Commit graph

4315 commits

Author SHA1 Message Date
Marko Henning
6663fc3a6c Unloads only if internal models are used. 2025-08-21 10:49:03 +02:00
Marko Henning
cd02ff2e07 Fix if checks 2025-08-20 14:07:13 +02:00
Marko Henning
39fe385017 Correctly unloads embedding/reranker models 2025-08-20 13:30:45 +02:00
Timothy Jaeryang Baek
b3a95f40fc refac/enh: add performance indexes
Co-Authored-By: decent-engineer-decent-datascientist <77806775+decent-engineer-decent-datascientist@users.noreply.github.com>
2025-08-19 03:24:10 +04:00
Tim Jaeryang Baek
96643f5b6d
Merge pull request #14682 from olivier-lacroix/genai-tool-function
refactor: Improve tool callable generation to allow for genai native function call
2025-08-19 03:16:12 +04:00
Timothy Jaeryang Baek
575db66295 feat: save temporary chats 2025-08-19 02:37:18 +04:00
Timothy Jaeryang Baek
d6f709574e refac/enh: async process chat handling 2025-08-19 01:24:53 +04:00
Timothy Jaeryang Baek
4bc77b544e refac 2025-08-18 23:39:14 +04:00
Timothy Jaeryang Baek
70d0477418 refac: tool name collision handling 2025-08-18 21:28:28 +04:00
Timothy Jaeryang Baek
f592748011 refac: tool server redis cache 2025-08-18 20:53:46 +04:00
Timothy Jaeryang Baek
8a157578f4 enh/refac: ability to specify external tool server id 2025-08-18 20:38:55 +04:00
Timothy Jaeryang Baek
f97f21bf3a refac/fix: rename WEB_SEARCH_CONCURRENT_REQUESTS to WEB_LOADER_CONCURRENT_REQUESTS 2025-08-18 20:06:36 +04:00
Timothy Jaeryang Baek
68d42ef850 refac 2025-08-18 19:49:29 +04:00
Timothy Jaeryang Baek
6d0f757848 refac: openai model list 2025-08-18 19:45:26 +04:00
Timothy Jaeryang Baek
094a82b264 refac: follow up prompt template 2025-08-18 15:53:44 +04:00
Timothy Jaeryang Baek
d7363fd65f fix: arena model selected model id 2025-08-17 04:55:45 +04:00
Timothy Jaeryang Baek
f23eb2a31c refac: audio lang fallback logic 2025-08-17 04:33:42 +04:00
Timothy Jaeryang Baek
ccd2a0be5b refac 2025-08-17 04:15:13 +04:00
Tim Jaeryang Baek
47560d4d72
Merge pull request #14703 from rragundez/code-interpreter-blacklist
feat: Blacklist modules from arbitrary code execution in code interpreter
2025-08-17 04:12:12 +04:00
Timothy Jaeryang Baek
7f0c50f445 refac 2025-08-17 04:06:16 +04:00
Timothy Jaeryang Baek
bed6aa63e1 refac 2025-08-17 03:59:00 +04:00
Tim Jaeryang Baek
6a109e972e
Merge pull request #15863 from tcx4c70/feat/sqlite-wal
perf(db): Improve performance of db, especially sqlite
2025-08-17 03:55:59 +04:00
Timothy Jaeryang Baek
2387877dae refac/fix: model name retrieval edge case 2025-08-17 03:50:55 +04:00
Timothy Jaeryang Baek
35e8c77025 refac/fix 2025-08-17 03:21:14 +04:00
Sihyeon Jang
3da22af859 fix(utils/middleware): flush pending chat deltas on stream termination
Guarantees the last partial delta chunk is emitted when the SSE stream closes (EOF, break, or `[DONE]` sentinel).

* Buffer `last_delta_data` and track `delta_count`
* Flush automatically once `delta_count >= chunk_size`
* Perform a final flush after the iterator ends

Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>
2025-08-16 13:03:57 +09:00
Timothy Jaeryang Baek
43aa23ea77 refac 2025-08-15 14:15:27 +04:00
silentoplayz
b810868239 fix: Alembic CLI commands from failing 2025-08-15 04:17:47 -04:00
Tim Jaeryang Baek
0b59aa940e
Merge pull request #16606 from Rain6435/fix/azure-postgresql-pgvector-permissions
fix: resolve Azure PostgreSQL pgvector extension permission issue
2025-08-15 00:59:04 +04:00
Timothy Jaeryang Baek
f1c28455ad refac: async webhook request 2025-08-15 00:07:02 +04:00
Timothy Jaeryang Baek
daa4b3284f refac/fix: OAUTH_GROUPS_CLAIM env var 2025-08-14 23:59:54 +04:00
Timothy Jaeryang Baek
057533f9cc refac 2025-08-14 16:56:08 +04:00
Rain6435
a1e62ab422 fix: Formatting 2025-08-14 01:50:57 -04:00
Rain6435
1a42e96a3b fix: resolve Azure PostgreSQL pgvector extension permission issue
Replace direct CREATE EXTENSION commands with conditional checks to avoid
  permission errors on Azure PostgreSQL Flexible Server where only
  azure_pg_admin members can create extensions.

  - Check pg_extension table before attempting to create vector extension
  - Apply same fix to pgcrypto extension for consistency
  - Allows following least privilege principle for database users

  Fixes #12453
2025-08-14 01:45:02 -04:00
Timothy Jaeryang Baek
13fe78428b refac 2025-08-14 04:50:33 +04:00
Timothy Jaeryang Baek
b43acc2b3d refac/fix: tag attribute handling 2025-08-14 04:04:34 +04:00
Timothy Jaeryang Baek
3e8d3b08fa refac 2025-08-14 04:04:20 +04:00
Timothy Jaeryang Baek
ad98d4300b refac/fix: milvus query logic 2025-08-14 03:18:38 +04:00
Timothy Jaeryang Baek
93205d4320 fix: pending user display content 2025-08-14 02:27:24 +04:00
Timothy Jaeryang Baek
2ed9896dea refac/fix: oauth jwt cookie 2025-08-14 02:00:38 +04:00
Tim Jaeryang Baek
0845b7ffe5
Merge pull request #16582 from koflerm/patch-1
Fix: Retrieve Username Claim from Userinfo Endpoint
2025-08-13 19:23:44 +04:00
Timothy Jaeryang Baek
ff55ca4d75 fix: temp chat not working 2025-08-13 19:18:30 +04:00
Markus Kofler
2011e5711d
Enable Retrieving Username Claim from Userinfo Endpoint 2025-08-13 16:27:25 +02:00
Timothy Jaeryang Baek
e7d9755d97 refac 2025-08-13 18:18:30 +04:00
Tim Jaeryang Baek
8a745b9bbf
Merge branch 'dev' into fix_model_access 2025-08-13 18:07:29 +04:00
Tim Jaeryang Baek
37b8ea3ab2
Merge pull request #16557 from ShirasawaSama/patch-3
feat: Add administrator permission control (BYPASS_MODEL_ACCESS_CONTROL) to the two remaining main APIs
2025-08-13 17:56:39 +04:00
Timothy Jaeryang Baek
4cca1829c2 refac 2025-08-13 17:49:57 +04:00
Timothy Jaeryang Baek
230e21b10c Revert "Merge pull request #16547 from Gyarbij/main"
This reverts commit dd3cd4ac4f, reversing
changes made to f0c2d47b24.
2025-08-13 17:49:19 +04:00
Tim Jaeryang Baek
dd3cd4ac4f
Merge pull request #16547 from Gyarbij/main
fix: improve model sorting by handling missing names
2025-08-13 17:48:46 +04:00
Shirasawa
e966f54001 feat: Add administrator permission control to the two remaining APIs 2025-08-13 07:02:36 +00:00
Chono N
23575825a1
fix: improve model sorting by handling missing names 2025-08-12 22:27:59 +02:00