290e2528cd
Schedule budget resets at expectable times ( #10331 ) ( #10333 )
...
* Schedule budget resets at expectable times (#10331 )
* Enhance budget reset functionality with timezone support and standardized reset times
- Added `get_next_standardized_reset_time` function to calculate budget reset times based on specified durations and timezones.
- Introduced `timezone_utils.py` to manage timezone retrieval and budget reset time calculations.
- Updated budget reset logic in `reset_budget_job.py`, `internal_user_endpoints.py`, `key_management_endpoints.py`, and `team_endpoints.py` to utilize the new timezone-aware reset time calculations.
- Added unit tests for the new reset time functionality in `test_duration_parser.py`.
- Updated `.gitignore` to include `test.py` and made minor formatting adjustments in `docker-compose.yml` for consistency.
* Fixed linting
* Fix for mypy
* Fixed testcase for reset
* fix(duration_parser.py): move off zoneinfo - doesn't work with python 3.8
* test: update test
* refactor: improve budget reset time calculation and update related tests for accuracy
* clean up imports in team_endpoints.py
* test: update budget remaining hours assertions to reflect new reset time logic
* build(model_prices_and_context_window.json): update model
---------
Co-authored-by: Prathamesh Saraf <pratamesh1867@gmail.com >
2025-04-29 20:59:44 -07:00
d783190e04
Update fireworks ai pricing ( #10425 )
...
* build(model_prices_and_context_window.json): add fireworks ai new 0-4b pricing tier
* build(model_prices_and_context_window.json): add more fireworks ai models
* test: update testing
* test: testing updates
* test: update test
* test: update test
2025-04-29 20:58:05 -07:00
839878f4f5
Support x-litellm-api-key header param + allow key at max budget to call non-llm api endpoints ( #10392 )
...
* fix(user_api_key_auth.py): fix passing `x-litellm-api-key` to user api key auth
Support using this when given, or bearer token when given
Fixes issue with auth on vertex passthrough
* test(test_user_api_key_auth.py): use new fastapi.security check
* fix(user_api_key_auth.py): allow key at budget, to still call non-llm api endpoints
Fixes issue where key at budget, couldn't call `/key/info`
2025-04-29 18:57:57 -07:00
70accb754e
fix(langsmith.py): respect langsmith batch size param ( #10411 )
...
* fix(langsmith.py): respect langsmith batch size param
* build(model_prices_and_context_window.json): add missing tgai models
Fixes https://github.com/BerriAI/litellm/issues/8921
Fixes https://github.com/BerriAI/litellm/issues/8278
2025-04-29 18:55:22 -07:00
cd27185e2c
test: override flaky test
2025-04-29 18:54:49 -07:00
e06e7078da
[New model] Add openai/computer-use-preview cost tracking / pricing ( #10422 )
...
* add computer-use-preview
* fix computer-use-preview
2025-04-29 17:49:11 -07:00
f1d6ac4af6
fix google studio url ( #10095 )
2025-04-29 17:34:58 -07:00
25c726ed61
Revert "build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-…" ( #10421 )
...
This reverts commit a01cd87f4d
2025-04-29 17:33:47 -07:00
f30871ef13
[Feat] Add support for using Bedrock Knowledge Bases with LiteLLM /chat/completions requests ( #10413 )
...
* add make_bedrock_kb_retrieve_request
* working bedrock KB hook
* working bedrock KB hook
* test_openai_with_knowledge_base_mock_openai
* fix linting
* fix BedrockKnowledgeBaseHook
* docs using bedrock kb with litellm
* docs kb with litellm
* fix bedrock kb test
* DynamicPromptManagementParamLiteral
* fix _should_run_prompt_management_hooks_without_prompt_id
* test_init_custom_logger_compatible_class_as_callback
2025-04-29 17:29:02 -07:00
36264d4764
[Feat Security] - Allow blocking web crawlers ( #10420 )
...
* security add robots.txt settings to security
* block web crawlers
* test_enterprise_routes.py
* docs proxy enterprise
2025-04-29 17:28:08 -07:00
00605e3611
docs: Improve documentation of phoenix logging ( #10416 )
2025-04-29 17:24:47 -07:00
b482618456
docs: Fix link formatting in GitHub PR template ( #10417 )
2025-04-29 17:23:53 -07:00
a01cd87f4d
build(deps): bump axios, @docusaurus/core, @docusaurus/plugin-google-gtag, @docusaurus/plugin-ideal-image and @docusaurus/preset-classic ( #10419 )
...
Removes [axios](https://github.com/axios/axios ). It's no longer used after updating ancestor dependencies [axios](https://github.com/axios/axios ), [@docusaurus/core](https://github.com/facebook/docusaurus/tree/HEAD/packages/docusaurus ), [@docusaurus/plugin-google-gtag](https://github.com/facebook/docusaurus/tree/HEAD/packages/docusaurus-plugin-google-gtag ), [@docusaurus/plugin-ideal-image](https://github.com/facebook/docusaurus/tree/HEAD/packages/docusaurus-plugin-ideal-image ) and [@docusaurus/preset-classic](https://github.com/facebook/docusaurus/tree/HEAD/packages/docusaurus-preset-classic ). These dependencies need to be updated together.
Removes `axios`
Updates `@docusaurus/core` from 2.4.1 to 3.7.0
- [Release notes](https://github.com/facebook/docusaurus/releases )
- [Changelog](https://github.com/facebook/docusaurus/blob/main/CHANGELOG.md )
- [Commits](https://github.com/facebook/docusaurus/commits/v3.7.0/packages/docusaurus )
Updates `@docusaurus/plugin-google-gtag` from 2.4.3 to 3.7.0
- [Release notes](https://github.com/facebook/docusaurus/releases )
- [Changelog](https://github.com/facebook/docusaurus/blob/main/CHANGELOG.md )
- [Commits](https://github.com/facebook/docusaurus/commits/v3.7.0/packages/docusaurus-plugin-google-gtag )
Updates `@docusaurus/plugin-ideal-image` from 2.4.3 to 3.7.0
- [Release notes](https://github.com/facebook/docusaurus/releases )
- [Changelog](https://github.com/facebook/docusaurus/blob/main/CHANGELOG.md )
- [Commits](https://github.com/facebook/docusaurus/commits/v3.7.0/packages/docusaurus-plugin-ideal-image )
Updates `@docusaurus/preset-classic` from 2.4.1 to 3.7.0
- [Release notes](https://github.com/facebook/docusaurus/releases )
- [Changelog](https://github.com/facebook/docusaurus/blob/main/CHANGELOG.md )
- [Commits](https://github.com/facebook/docusaurus/commits/v3.7.0/packages/docusaurus-preset-classic )
---
updated-dependencies:
- dependency-name: axios
dependency-version:
dependency-type: indirect
- dependency-name: "@docusaurus/core"
dependency-version: 3.7.0
dependency-type: direct:production
- dependency-name: "@docusaurus/plugin-google-gtag"
dependency-version: 3.7.0
dependency-type: direct:production
- dependency-name: "@docusaurus/plugin-ideal-image"
dependency-version: 3.7.0
dependency-type: direct:production
- dependency-name: "@docusaurus/preset-classic"
dependency-version: 3.7.0
dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-04-29 17:23:07 -07:00
a69fa1dc1e
[Bug Fix] Responses API - fix for handling multiturn responses API sessions ( #10415 )
...
* fix for handling previous_response_id id sessions on responses API
* fix test_decode_previous_response_id_to_original_previous_response_id
2025-04-29 17:22:47 -07:00
08ba839c31
bump: version 1.67.4 → 1.67.5
2025-04-29 16:20:31 -07:00
37bdf7c042
test: add more debug logs
2025-04-29 15:40:18 -07:00
1ef17c2f0e
fix test_openai_moderation_error_raising
2025-04-29 07:26:41 -07:00
ae7eecaa40
test: mark flaky test
2025-04-29 06:40:26 -07:00
f984089b01
[Reliability fix] Redis transaction buffer - ensure all redis queues are periodically flushed ( #10393 )
...
* test_e2e_size_of_redis_buffer
* fix store_in_memory_spend_updates_in_redis
* _commit_spend_updates_to_db_with_redis
* daily_tag_spend_update_transactions
* pip install fakeredis==2.28.1
2025-04-28 21:36:54 -07:00
72de453cc0
fix gemini/gemini-2.5-pro-exp-03-25
2025-04-28 20:24:40 -07:00
34cdefbb77
[Feat] Add logging callback support for /moderations API ( #10390 )
...
* add OpenAIModerationResponse as a type
* Add typing for litellm.moderation response obj
* Add typing for litellm.moderation response obj
* test_moderations_api_logging
* add assertions for logged slp object
* test_moderations_api_logging
* refactor moderations api usage
* Revert "test_moderations_api_logging"
This reverts commit 5a9001f04c592b063f016d2bb854416255ec6cdf.
* Revert "refactor moderations api usage"
This reverts commit b076d3174ca14251ee3fc28bd4744e25685c1e5f.
* test_moderations_api_logging
2025-04-28 20:24:17 -07:00
25213f6087
docs: fix docs
2025-04-28 15:36:56 -07:00
a38e2f052e
docs: fix docs
2025-04-28 15:36:31 -07:00
bf9382a182
Handle more gemini tool calling edge cases + support bedrock 'stable-image-core' ( #10351 )
...
* test(test_amazing_vertex_completion.py): try to repro https://github.com/BerriAI/litellm/issues/10319
* fix(common_utils.py): handle edge case on tools
Fixes https://github.com/BerriAI/litellm/issues/10319
* test: add unit testing for infinite loops
* fix(amazon_stability3_transformation.py): support 'stable-image-core' transformation
Fixes https://github.com/BerriAI/litellm/issues/8488
* test: add unit testing for stable image core model
* test: update test
2025-04-28 14:22:29 -07:00
a5ef8a9556
update release note with imgs
2025-04-26 20:14:39 -07:00
52ceeaeb40
fix code quality check
2025-04-26 19:37:34 -07:00
2be334eeb1
fix build from pip test
2025-04-26 19:36:47 -07:00
c2f7d7b185
fix linting errors
2025-04-26 19:34:37 -07:00
4153b8975c
fix types/responses/main.py
2025-04-26 19:18:26 -07:00
c8688ee85c
fix linting _ENTERPRISE_ResponsesSessionHandler
2025-04-26 19:17:20 -07:00
15ab172cf5
fix def of ChatCompletionSession
2025-04-26 19:16:20 -07:00
1e0ee22445
fix build from pip tests
2025-04-26 19:05:28 -07:00
ab4523c080
docs(index.md): cleanup
2025-04-26 19:00:56 -07:00
1390ae8e18
docs(index.md): cleanup doc
2025-04-26 18:54:08 -07:00
6f3c158266
[QA] Allow managing sessions with litellm_session_id ( #10348 )
...
* allow dynamically setting litellm_session_id
* allow dynamically setting litellm_session_id
2025-04-26 18:52:50 -07:00
fcaac91724
ui new build
2025-04-26 18:25:50 -07:00
2ab00bd12c
Litellm UI improvements 04 26 2025 p1 ( #10346 )
...
* fix(provider_info_helpers.tsx): fix together ai provider name
* fix(user_edit_view.tsx): all admin to edit user's personal models
* fix(model_dashboard.tsx): fix model filtering by team id check
* fix(proxy_server.py): support returning available models for a user on `/model_group/info`
Fixes issue where personal key with 'all team models' would see all proxy models (not just the ones user can call)
* test(test_models.py): add unit test for model group info check on personal key
2025-04-26 18:24:49 -07:00
42928601b4
bump litellm-proxy-extras
2025-04-26 18:11:06 -07:00
d6103c3962
ui fix linting
2025-04-26 17:44:09 -07:00
c2480db73d
[Bug Fix] UI QA - Fix wildcard model test connection not working ( #10347 )
...
* fix setFieldsValue for wildcard
* fix async_completion_with_fallbacks
* fix ahealth_check_wildcard_models
2025-04-26 17:42:06 -07:00
31313dd489
Fix - support azure dall e custom pricing ( #10339 )
...
* fix(cost_calculator.py): support custom pricing for image gen
Allow user to set custom pricing on azure image gen models
* test(test_cost_calculator.py): add unit test
* test(test_litellm_logging.py): add more unit testing
* fix(litellm_logging.py): fix ruff check
2025-04-26 17:16:03 -07:00
f30479557e
fix remove Column Selector, it seems to not be working
2025-04-26 16:36:14 -07:00
f2c9406980
fix /sso/callback ( #10345 )
2025-04-26 16:27:40 -07:00
9ab9744fac
ui - fix infinite scroll on test key page ( #10343 )
2025-04-26 16:18:54 -07:00
f694878155
fix SSO ( #10344 )
2025-04-26 16:17:38 -07:00
58878aa0bb
[UI] Fixes for sessions on UI - ensure errors have a session and use 1 session for test key ( #10342 )
...
* ui fix use same trace id on test key page
* _get_session_id_for_spend_log
* fix linting
2025-04-26 16:02:58 -07:00
faf54e3f29
fixes for EE image
2025-04-26 15:43:21 -07:00
fd3603d4e8
deploy - add build-and-push-image-ee
2025-04-26 14:40:20 -07:00
dcfa26c428
docs fix index stable release
2025-04-26 14:31:24 -07:00
9614d5ba69
docs fix stable release
2025-04-26 14:23:09 -07:00
Krish Dholakia