2915 Commits

Author SHA1 Message Date
e399eeb014 fix: Query History Export (#4841)
* Move task registration to earlier in the API

* Remove unnecessary check
2025-06-09 10:10:53 -07:00
b133e8fcf0 enforce sub_question ordering for chat_message (#4848) 2025-06-09 02:37:35 +00:00
ba9b24a477 Enhance credential management with multi-auth support and improved validation (#4846)
Co-authored-by: Subash <subash@onyx.app>
2025-06-09 00:53:18 +00:00
cc7fb625a6 KG autofill metadata (#4834)
* feat: autofill metadata

* fix: typo

* fix: enum

* fix: nit
2025-06-08 21:56:50 +00:00
2b812b7d7d Kg batch clustering (#4847)
* super genius kg_entity parent migration

* feat: batched clustering

* fix: nit
2025-06-08 21:16:10 +00:00
c5adbe4180 Knowledge Graph v1 (#4626)
* db setup

* transfer 1 - incomplete

* more adjustments

* relationship table + query update

* temp view creation

* restructuring

* nits

* updates

* separate read_only engine

* extraction revamp

* focus on metadata relatonships 1

* dev

* migration downgrade fix

* rebase migration change

* a3+

* progress

* base

* new extraction

* progress

* fixed KG extraction

* nits

* updates

* simplifications & cleanup

* fixes

* updates

* more feature flag checks

* fixes

* extraction process fix

* read-only user creation as part of setup

* fix for missing entity attributes

* kg read-only user creation as part of migration

* typo

* EL initial comments

* initial Account/SF Connector chnges

* SF Connector update

 - include account information

* base w/ salesforce

* evan updates + quite a bit more

* kg-filtered search

* EL changes pt 2

* migrations and env vars

* quick migration fix

* migration update

* post_rebase fixes

* mypy fixes

* test fixes

* test fix

* test fix

* read_only pool + misc

* nf

* env vars

* test improvements

* salesforce fix

* test update

* small changes

* small adjustments

* SF Connector fix & kg_stage removal for one table

* mypy fix

* small fixes

* EL + RK (pt 1) comments

* nit

* setting updated

* Salesforce test update

* EL comments

* read-only user replacement & cleanup

* SQL View fix

* converting entity type-name separators

* sql view group ownership

* view fix

* SQL tweak

* dealing with docs that were skipped by indexing

* increased error handling

* more error handling

* Output formatting fix

* kg-incremental-reindexing

* 0-doc found improvement

* celery

* migration correction

* timeout adjustments

* nit

* Updated migration

* Entity Normalization for KG Dev 1 (#4746)

* feat: trigrams column

* fix: reranking and db

* feat: v1

* fix: convert to orm

* feat: parallel

* fix: default to id_name

* fix: renamed semantic_id and semantic_id_trigrams

* fix: scalar subquery

* fix: tuning + redundancy

* fix: threshold

* fix: typo

* fix: shorten names

* wip

* fix: reverted

* feat: config

* feat: works but it was dumb

* feat: clustering works

* fix: mypy

* normalization <-> language awareness for SQL generation

* small type fixes

---------

Co-authored-by: joachim-danswer <joachim@danswer.ai>

* mypy

* typo and dead code

* kg_time_fencing

* feat: remove temp views on migration downgrade

* remove functions and triggers for now

* rebase adjustments

* EL code review results

* quick fix + trigger/funcs for single tenant

* fix: typo, mypy, dead code

* fix: autoflake

* small updatesd

* nit

* fix: typo

* early + faster view creation

* Extension creation in MT migration

* nit changes to default ETs

* Incremental Clustering and KG Refactor V1 (#4784)

Optimized/restructured incremental clustering. New pipeline actually that moves vespa updates to clustering.
Also, celery configuration has been updated.
---------

Co-authored-by: joachim-danswer <joachim@danswer.ai>

* prompt tweak & ET extraction reset

* more general hierarchical structure

* feat: better vespa reset logic

* prompt optimization and entity replacemants

* small prompt changes

* KG Refactor V2 (#4814)

Clustering & Extraction improvements & various nits 

Co-authored-by: joachim-danswer <joachim@danswer.ai>

* add connector-level coverage days

* fix: nit

* initial  EL responses

* refactor: helper functions for formatting

* fix: more helper fns & comments

* fix: comment code that's been implemented elsewhere

* fix: tenant_id missing arg

* fix: removed debugging stuff

* fix: moved kg_interactions db query to helper fn

* fix: tenant_id

* fix: tenant_id & removed outdated helper fn

* fix always set entity class

* fix: typo

* fix alembic heads

* fix: celery logging

* fix: migrations fix

* fix: multi tenant permissions

* fix: temp connector fix

* fix: downgrade

* Fix upgrade migration

* fix: tenant for normalization

* added additional acl

* stray EL comments

* fix: connector test

* fix mypy

* fix: temporary connector test fix

* fix: jira connector test

* nit

* small nits

* fix: black

* fix: mypy

* fix: mypy

---------

Co-authored-by: Rei Meguro <36625832+Orbital-Web@users.noreply.github.com>
2025-06-07 23:14:20 +00:00
21dc3a2456 Restart script clarity (#4839)
* Add error clarity to restart containers script

* erroneous cleanup on exit

* fix when starting containers for the first time

---------

Co-authored-by: Wenxi Onyx <wenxi-onyx@Wenxis-MacBook-Pro.local>
2025-06-06 09:11:58 -07:00
9631f373f0 Restart script clarity (#4837)
* Add error clarity to restart containers script

* erroneous cleanup on exit

* space

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

---------

Co-authored-by: Wenxi Onyx <wenxi-onyx@Wenxis-MacBook-Pro.local>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2025-06-05 19:24:06 -07:00
dc4b9bc003 Fixed indexing when no sites are specified (#4822)
* Fixed indexing when no sites are specificed

* Added test for Sharepoint all sites index

* Accounted for paginated results.

* Typing

* Typing

---------

Co-authored-by: Wenxi Onyx <wenxi-onyx@Wenxis-MacBook-Pro.local>
2025-06-05 23:25:20 +00:00
affb9e6941 Extend the onyx_vespa_schemas.py script (#4835) 2025-06-05 22:47:32 +00:00
dc542fd7fa Enable default quantization (#4815)
* Adjust migration

* update default in form

* Add cloud indices for bfloat16

* Update backend/shared_configs/configs.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Update vespa schema gen script

* Move embedding configs

* Remove unused imports

* remove import from shared configs

* Remove unused model

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2025-06-05 14:02:08 -07:00
85eeb21b77 add slack percentage progress (#4809)
* add percentage progress

* range checking

* formatting

* for new channels, skip them if the most recent messages are all from bots

* comments

* bypass bot channels

* code review

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-06-05 17:52:46 +00:00
4bb3ee03a0 Update GitHub Connector metadata (#4769)
* feat: updated github metadata

* feat: nullity check

* feat: more metadata

* feat: userinfo

* test: connector test + more metadata

* feat: num files changed

* feat str

* feat: list of str
2025-06-04 18:33:14 +00:00
1bb23d6837 Upgrade asyncpg for Python 3.12 (#4699) 2025-06-04 11:44:52 -07:00
f447359815 bump up agent timeouts across the board (#4821) 2025-06-04 14:36:46 +00:00
094cc940a4 Small embedding model cleanups (#4820)
* Small embedding model cleanups

* fix

* address greptile

* fix build
2025-06-04 00:10:44 +00:00
80ecdb711d New metadata for Jira for KG (#4785)
* new metadata components

* nits & tests
2025-06-03 20:12:56 +00:00
a599176bbf Improve reasoning detection (#4817)
* Improve reasoning detection

* Address greptile comments

* Fix mypy
2025-06-03 20:01:12 +00:00
4c93fd448f fix: updating gemini models (#4806)
Co-authored-by: Jeffrey Drakos <jeffreydrakos@Jeffreys-MacBook-Pro-2.local>
2025-06-03 11:16:42 -07:00
84d916e210 Fix hard delete of agentic chats (#4803)
* Fix hard delete of agentic chats

* Update backend/tests/integration/tests/chat/test_chat_deletion.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Address Greptile comments

* fix tests

---------

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2025-06-03 11:14:11 -07:00
f57ed2a8dd Adjust script 2025-06-02 18:39:00 -07:00
713889babf [Connectors][Script] Resume Paused Connectors (#4798)
* [Connectors][Script] Resume Paused Connectors

* Addressing comment
2025-06-02 18:34:00 -07:00
58c641d8ec Remove ordering-only flow 2025-06-02 18:29:42 -07:00
94985e24c6 Adjust user file access 2025-06-02 17:28:49 -07:00
4c71a5f5ff drive perm sync logs + misc deployment improvements (#4788)
* some logs

* give postgress more memory

* give postgress more memory

* give postgress more memory

* revert

* give postgress more memory

* bump external access limit

* vespa timeout

* deployment consistency

* bump vespa version

* skip upgrade check

* retry permission by ids

* logs

* fix temp docx file issue

* fix drive file deduping

* RK comments

* mypy

* aggregate logs
2025-06-01 23:36:57 +00:00
b19e3a500b try fixing slack bot (#4792)
* try fixing slack bot

* add logging

* just use if

* safe msg get

* .close isn't async

* enforce block list size limit

* various fixes and notes

* don't use self

* switch to punkt_tab

* fix return condition

* synchronize waiting, use non thread local redis locks

* fix log format, make collection copy more explicit for readability

* fix some logging

* unnecessary function

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-31 00:39:14 +00:00
267fe027f5 Fix failed docs table (#4800)
* Fix initial LLM provider set up

* Fix IndexAttemptErrorsModal pagination
2025-05-30 22:19:52 +00:00
0d4d8c0d64 jira daylight savings handling (#4797) 2025-05-30 19:13:38 +00:00
6f9d8c0cff Simplify passing in of file IDs for filtering (#4791)
* Simplify passing in of file IDs for filtering

* Address RK comments
2025-05-30 05:08:21 +00:00
5031096a2b Fix frozen add token rate limit migration 2025-05-29 22:22:36 -07:00
797e113000 add a comment (#4789)
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-29 14:11:19 -07:00
ef4d5dcec3 new slack rate limiting approach (#4779)
* fix slack rate limit retry handler for groups

* trying to mitigate memory usage during csv download

* Revert "trying to mitigate memory usage during csv download"

This reverts commit 48262eacf6.

* integrated approach to rate limiting

* code review

* try no redis setting

* add pytest-dotenv

* add more debugging

* added comments

* add more stats

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-29 19:49:32 +00:00
0b5e3e5ee4 skip excel files that openpyxl fails on (#4787) 2025-05-29 18:09:46 +00:00
9f72826143 Bugfix/slack bot debugging (#4782)
* adding some logging

* better var name

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-28 18:43:11 +00:00
16a14bac89 Feature/tenant reporting 2 (#4750)
* add more info

* fix headers

* add filename as param (merge)

* db manager entry in launch template

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-27 23:24:47 +00:00
0b01d7f848 refactor: stream_llm_answer (#4772)
* refactor: stream_llm_answer

* fix: lambda

* fix: mypy, docstring
2025-05-26 22:29:33 +00:00
23ff3476bc print sanitized api key to help troubleshoot (#4764)
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-24 22:27:37 +00:00
0c7ba8e2ac Fix/add back search with files (#4767)
* Allow search w/ user files

* more

* More

* Fix

* Improve prompt

* Combine user files + regular uploaded files
2025-05-24 15:44:39 -07:00
dad99cbec7 v1 refresh drive creds during perm sync (#4768) 2025-05-23 23:01:26 +00:00
3e78c2f087 Fix POSTGRES_IDLE_SESSIONS_TIMEOUT (#4765) 2025-05-23 14:55:23 -07:00
b824951c89 add probe signals for beat (#4760)
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-23 01:41:11 +00:00
ca20e527fc fix tool calling for bedrock claude models (#4761)
* fix tool calling for bedrock claude models

* unit test

* fix unit test
2025-05-23 01:13:18 +00:00
c8e65cce1e add k8s probes (#4752)
* add file signals to celery workers

* improve probe script

* cancel tref

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-22 20:21:59 +00:00
6c349687da improve impersonation logging slightly (#4758)
Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-22 11:17:27 -07:00
9dbe12cea8 Feat: Search Eval Testing Overhaul (provide ground truth, categorize query, etc.) (#4739)
* fix: autoflake & import order

* docs: readme

* fix: mypy

* feat: eval

* docs: readme

* fix: oops forgot to remove comment

* fix: typo

* fix: rename var

* updated default config

* fix: config issue

* oops

* fix: black

* fix: eval and config

* feat: non tool calling query mod
2025-05-21 19:25:10 +00:00
e78637d632 mitigate memory usage during csv download (#4745)
* mitigate memory usage during csv download

* more gc tweaks

* missed some small changes

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-21 00:44:27 +00:00
cac03c07f7 v1 answer refactor (#4721)
* v1 answer refactor

* fix tests

* good catch, tests

* more cleanup
2025-05-20 23:34:27 +00:00
95dabfaa18 fix: Add back Teams' replies processing (#4744)
* Add replies to document construction and edit tests

* Update tests

* Add replies processing to teams

* Fix test

* Add try-except block around potential failure

* Update entity-id during ConnectorFailure raise
2025-05-20 22:55:28 +00:00
e92c418e0f Feature/openapi (#4710)
* starting openapi support

* fix app / app_fn

* send gitignore

* dedupe function names

* add readme

* modify gitignore

* update launch template

* fix unused path param

* fix mypy

* local tests pass

* first pass at making integration tests work

* fixes

* fix script path

* set python path

* try full path

* fix output dir

* fix integration test

* more build fixes

* add generated directory

* use the config

* add a comment

* add

* modify tsconfig.json

* fix index linting bugs

* tons of lint fixes

* new gitignore

* remove generated dir

* add tasks template

* check for undefined explicitly

* fix hooks.ts

* refactor destructureValue

* improve readme

---------

Co-authored-by: Richard Kuo (Onyx) <rkuo@onyx.app>
2025-05-20 21:33:18 +00:00
0593d045bf Fix ext_perm_user sign-up for non multi-tenant (#4743)
* OAuth w/ external user fix

* Apply to basic auth as well
2025-05-20 20:17:01 +00:00