5f2df4f6
Create Date: 2025-01-13 12:49:51.705235
"""
from alembic import op
import sqlalchemy as sa
import fastapi_users_db_sqlalchemy
@@ -42,7 +41,6 @@ def upgrade() -> None:
sa.Column(
"user_id", fastapi_users_db_sqlalchemy.generics.GUID(), nullable=False
),
sa.Column("disabled", sa.Boolean(), nullable=False, default=False),
sa.ForeignKeyConstraint(
["input_prompt_id"],
["inputprompt.id"],

View File

@@ -5,7 +5,6 @@ Revises: 703313b75876
Create Date: 2024-04-13 18:07:29.153817
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: e1392f05e840
Create Date: 2024-08-01 12:38:54.466081
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,7 +5,6 @@ Revises: d716b0791ddd
Create Date: 2024-06-28 20:01:05.927647
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: c18cdf4b497e
Create Date: 2024-06-18 20:46:09.095034
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 3c5e35aa9af0
Create Date: 2023-07-18 17:33:40.365034
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 9d97fecfab7f
Create Date: 2023-10-27 11:38:33.803145
"""
from alembic import op
from sqlalchemy import String

View File

@@ -5,7 +5,6 @@ Revises: f32615f71aeb
Create Date: 2024-09-23 12:58:03.894038
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,7 +5,6 @@ Revises: e91df4e935ef
Create Date: 2024-03-20 18:53:32.461518
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises:
Create Date: 2023-05-04 00:55:32.971991
"""
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: ecab2b3f1a3b
Create Date: 2024-04-11 11:05:18.414438
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,51 +0,0 @@
"""update prompt length
Revision ID: 4794bc13e484
Revises: f7505c5b0284
Create Date: 2025-04-02 11:26:36.180328
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = "4794bc13e484"
down_revision = "f7505c5b0284"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.alter_column(
"prompt",
"system_prompt",
existing_type=sa.TEXT(),
type_=sa.String(length=5000000),
existing_nullable=False,
)
op.alter_column(
"prompt",
"task_prompt",
existing_type=sa.TEXT(),
type_=sa.String(length=5000000),
existing_nullable=False,
)
def downgrade() -> None:
op.alter_column(
"prompt",
"system_prompt",
existing_type=sa.String(length=5000000),
type_=sa.TEXT(),
existing_nullable=False,
)
op.alter_column(
"prompt",
"task_prompt",
existing_type=sa.String(length=5000000),
type_=sa.TEXT(),
existing_nullable=False,
)

View File

@@ -5,7 +5,6 @@ Revises: dfbe9e93d3c7
Create Date: 2024-11-05 18:55:02.221064
"""
from alembic import op
import sqlalchemy as sa
@@ -41,6 +40,6 @@ def upgrade() -> None:
def downgrade() -> None:
op.drop_constraint("persona_category_id_fkey", "persona", type_="foreignkey")
op.drop_constraint("fk_persona_category", "persona", type_="foreignkey")
op.drop_column("persona", "category_id")
op.drop_table("persona_category")

View File

@@ -5,7 +5,6 @@ Revises: b85f02ec1308
Create Date: 2024-06-09 14:58:19.946509
"""
from alembic import op
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 7477a5f5d728
Create Date: 2024-08-10 19:20:34.527559
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: d9ec13955951
Create Date: 2024-08-20 15:28:52.993827
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -1,65 +0,0 @@
"""lowercase_user_emails
Revision ID: 4d58345da04a
Revises: f1ca58b2f2ec
Create Date: 2025-01-29 07:48:46.784041
"""
import logging
from typing import cast
from alembic import op
from sqlalchemy.exc import IntegrityError
from sqlalchemy.sql import text
# revision identifiers, used by Alembic.
revision = "4d58345da04a"
down_revision = "f1ca58b2f2ec"
branch_labels = None
depends_on = None
logger = logging.getLogger("alembic.runtime.migration")
def upgrade() -> None:
"""Conflicts on lowercasing will result in the uppercased email getting a
unique integer suffix when converted to lowercase."""
connection = op.get_bind()
# Fetch all user emails that are not already lowercase
user_emails = connection.execute(
text('SELECT id, email FROM "user" WHERE email != LOWER(email)')
).fetchall()
for user_id, email in user_emails:
email = cast(str, email)
username, domain = email.rsplit("@", 1)
new_email = f"{username.lower()}@{domain.lower()}"
attempt = 1
while True:
try:
# Try updating the email
connection.execute(
text('UPDATE "user" SET email = :new_email WHERE id = :user_id'),
{"new_email": new_email, "user_id": user_id},
)
break # Success, exit loop
except IntegrityError:
next_email = f"{username.lower()}_{attempt}@{domain.lower()}"
# Email conflict occurred, append `_1`, `_2`, etc., to the username
logger.warning(
f"Conflict while lowercasing email: "
f"old_email={email} "
f"conflicting_email={new_email} "
f"next_email={next_email}"
)
new_email = next_email
attempt += 1
def downgrade() -> None:
# Cannot restore original case of emails
pass

View File

@@ -5,7 +5,7 @@ Revises: 47e5bef3a1d7
Create Date: 2024-11-06 13:15:53.302644
"""
import logging
from typing import cast
from alembic import op
import sqlalchemy as sa
@@ -20,8 +20,13 @@ down_revision = "47e5bef3a1d7"
branch_labels: None = None
depends_on: None = None
# Configure logging
logger = logging.getLogger("alembic.runtime.migration")
logger.setLevel(logging.INFO)
def upgrade() -> None:
logger.info(f"{revision}: create_table: slack_bot")
# Create new slack_bot table
op.create_table(
"slack_bot",
@@ -58,6 +63,7 @@ def upgrade() -> None:
)
# Handle existing Slack bot tokens first
logger.info(f"{revision}: Checking for existing Slack bot.")
bot_token = None
app_token = None
first_row_id = None
@@ -65,12 +71,15 @@ def upgrade() -> None:
try:
tokens = cast(dict, get_kv_store().load("slack_bot_tokens_config_key"))
except Exception:
logger.warning("No existing Slack bot tokens found.")
tokens = {}
bot_token = tokens.get("bot_token")
app_token = tokens.get("app_token")
if bot_token and app_token:
logger.info(f"{revision}: Found bot and app tokens.")
session = Session(bind=op.get_bind())
new_slack_bot = SlackBot(
name="Slack Bot (Migrated)",
@@ -161,9 +170,10 @@ def upgrade() -> None:
# Clean up old tokens if they existed
try:
if bot_token and app_token:
logger.info(f"{revision}: Removing old bot and app tokens.")
get_kv_store().delete("slack_bot_tokens_config_key")
except Exception:
pass
logger.warning("tried to delete tokens in dynamic config but failed")
# Rename the table
op.rename_table(
"slack_bot_config__standard_answer_category",
@@ -180,6 +190,8 @@ def upgrade() -> None:
# Drop the table with CASCADE to handle dependent objects
op.execute("DROP TABLE slack_bot_config CASCADE")
logger.info(f"{revision}: Migration complete.")
def downgrade() -> None:
# Recreate the old slack_bot_config table
@@ -261,7 +273,7 @@ def downgrade() -> None:
}
get_kv_store().store("slack_bot_tokens_config_key", tokens)
except Exception:
pass
logger.warning("Failed to save tokens back to KV store")
# Drop the new tables in reverse order
op.drop_table("slack_channel_config")

View File

@@ -5,7 +5,6 @@ Revises: 7da0ae5ad583
Create Date: 2023-11-27 17:23:29.668422
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: f7e58d357687
Create Date: 2024-08-28 17:40:46.077470
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.sql import func

View File

@@ -5,7 +5,6 @@ Revises: 94dc3d0236f8
Create Date: 2024-12-11 18:05:05.490737
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 61ff3651add4
Create Date: 2024-09-18 17:00:23.755399
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 7547d982db8f
Create Date: 2024-05-04 17:49:28.568109
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 800f48024ae9
Create Date: 2023-09-20 16:59:39.097177
"""
from alembic import op
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: d929f0c1c6af
Create Date: 2023-09-04 15:29:44.002164
"""
import fastapi_users_db_sqlalchemy
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 949b4a92a401
Create Date: 2024-10-30 19:37:59.630704
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: efb35676026c
Create Date: 2024-09-13 18:52:59.256478
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e4334d5b33ba
Create Date: 2024-10-08 15:56:07.975636
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e6a4bbc13fe4
Create Date: 2023-08-10 21:43:09.069523
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: dbaa756c2ccf
Create Date: 2024-02-16 15:02:03.319907
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 1d6ad76d1f37
Create Date: 2024-08-06 15:35:40.278485
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 1b8206b29c5d
Create Date: 2024-09-05 13:57:11.770413
"""
import fastapi_users_db_sqlalchemy
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 0a98909f2757
Create Date: 2024-05-07 14:54:55.493100
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5d12a446f5c0
Create Date: 2024-10-15 17:47:44.108537
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,118 +0,0 @@
"""duplicated no-harm user file migration
Revision ID: 6a804aeb4830
Revises: 8e1ac4f39a9f
Create Date: 2025-04-01 07:26:10.539362
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy import inspect
import datetime
# revision identifiers, used by Alembic.
revision = "6a804aeb4830"
down_revision = "8e1ac4f39a9f"
branch_labels = None
depends_on = None
def upgrade() -> None:
# Check if user_file table already exists
conn = op.get_bind()
inspector = inspect(conn)
if not inspector.has_table("user_file"):
# Create user_folder table without parent_id
op.create_table(
"user_folder",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("user_id", sa.UUID(), sa.ForeignKey("user.id"), nullable=True),
sa.Column("name", sa.String(length=255), nullable=True),
sa.Column("description", sa.String(length=255), nullable=True),
sa.Column("display_priority", sa.Integer(), nullable=True, default=0),
sa.Column(
"created_at", sa.DateTime(timezone=True), server_default=sa.func.now()
),
)
# Create user_file table with folder_id instead of parent_folder_id
op.create_table(
"user_file",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("user_id", sa.UUID(), sa.ForeignKey("user.id"), nullable=True),
sa.Column(
"folder_id",
sa.Integer(),
sa.ForeignKey("user_folder.id"),
nullable=True,
),
sa.Column("link_url", sa.String(), nullable=True),
sa.Column("token_count", sa.Integer(), nullable=True),
sa.Column("file_type", sa.String(), nullable=True),
sa.Column("file_id", sa.String(length=255), nullable=False),
sa.Column("document_id", sa.String(length=255), nullable=False),
sa.Column("name", sa.String(length=255), nullable=False),
sa.Column(
"created_at",
sa.DateTime(),
default=datetime.datetime.utcnow,
),
sa.Column(
"cc_pair_id",
sa.Integer(),
sa.ForeignKey("connector_credential_pair.id"),
nullable=True,
unique=True,
),
)
# Create persona__user_file table
op.create_table(
"persona__user_file",
sa.Column(
"persona_id",
sa.Integer(),
sa.ForeignKey("persona.id"),
primary_key=True,
),
sa.Column(
"user_file_id",
sa.Integer(),
sa.ForeignKey("user_file.id"),
primary_key=True,
),
)
# Create persona__user_folder table
op.create_table(
"persona__user_folder",
sa.Column(
"persona_id",
sa.Integer(),
sa.ForeignKey("persona.id"),
primary_key=True,
),
sa.Column(
"user_folder_id",
sa.Integer(),
sa.ForeignKey("user_folder.id"),
primary_key=True,
),
)
op.add_column(
"connector_credential_pair",
sa.Column("is_user_file", sa.Boolean(), nullable=True, default=False),
)
# Update existing records to have is_user_file=False instead of NULL
op.execute(
"UPDATE connector_credential_pair SET is_user_file = FALSE WHERE is_user_file IS NULL"
)
def downgrade() -> None:
pass

View File

@@ -5,7 +5,6 @@ Revises: 47433d30de82
Create Date: 2023-05-05 14:40:10.242502
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 177de57c21c9
Create Date: 2024-11-22 11:51:29.331336
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 3c6531f32351
Create Date: 2025-01-13 18:12:18.029112
"""
from alembic import op
import sqlalchemy as sa
@@ -33,7 +32,6 @@ def upgrade() -> None:
sa.ForeignKeyConstraint(
["persona_label_id"],
["persona_label.id"],
ondelete="CASCADE",
),
sa.PrimaryKeyConstraint("persona_id", "persona_label_id"),
)

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