Commit graph

5084 commits

Author SHA1 Message Date
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 537b672887.

* 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
Krish Dholakia
1a57875d24
Proxy - specify key_type - allows specifying if key can call LLM API routes vs. Management routes only (#12909)
* feat(key_management_endpoints.py): Support new 'key_type' field

allow user to specify if key should be 'management' or 'llm api' key

Security fix

* test(test_route_checks.py): add unit tests

* fix(create_key_button.tsx): add ui component to select key type

allows specifying if key can call llm api vs. management routes

* feat(create_key_button.tsx): add specifying key type to ui

* fix(route_checks.py): add sensitive data masker for user id on not allowed error message

prevent leaking sensitive information
2025-07-24 16:40:40 -07:00
Ishaan Jaff
3e529fae7f
[UI] Allow setting up CloudZero Usage through LiteLLM UI (#12923)
* refactor cz settings

* allow viewing/setting CZ settings

* working button

* fixes for export button

* nicer button

* fix className
2025-07-23 21:17:12 -07:00
Krrish Dholakia
4277becdc2 docs(credentials.tsx): cleanup reference to dead link 2025-07-23 09:02:39 -07:00
Krish Dholakia
d26f74ade5
Request Headers - support x-litellm-num-retries + Usage - support usage by model group (#12890)
* feat(litellm_pre_call_utils.py): add num_retries to litellm data for backend call

allow user to pass in num retries via request headers

* test(test_litellm_pre_call_utils.py): add unit test

* docs(request_headers.md): document new request header

* fix(common_daily_activity.py): show spend breakdown by model group

Partial fix for https://github.com/BerriAI/litellm/issues/12887

* feat(new_usage.tsx): new tab switcher for viewing usage by model group vs. received model

Closes https://github.com/BerriAI/litellm/issues/12887
2025-07-22 23:09:36 -07:00
Ishaan Jaff
bf300f8ca7 Revert "Litellm dev 07 21 2025 p1 (#12848)"
This reverts commit e4e10aa4ed.
2025-07-22 18:28:36 -07:00
tanjiro
03e420f91a
Improvements on the Regenerate Key Flow (#12788)
* improve regeneration ux

* toLocaleString

* regenerate key twice in a row

* fix delete key
2025-07-22 07:47:26 -07:00
Krish Dholakia
e4e10aa4ed
Litellm dev 07 21 2025 p1 (#12848)
* fix(main.py): fix async retryer

Fixes https://github.com/BerriAI/litellm/issues/12830

* fix(forward_clientside_headers_by_model_group.py): filter out 'content-type' from forwardable headers

clientside content-type != proxy content type, can cause requests to hang

* test(tests/): update tests
2025-07-21 22:09:39 -07:00
dependabot[bot]
2be16eb493
build(deps): bump form-data from 4.0.0 to 4.0.4 in /ui/litellm-dashboard (#12851)
---
updated-dependencies:
- dependency-name: form-data
  dependency-version: 4.0.4
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-07-21 22:05:38 -07:00
Ishaan Jaff
67edd7c481
fix team edit guardrail (#12823) 2025-07-21 11:44:22 -07:00
Ishaan Jaff
7e2076d8d2 ui new build 2025-07-19 17:40:19 -07:00
Krish Dholakia
ec01ec923b
UI - support adding links to model hub (#12776)
* feat(model_hub_table.tsx): add ability for admin to add links to model hub

allows admin to add model + key request access forms to model hub

makes it easier to request access to specific models

* refactor(ui/): cleanup ui - consistent styling

* fix(useful_links_management.tsx): make tab collapsible and explain purpose

* fix(ui/): fix ui linting errors

* fix: fix linting error
2025-07-19 16:32:02 -07:00
Ishaan Jaff
6239ff05bb ui fix logo for vector stores 2025-07-19 16:19:37 -07:00
Ishaan Jaff
38760e9673 fix msg 2025-07-19 16:19:37 -07:00
Ishaan Jaff
14e0cf0e4c ui new build 2025-07-19 15:24:54 -07:00
Ishaan Jaff
8c258faeaf fix linting 2025-07-19 15:23:32 -07:00
Ishaan Jaff
1ab05cbd3c leftnav 2025-07-19 15:21:00 -07:00
Ishaan Jaff
805fbf55a2
[QA] Disable Logging settings for Keys (#12774)
* fix keyData metadata access

* fix helpers
2025-07-19 15:15:44 -07:00
Ishaan Jaff
93badc72dc ui fix formatNumberWithCommas 2025-07-19 14:42:41 -07:00
Ishaan Jaff
76d461dcae fix add model 2025-07-19 14:32:41 -07:00
Jugal D. Bhatt
b443817a56
[Key Access] Litellm disabled callbacks for UI (#12769)
* add disabled callbacks to ui

* added body

* update edit settings

* add tests
2025-07-19 14:32:05 -07:00
Krish Dholakia
ee066481f8
UI - Support 'batch' model health checks + make 'team-only' model concept clearer (#12770)
* fix(add_model_modes.tsx): add 'batch' mode to ui

* fix(main.py): support health checks on batches + support litellm_credentials on batches

* fix(add_model_tab.tsx): clarify what 'team' on add model means
2025-07-19 14:30:38 -07:00
Ishaan Jaff
05af269425 Revert "ui fix linting"
This reverts commit 85184c7f82.
2025-07-19 12:42:45 -07:00
Ishaan Jaff
5c7e5d4324 Revert "Regenerate Key State Management and Authentication Issues (#12729)"
This reverts commit 663abbe275.
2025-07-19 12:42:20 -07:00
Krish Dholakia
d72b3389a1
Bulk Edit Users on UI (#12763)
* feat(bulk_edit_user.tsx): initial working ui for editing users in bulk on the ui

easier to give access / assign to a default team

* feat(team_endpoints-+-bulk_edit_users.tsx): add bulk adding users to teams

make it easier to add existing users to a default team

* fix(bulk_edit_user.tsx): fix ui linting error

* fix: fix linting error
2025-07-19 11:04:23 -07:00
tanjiro
657ca3b81a
Fix Y-axis labels overlap on Spend per Tag (#12754)
* fix spend per tag bar chart labels

* remove console.log
2025-07-19 09:40:40 -07:00
tanjiro
f8e5dc5034
copy button (#12760) 2025-07-19 09:39:14 -07:00
Ishaan Jaff
d0af0db766 ui new build 2025-07-18 18:47:53 -07:00
Ishaan Jaff
85184c7f82 ui fix linting 2025-07-18 18:42:24 -07:00
Ishaan Jaff
7eca3efc92 Revert "ui fix linting"
This reverts commit 586918dddb.
2025-07-18 18:38:53 -07:00
Ishaan Jaff
02f987d63d Revert "fix linting ui"
This reverts commit 1ff766e738.
2025-07-18 18:38:44 -07:00
Ishaan Jaff
1ff766e738 fix linting ui 2025-07-18 18:36:44 -07:00
Ishaan Jaff
586918dddb ui fix linting 2025-07-18 18:35:32 -07:00
Ishaan Jaff
81eb2fdd30
[Feat] UI Vector Stores - Allow adding Vertex RAG Engine, OpenAI, Azure (#12752)
* fix _pass_through_endpoint_without_required_model

* add get_litellm_managed_vector_store_from_registry

* undo router change

* fix for using router + vector search methods

* add simple helper for _update_request_data_with_litellm_managed_vector_store_registry

* add vector_stores routes

* test_router_avector_store_search_passes_correct_args

* [Feat] UI - Allow clicking into Vector Stores (#12741)

* Add View Vector Store

* add /info for vector store

* fix updated_at

* allow easily testing the KB on litellm

* fix

* rename test

* test_init_vector_store_api_endpoints

* add get_vertex_ai_project

* fixes to vertex transformation for RAG Engine

* fix vectorStoreProviderFields

* Add Vertex Rag engine

* add oai, azure

* fix validate_environment

* fix provider name

* fix tester

* working vertex vector store
2025-07-18 18:25:26 -07:00
Ishaan Jaff
5802a5bbe3
[Feat] LLM API Endpoint - Expose OpenAI Compatible /vector_stores/{vector_store_id}/search endpoint (#12749)
* fix _pass_through_endpoint_without_required_model

* add get_litellm_managed_vector_store_from_registry

* undo router change

* fix for using router + vector search methods

* add simple helper for _update_request_data_with_litellm_managed_vector_store_registry

* add vector_stores routes

* test_router_avector_store_search_passes_correct_args

* [Feat] UI - Allow clicking into Vector Stores (#12741)

* Add View Vector Store

* add /info for vector store

* fix updated_at

* allow easily testing the KB on litellm

* fix

* rename test

* test_init_vector_store_api_endpoints

* test_update_request_data_with_litellm_managed_vector_store_registry
2025-07-18 18:18:53 -07:00
Ishaan Jaff
99e2ea081d
[Feat] UI - Allow clicking into Vector Stores (#12741)
* Add View Vector Store

* add /info for vector store

* fix updated_at
2025-07-18 14:28:57 -07:00
Ishaan Jaff
3051a9c68a
[Bug Fix] QA - Use PG Vector Vector Store with LiteLLM (#12716)
* store in generic litellm params

* handle storing litellm_params_json

* add litellm_params

* update file loc

* fix startup issue

* ui fix litellm_params

* fix typing

* fix adding PG Vector

* use litellm params

* fix transform_search_vector_store_request

* fix transform

* fix URL

* test fix

* test_pg_vector_search_request_construction
2025-07-18 08:41:18 -07:00
tanjiro
663abbe275
Regenerate Key State Management and Authentication Issues (#12729)
* fix bug

When Max Budget, TPM, RPM, Expire Key are set on Regenerate Key, these values are not reflected on the settings page. Refreshing the page is required.

* fix editing settings after key generation
2025-07-18 07:25:01 -07:00
Krish Dholakia
bc2ab84342
Teams - allow setting custom key duration + show many user + service account keys have been created (#12722)
* fix(team_info.tsx): allow setting custom key duration

more flexible than previous pre-set options

* feat(team_info.tsx): show how many user + service account keys have been created within a team
2025-07-17 22:33:59 -07:00
Jugal D. Bhatt
f4a94ec911
Added name change (#12702) 2025-07-17 18:35:01 -07:00
Jugal D. Bhatt
842af61a05
[MCP Gateway] add fix to update object permission on update/delete key/team (#12701)
* add fix to update object permission on update/delete

* fix edit team page dropdown
2025-07-17 18:34:35 -07:00
Ishaan Jaff
e5f0a8477b
[Feat] New Vector Store - PG Vector (#12667)
* add PGVectorStoreConfig

* add PGVectorStoreConfig

* test_environment_variable_support

* fix code QA check

* rename test

* add PG vector img

* allow adding vector stores

* add pg vector

* add vector store

* TestPGVectorStoreConfig

* TestPGVectorStoreConfig
2025-07-16 18:17:05 -07:00
Ishaan Jaff
538339e1a8
[Feat] UI - Add end_user filter on UI (#12663)
* add end_user filter on Logs

* add end user filter
2025-07-16 15:20:31 -07:00
Krrish Dholakia
0fb7c01382 fix(make_model_public_form.tsx): make distinction clearer 2025-07-16 10:58:23 -07:00
tanjiro
720b94fd2b
Add Copy-on-Click for IDs (#12615)
* added the mcp_connect copy button to key_info_view

* user id copy button

* copy button on session view

* model id copy

* more copy buttons

* icon size
2025-07-15 11:25:57 -07:00
tanjiro
c0f1b8119e
Wildcard model filter (#12597)
* filter by wildcard models

* merge conflict
2025-07-14 20:01:10 -07:00
Ishaan Jaff
8bcdb07fcd ui new build 2025-07-12 16:44:13 -07:00
Ishaan Jaff
50b106be11
[MCP Gateway] Ensure we use the same param for specifying groups (#12561)
* just use 1 param for mcp groups

* fix just use 1 param for access groups

* test_get_tools_from_mcp_servers

* docs access groups

* group MCPs

* test fix

* fix screenshots on docs

* TestMCPAccessGroupsE2E

* update img

* fix MCP connect
2025-07-12 16:41:58 -07:00
Ishaan Jaff
00ab400500
UI - v1.74.3-stable QA fixes (#12559)
* fix chat ui

* fixes for types

* ui - fix back button on MCP

* mcp - show existing groups when creating new mcps

* fix design

* fix color scheme

* fix linting

* fixes for mapped tests
2025-07-12 15:31:39 -07:00
Krish Dholakia
d8ae044ec5
UI - Model Hub - refactor 'Make Public' to have a select + confirm form (#12555)
* fix(model_hub_table.tsx): fix null link

* fix(model_hub_table.tsx): add tooltip on disabled make public

tell user how to enable button

* feat(model_hub_table.tsx): make Model Hub OSS

allow more teams to share available models via litellm

* fix(model_hub_table_columns.tsx): make table view only model hub view, rename 'model' column to 'public model name', make model hub url copyable

* fix(page.tsx): fix logo re-rendering

* fix(public_model_hub.tsx): fix theme

* style(public_model_hub.tsx): move filters into same card as model table

filters are for table

* fix(page.tsx): fix ui linting error

* refactor(model_hub_table.tsx): refactor public model selection to inside the 'make public' button - modal

similar flow to adding guardrails

consistent flow for doing stuff on the proxy

* style(ui/): make 'make public' modal wider, to have all filters on same horizontal axis

* style(model_hub_table.tsx): have already public models be pre-selected

* fix(model_hub_table.tsx): ensure only admin can make models public via UI

* fix: fix linting errors

* fix(model_hub_table.tsx): make model hub purpose clearer

* fix(model_hub_table_columns.tsx): fix linting error
2025-07-12 14:12:52 -07:00