Krish Dholakia
eed0cf2ee9
UI SSO - fix reset env var when ui_access_mode is updated ( #13011 )
...
* fix(ui_sso.py): fix form action on login when sso is enabled
* fix: multiple fixes - fix resetting env var in proxy config + add key to exception message on key decryption
fixes issue where env vars would be reset
* refactor(proxy_server.py): cleanup redundant decryption line
* fix(proxy_setting_endpoints.py): show saved ui access mode
allows admin to know what they'd previously stored in db
2025-07-26 11:42:41 -07:00
Krish Dholakia
4b50566d6d
[FEAT] Model-Guardrails: Add on UI ( #13006 )
...
* feat(proxy_server.py): working guardrails on streaming output
ensures guardrail actually raises an error if flagged during streaming output
* test: add unit tests
* feat(advanced_settings.tsx): add guardrails option as ui component on model add
enables setting guardrails on model add
* feat(add_model_tab.tsx): fix add model form
* feat(model_info_view.tsx): support adding guardrails on model update
* fix(add_model_tab.tsx/): working health check when guardrails selected
* fix(proxy_server.py): fix yield
2025-07-26 11:42:03 -07:00
Jugal D. Bhatt
586b1ec8b4
[Vector Store] make vector store permission management OSS ( #12990 )
...
* add vector store on ui behind enterprise in vector store
* remove enterprise
2025-07-26 11:13:49 -07:00
Matthias Dittrich
9211158e73
Fixup ollama model listing (again) ( #13008 )
2025-07-26 11:07:49 -07:00
Jugal D. Bhatt
10595ea077
[MCP Gateway] add Litellm mcp alias for prefixing ( #12994 )
...
* change alias-> server_name
* add server alias uses
* add tests
* schema
* ruff fix
* fix alias for config
* fix tests
* add alias
* fix tests
* fix tests
* add a common util
* ruff fix
* fix migration
2025-07-25 17:57:52 -07:00
Jugal D. Bhatt
c7774ba495
add fix for redaction ( #13005 )
2025-07-25 17:48:48 -07:00
Emerson Gomes
dc8c14b504
Fix issue writing db ( #13001 )
2025-07-25 17:27:13 -07:00
Krish Dholakia
d6423d913d
build: update pip package ( #12998 )
2025-07-25 16:23:53 -07:00
Krrish Dholakia
5ad116ae89
feat(proxy_server.py): support checking full str on streaming guardrails post call hook
...
ensures streaming guardrails are actually useful
2025-07-25 15:49:50 -07:00
Timothy Lowrimore
94273dc8b7
Merge branch 'main' into heroku-llms
2025-07-25 16:46:01 -06:00
Krrish Dholakia
e5d68e5222
feat(proxy/utils.py): support model level guardrails on stream event
...
enables guardrails to work with streaming
2025-07-25 15:37:27 -07:00
Timothy Lowrimore
dd109e7c37
adds heroku to supported providers table
2025-07-25 16:28:56 -06:00
Andrei Darashenka
ddac3d5386
honor OLLAMA_API_KEY for ollama_chat
2025-07-26 00:16:14 +02:00
Timothy Lowrimore
c51b8d0a6d
doc edits
2025-07-25 16:14:36 -06:00
Timothy Lowrimore
0eb05ad23f
adds sidebar link to Heroku provider docs
2025-07-25 16:11:39 -06:00
Timothy Lowrimore
79e4308809
adds provider docs
2025-07-25 16:02:26 -06:00
Jugal D. Bhatt
d1b63566ac
remove features from enterprise ( #12988 )
2025-07-25 10:55:28 -07:00
Jugal D. Bhatt
c66b288bcf
[LLM Translation] fix query params for realtime api intent ( #12838 )
...
* fix query params for realtime api intent
* fix my py
* Add typed dict
* remove typed dict
* fix comments
* add test
* add test
* added proxt log revert
* add real time q params
2025-07-25 10:09:53 -07:00
Jugal D. Bhatt
c2833e693e
clean and verify key before inserting ( #12840 )
...
* clean and verify key
* change checking logic
* Add unit test
2025-07-25 10:09:28 -07:00
Jugal D. Bhatt
b4da29c83e
[LLM Translation] Add bytedance/ui-tars-1.5-7b on openrouter ( #12882 )
...
* add bytedance model
* add source
2025-07-25 10:09:14 -07:00
Krish Dholakia
23d562b1a2
build(github/manual_pypi_publish.yml): manual workflow to publish pip package - used for pushing dev releases ( #12985 )
...
* build(github/manual_pypi_publish.yml): manual workflow to publish pip package - used for pushing dev releases
* ci: remove redundant file
2025-07-25 09:26:47 -07:00
Ishaan Jaff
0f015a2f68
docs fix link
2025-07-25 09:08:18 -07:00
Ishaan Jaff
8f86355361
fix ci/cd testing
2025-07-25 09:05:27 -07:00
Ishaan Jaff
1a15bd4885
docs auto router
2025-07-25 09:04:27 -07:00
Ishaan Jaff
f2e9834dc6
docs - auto router on litellm proxy
2025-07-25 08:58:54 -07:00
Ishaan Jaff
7bb48ffaf9
docs auto routing
2025-07-25 08:50:16 -07:00
Timothy Lowrimore
da6eac4aac
passing tests
...
added necessary provider models to model prices and context window files
2025-07-25 09:18:54 -06:00
Ishaan Jaff
50574c0c3e
docs - auto routing
2025-07-25 07:31:39 -07:00
Ishaan Jaff
20450bfe94
fix mapped test
2025-07-25 07:24:42 -07:00
Ishaan Jaff
ecfafd1243
docs update
2025-07-25 07:19:32 -07:00
Ishaan Jaff
7745f61fb1
docs update
2025-07-25 07:19:20 -07:00
Ishaan Jaff
9c76ccd92c
docs Health Check Server
2025-07-25 07:17:26 -07:00
Krish Dholakia
6d3ce76e1c
Guardrails - support model-level guardrails ( #12968 )
...
* fix(custom_guardrail.py): initial logic for model level guardrails
* feat(custom_guardrail.py): working pre call guardrails
* fix(custom_guardrails.py): check if custom guardrails set before running event hook
* test(test_custom_guardrail.py): add unit tests for async pre call deployment hook on custom guardrail
* feat(custom_guardrail.py): add post call processing support for guardrails
allows model based guardrails to run on the post call event for that model only
* fix(utils.py): only run if call type is in enum
* test: update unit tests to work
2025-07-24 22:38:03 -07:00
Krish Dholakia
dd607cd301
Show global retry policy on UI ( #12969 )
...
* fix(router.py): return global retry policy on `get/config/callbacks`
Partial fix for https://github.com/BerriAI/litellm/issues/12855
* fix(model_dashboard.tsx): accept global retry policy
Fixes https://github.com/BerriAI/litellm/issues/12855
* fix(model_dashboard.tsx): update global retry policy, if that's what was edited
2025-07-24 22:37:15 -07:00
Dmitriy Alergant
0cc320cc0a
GuardrailsAI: use validatedOutput to allow usage of "fix" guards. Previously "fix" guards had no effect in llmOutput mode. ( #12891 )
2025-07-24 22:07:06 -07:00
sings-to-bees-on-wednesdays
eb96fb78bc
fix(auth_utils): make header comparison case-insensitive ( #12950 )
...
If the user specified in the configuration e.g. "user_header_name:
X-OpenWebUI-User-Email", here we were looking for a dict key
"X-OpenWebUI-User-Email" when the dict actually contained
"x-openwebui-user-email".
Switch to iteration and case insensitive string comparison instead to
fix this.
This fixes customer budget enforcement when the customer ID is passed
in as a header rather than as a "user" value in the body.
2025-07-24 22:06:12 -07:00
Cole McIntosh
3ca65b3064
feat: Update model pricing and context window configurations ( #12910 )
...
- Adjusted input and output cost per token for existing models.
- Added new model configuration for "openrouter/qwen/qwen3-coder" with specified token limits and costs.
2025-07-24 21:57:15 -07:00
Gaston
6cfaf674e4
Fix: Shorten Gemini tool_call_id for Azure compatibility ( #12941 )
2025-07-24 21:52:16 -07:00
Murad Khafizov
650ae0ef88
Added documentation about metadata exposed over the /v1/models endpoint ( #12942 )
2025-07-24 21:51:16 -07:00
Santosh Dhaladhuli
d9d53466e8
[Feat] Add inpainting support and corresponding tests for Amazon Nova Canvas ( #12949 )
2025-07-24 21:46:06 -07:00
Ishaan Jaff
fdb2ebf344
bump: version 1.74.8 → 1.74.9
2025-07-24 21:27:15 -07:00
Ishaan Jaff
d892e969ab
ui new build
2025-07-24 21:27:06 -07:00
Ishaan Jaff
91eee78a8c
Revert "EditAutoRouterTabProps"
...
This reverts commit 2835d3a3743e6411b9914a0b01381050e2273ad7.
2025-07-24 21:26:01 -07:00
Ishaan Jaff
0630b52044
EditAutoRouterTabProps
2025-07-24 21:26:01 -07:00
Ishaan Jaff
39b0fe0bf7
[Feat] Edit Auto Router Settings on UI ( #12966 )
...
* EditAutoRouterTabProps
* Revert "EditAutoRouterTabProps"
This reverts commit 2835d3a3743e6411b9914a0b01381050e2273ad7.
* add EditAutoRouterTab
* delete edit
* fixes for edit auto-router
* fix accessing model edit
* working edit auto router
* fix - edit remove custom model name
* fixes for edit auto router settings
* qa for adding a model router
* test fix
2025-07-24 21:25:48 -07:00
Ishaan Jaff
29cff4f4e6
pip install semantic_router --no-deps
2025-07-24 20:09:37 -07:00
Ishaan Jaff
6e0c84363e
test fix test_litellm_anthropic_prompt_caching_tools
2025-07-24 20:06:22 -07:00
Ishaan Jaff
106a298f0a
[Feat] UI - Allow Adding LiteLLM Auto Router on UI ( #12960 )
...
* add router.json
* test_router_auto_router
* async_pre_routing_hook
* fixes for auto router
* add async_pre_routing_hook
* add LiteLLMRouterEncoder
* update test auto_router_embedding_model
* add auto_router_embedding_model
* add AutoRouter
* fix async_pre_routing_hook
* update async_pre_routing_hook
* fix auto router
* fix router.json
* working router init
* working embedding encoder
* working auto router
* test_router_auto_router
* test auto router
* add semantic-router as optional for litellm
* add extras
* semantic_router==0.1.10
* ruff fix
* use aiohttp==3.10.11
* python-dotenv==1.0.1
* test auto router
* test_router_auto_router
* semantic_router
* test_is_auto_router_deployment
* fix check
* fix docker build step
* add semantic_router
* UI - Add auto router on litellm
* working utterances config
* fix route config builder
* kind of working add automodel router
* move loc of add deployment
* fixes for AutoRouter
* add auto_router_config in types.py
* fixes for init_auto_router_deployment
* fix adding auto router models
* working auto-router with dB
* Revert "add semantic_router"
This reverts commit 537b67288798731a119d811f643b682086377ee9.
* TestAutoRouter
* fix linting
* add semantic router to docker
* test fix
* fix router config builder
* remove export button
2025-07-24 19:58:49 -07:00
Jugal D. Bhatt
e63b163578
added new realtime model for openai ( #12946 )
2025-07-24 19:57:39 -07:00
Ishaan Jaff
6174609685
[LLM Translation] - Bug fix Anthropic Tool calling ( #12959 )
...
* fix _map_tool_helper
* fix linting
2025-07-24 19:55:52 -07:00
