Classic298
d0c2bfdbff
fix(db): release connection before LLM call in OpenAI /chat/completions ( #20572 )
...
Remove Depends(get_session) from the /chat/completions endpoint to prevent database connections from being held during the entire duration of LLM calls (30-60+ seconds for streaming responses).
Previously, the database session was acquired at request start and held until the streaming response completed. Under concurrent load, this exhausted the connection pool, causing QueuePool timeout errors for other database operations.
The fix allows Models.get_model_by_id() and has_access() to manage their own short-lived sessions internally, releasing the connection immediately after the quick authorization checks complete - before the slow external LLM API call begins.
2026-01-11 23:34:11 +04:00
Timothy Jaeryang Baek
9223efaff0
fix: native function calling system prompt duplication
2026-01-08 23:08:47 +04:00
Timothy Jaeryang Baek
700349064d
chore: format
2026-01-08 01:55:56 +04:00
Timothy Jaeryang Baek
fe3047d53c
refac
2025-12-29 02:05:55 +04:00
Timothy Jaeryang Baek
2453b75ff0
refac
2025-12-29 01:31:27 +04:00
Timothy Jaeryang Baek
b35aeb8f46
feat: custom model base model fallback
...
Co-Authored-By: Classic298 <27028174+Classic298@users.noreply.github.com >
2025-12-21 20:22:37 +04:00
Classic298
823b9a6dd9
chore/perf: Remove old SRC level log env vars with no impact ( #20045 )
...
* Update openai.py
* Update env.py
* Merge pull request open-webui#19030 from open-webui/dev (#119 )
Co-authored-by: Tim Baek <tim@openwebui.com >
Co-authored-by: Claude <noreply@anthropic.com >
---------
Co-authored-by: Tim Baek <tim@openwebui.com >
Co-authored-by: Claude <noreply@anthropic.com >
2025-12-20 08:16:14 -05:00
Timothy Jaeryang Baek
0eb33e8e12
refac: logit bias handling
2025-12-16 13:49:00 -05:00
Classic298
99f0fe7f32
chore: user header forward minimize code changes throughout codebase ( #19392 )
...
* Update external.py
* remove unused imports
* Update ollama.py
* Update ollama.py
* Update ollama.py
* Update openai.py
2025-11-23 16:48:03 -05:00
Timothy Jaeryang Baek
c2f889cf9a
refac: add reasoning_effort to azure supported params
2025-11-19 14:59:20 -05:00
Timothy Jaeryang Baek
e76f77bcb7
refac: stream chunk max buffer size
2025-11-09 21:16:34 -05:00
Shirasawa
89c0e150c8
feat: handle large stream chunks responses
2025-11-07 07:00:06 +00:00
Timothy Jaeryang Baek
20af60be42
refac
2025-11-01 16:00:11 -04:00
Timothy Jaeryang Baek
fdf7ca15ea
refac
2025-11-01 06:07:00 -04:00
Timothy Jaeryang Baek
f25b7b73b4
refac: openai additional headers support
2025-10-03 00:23:26 -05:00
Timothy Jaeryang Baek
e4c4ba0979
fix: oauth token
2025-09-19 00:10:48 -05:00
Timothy Jaeryang Baek
c01255570b
chore: format
2025-09-17 11:11:46 -05:00
Timothy Jaeryang Baek
caf0a1fbb6
feat: Allow Azure OpenAI to authenticate using DefaultAzureCredential
...
Co-Authored-By: Selene Blok <20491756+selenecodes@users.noreply.github.com >
2025-09-17 11:04:47 -05:00
Timothy Jaeryang Baek
6c0a5fa91c
refac
2025-09-11 21:56:59 +04:00
Timothy Jaeryang Baek
6f6412dd16
refac
2025-09-08 19:53:44 +04:00
Timothy Jaeryang Baek
2b2d123531
refac: oauth auth type in openai connection
2025-09-08 19:42:50 +04:00
Sihyeon Jang
3ccbb46938
perf: fix cache key generation for model list caching
...
- Replace Request object with user.id in cache key for get_all_models
- Request objects are new instances per HTTP request, preventing cache hits
- Cache keys now use user.id ensuring proper cache functionality
- Affects both Ollama and OpenAI model list endpoints
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com >
2025-09-03 05:17:41 +09:00
Timothy Jaeryang Baek
094a16ab49
refac
2025-08-21 03:38:26 +04:00
Timothy Jaeryang Baek
ba972ecd52
refac
2025-08-20 21:05:04 +04:00
Timothy Jaeryang Baek
6d0f757848
refac: openai model list
2025-08-18 19:45:26 +04:00
Timothy Jaeryang Baek
35e8c77025
refac/fix
2025-08-17 03:21:14 +04:00
Timothy Jaeryang Baek
4b41cd1891
chore: format
2025-08-09 02:05:07 +04:00
Tim Jaeryang Baek
17084f629c
Merge pull request #16385 from gaby/2025-08-08-13-38-31
...
feat: Propagate upstream OpenAI router errors
2025-08-09 00:58:14 +04:00
Tim Jaeryang Baek
9fbc76f4bb
Merge pull request #16397 from 17jmumford/add_gpt_5_max_token_handling
...
fix: added gpt-5 to reasoning model payload handler
2025-08-09 00:22:30 +04:00
Jeremy Mumford
c69f2cc776
updated comments
2025-08-08 14:20:14 -06:00
Jeremy Mumford
0c40d93da4
renamed and added gpt-5 to reflect OpenAI updates
2025-08-08 14:16:28 -06:00
Juan Calderon-Perez
5d7e8c8e5f
Format openai router
2025-08-08 10:04:02 -04:00
Juan Calderon-Perez
2ae7584686
feat: forward upstream OpenAI errors
2025-08-08 09:38:34 -04:00
Timothy Jaeryang Baek
d3547f0f54
refac: error handling
2025-07-31 16:17:33 +04:00
Timothy Jaeryang Baek
671f577264
feat/enh: forward chat id in header
2025-07-18 15:03:46 +04:00
Sihyeon Jang
17f0bef2e2
refactor: use cleanup_response on openai
...
Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com >
2025-07-15 10:11:22 +09:00
Athanasios Oikonomou
96758176cc
fix: don't over quote forwarded headers
...
Fix introduced on #15035 is over quoting headers.
Eg mails instead of user@example.com shown as user%40example.com
Eg names instead of First Last shown as First%20Last
Also we are spending some time quoting ids and roles without required.
Keep quote only on user name, initially had problem based on the discussion
https://github.com/open-webui/open-webui/discussions/14391
Also add space in safe characters, in order remove %20 from names.
2025-07-10 22:08:28 +03:00
Timothy Jaeryang Baek
2b88f66762
refac: MODEL_LIST_CACHE_TTL -> MODELS_CACHE_TTL
2025-06-28 14:44:47 +04:00
Timothy Jaeryang Baek
0447790e6a
feat: MODEL_LIST_CACHE_TTL
2025-06-27 15:59:30 +04:00
Timothy Jaeryang Baek
e1f5f1e0b1
refac
2025-06-20 09:58:44 +04:00
Adam Tao
baafdb752c
feat(openai): Add stream_options to payload if api_version supports
...
Signed-off-by: Adam Tao <tcx4c70@gmail.com >
2025-06-18 21:17:09 +08:00
priten
f7920df870
Fix non-ascii error issue on ENABLE_FORWARD_USER_INFO_HEADERS
2025-06-16 12:33:11 -05:00
Timothy Jaeryang Baek
5e35aab292
chore: format
2025-06-05 01:12:28 +04:00
henry
3ddebefca2
openai embeddings function modified
2025-06-04 16:13:53 +02:00
Henry
415114504f
Merge branch 'open-webui:main' into main
2025-06-04 15:37:33 +02:00
Timothy Jaeryang Baek
d43bbcae28
refac/fix: open webui params handling
2025-05-29 12:57:58 +04:00
Timothy Jaeryang Baek
2ab5aa4d34
refac: azure openai
2025-05-19 04:31:04 +04:00
Timothy Jaeryang Baek
2e56b1f13d
refac
2025-05-19 03:55:56 +04:00
Timothy Jaeryang Baek
caeb822cdc
feat: azure openai support
2025-05-19 03:40:32 +04:00
Timothy Jaeryang Baek
08e4c163ea
feat: local/external connections
2025-05-17 01:47:48 +04:00
