tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-06 02:23:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
22,106 Commits 2,072 Branches 1,425 Tags
0be7e7d0888a0b7ee5e10d1dbc8dfc0fda992155
Commit Graph
22106 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan Jaff 0be7e7d088 Revert "Support passing prompt_label to langfuse (#11018)" 
This reverts commit 2b50b43ae2.
 2025-05-22 14:11:19 -07:00
Ishaan Jaff 89daa1dbad docs add claude-4 models 2025-05-22 13:41:09 -07:00
Ishaan JaffandGitHub 197c608078 [Feat] Add claude-4 model family (#11060) 
* add new claude-sonnet-4-2025051

* feat: add bedrock claude-4 models

* add bedrock claude-4 models

* add vertx_ai/claude-sonnet-4

* fix provider=bedrock_converse

* feat: ensure thinking is supported for claude-4 model family
v1.70.2.dev5 		2025-05-22 13:33:54 -07:00
Ishaan Jaff 2c90ca0189 docs fix example 2025-05-22 09:33:22 -07:00
Ishaan Jaff d95c3a16f3 docs fix ad hoc recognizer 2025-05-22 08:55:07 -07:00
Ishaan Jaff d595c4ef2d bump: version 1.70.3 → 1.70.4 2025-05-22 07:32:35 -07:00
tanjiroandGitHub 1c652b67b6 Model filter on logs (#11048) 
* add model filter

* remove calling all models
 2025-05-22 07:31:43 -07:00
Ishaan JaffandGitHub dd4a65b83a Feat: add MCP to Responses API and bump openai python sdk (#11029) 
* feat: add MCP to responses API

* feat: bump openai version to 1.75.0

* docs MCP + responses API

* fixes: type checking

* fixes: type checking

* build: use latest openai 1.81.0

* fix: linting error

* fix: linting error

* fix: test

* fix: linting errors

* fix: test

* fix: test

* fix: linting

* Revert "fix: linting"

This reverts commit ebb19ff8cb1f8fcc3e224390e351676daccb33de.

* fix: linting
 2025-05-22 07:24:10 -07:00
tanjiroandGitHub bfb04d3e75 added cloding tags for </TabGroup> </Col> </Grid> + indentation changes (#11046) 2025-05-22 07:23:26 -07:00
Krish DholakiaandGitHub 2b50b43ae2 Support passing prompt_label to langfuse (#11018) 
* fix: add prompt label support to prompt management hook

* feat: support 'prompt_label' parameter for langfuse prompt management

Closes https://github.com/BerriAI/litellm/discussions/9003#discussioncomment-13221555

* fix(litellm_logging.py): deep copy optional params to avoid mutation while logging

* fix(log-consistent-optional-param-values-across-providers): ensures params can be used for finetuning from providers

* fix: fix linting error

* test: update test

* test: update langfuse tests

* fix(litellm_logging.py): avoid deepcopying optional params

might contain thread object
 2025-05-21 22:27:36 -07:00
Krrish Dholakia cd496fee2e fix: fix linting error 2025-05-21 22:04:41 -07:00
jmorenoc-oandGitHub 1cd2595006 Fixes the InvitationLink Prisma find_many query (#11031) 
Related: https://github.com/BerriAI/litellm/commit/3b6c6d05dd8f8bcd83f776cdc1c8fc64d3d85d13#r157675103

We should use "order", according to the prisma python docs https://prisma-client-py.readthedocs.io/en/stable/reference/limitations/#order-argument 

Also we are using "order" in other files of the project: 
https://github.com/search?q=repo%3ABerriAI%2Flitellm%20order%3D%7B&type=code
 2025-05-21 21:42:57 -07:00
Krish DholakiaandGitHub 58f958f30a Litellm dev 05 21 2025 p2 (#11039) 
* feat: initial commit adding managed file support to fine tuning endpoints

* feat(fine_tuning/endpoints.py): working call to openai finetuning route

Uses litellm managed files for finetuning api support

* feat(fine-tuning/main.py): refactor to use LiteLLMFineTuningJob pydantic object

includes 'hidden_params'

* fix: initial commit adding unified finetuning id support

return a unified finetuning id we can use to understand which deployment to route the ft request to

* test: fix test

* feat(managed_files.py): return unified finetuning job id on create finetuning job

enables retrieve, delete to work with litellm managed files

* test: update test

* fix: fix linting error

* fix: fix ruff linting error

* test: fix check
 2025-05-21 21:40:53 -07:00
Krrish Dholakia 546a508c8c test: mark flaky test 2025-05-21 21:36:46 -07:00
bepotpGitHubTommy PLANEL
 		e487f1e17d feat: add Databricks Llama 4 Maverick model cost (#11008) 
Co-authored-by: Tommy PLANEL <tommy.planel2@ubisoft.com>
 2025-05-21 20:59:18 -07:00
Jay GowdyandGitHub 85d577c8e6 Fix: Handle dict objects in Anthropic streaming response (#11032) 
* fix: handle dict objects in Anthropic streaming response

Fix issue where dictionary objects in Anthropic streaming responses
were not properly converted to SSE format strings before being yielded,
causing AttributeError: 'dict' object has no attribute 'encode'

* fix: refactor Anthropic streaming response handling

- Added STREAM_SSE_DATA_PREFIX constant in constants.py
- Created return_anthropic_chunk helper function for better maintainability
- Using safe_dumps from safe_json_dumps.py for improved JSON serialization
- Added unit test for dictionary object handling in streaming response

* fix: correct patch path in anthropic_endpoints test
 2025-05-21 20:58:11 -07:00
tanjiroandGitHub 0cde73ffb7 Spend rounded to 4 for Organizations and Users page (#11023) 
* spend rounded to 4

* fixed for organization and users table
 2025-05-21 20:41:54 -07:00
Jugal D. BhattandGitHub 03cda24681 Verbose error on admin add (#10978) 2025-05-21 19:30:18 -07:00
Tyler WagnerGitHubwagnerjt
 		b6508731dc fix(ui): call tool when no arguments needed (#11012) 
Co-authored-by: wagnerjt <wagnerjt@github.com>
 2025-05-21 14:06:22 -07:00
fzowlandGitHub 73727abd84 Updating the available VoyageAI models in the docs (#11003) 
* Refresh VoyageAI models and prices and context

* Refresh VoyageAI models and prices and context

* Refresh VoyageAI models and prices and context

* Updating the available VoyageAI models in the docs

* Updating the available VoyageAI models in the docs
 2025-05-21 14:04:43 -07:00
Ishaan JaffandGitHub e5d278c454 [Feat] Add Image Edits Support to LiteLLM (#11020) 
* refactor: use 1 file for image methods

* refactor: use 1 file for image methods

* feat: add stubs for image edits

* fix: types for image edits

* feat: add async image edits

* feat: add base config for image edits

* feat: add basic structure for image edits

* feat: add ImageEditRequestUtils

* feat: complete instrumentation of image edits

* tes: test_openai_image_edit_litellm_sdk

* tets: test_openai_image_edit_litellm_sdk

* feat: get_provider_image_edit_config

* feat: add OpenAIImageEditConfig

* feat: working image edits

* fixes: working image edits

* fix: code qa

* fix: using image edits

* fix: linting errors
 2025-05-21 14:03:09 -07:00
Ishaan JaffandGitHub 089e13b452 feat: add xai/grok-3 pricing (#11028) 2025-05-21 14:00:55 -07:00
tanjiroandGitHub 9b0e1bb16c put organization and team buttons at the top (#10948) 2025-05-21 12:59:14 -07:00
Krrish Dholakia e156636b8e fix(streaming_handler.py): fix check when response id already set 2025-05-21 12:30:28 -07:00
Krrish Dholakia 647c473971 fix: fix linting error 2025-05-21 12:22:40 -07:00
tanjiroandGitHub de5ec3fd9a spend rounded to 4 (#11013) 2025-05-21 09:55:44 -07:00
Matthias DittrichandGitHub 3322b282f8 Ollama wildcard support (#10982) 
* Add Ollama wildcard support

* Add Ollama-chatas well.

* Fix missing methods.

* Improve logs a bit.

* Add tests

* Add tests
 2025-05-21 08:47:01 -07:00
Krrish Dholakia 2ced944bbe fix(internal_user_endpoints.py): fix check 2025-05-21 08:37:31 -07:00
Søren MathiasenandGitHub aa11ea3a9f support vertex_ai global endpoints for chat (#10658) 2025-05-21 07:58:36 -07:00
daarko10andGitHub 00a789440d Improve response_id propagation logic and add tests for valid/empty ID handling in streaming. (#11006) 2025-05-21 07:27:17 -07:00
Krrish Dholakia 95fd281a7d bump: version 1.70.2 → 1.70.3 2025-05-20 23:10:44 -07:00
Krish DholakiaandGitHub 4bd64c872a fix(internal_user_endpoints.py): allow resetting spend/max budget on … (#10993) 
* fix(internal_user_endpoints.py): allow resetting spend/max budget on user update

Fixes https://github.com/BerriAI/litellm/issues/10495

* fix(internal_user_endpoints.py): correctly return set spend for user on /user/new

* fix(auth_checks.py): check redis for key object before checking in-memory

allows for quicker updates

* feat(internal_user_endpoints.py): update cache object when user is updated + check redis on user values being updated

* fix(auth_checks.py): use redis cache when user updated

* fix: set default value of 'expires' to None
 2025-05-20 23:08:26 -07:00
Ishaan JaffGitHubCopilot
 		bf97d994b5 fix: default role for JWT authentication (#10995) 
* fix: get_user_object

* test: test_default_internal_user_params_with_get_user_object

* Update litellm/proxy/auth/auth_checks.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-05-20 22:58:41 -07:00
Ishaan JaffandGitHub 14321a2708 [Feat] Prometheus - Track route on proxy_* metrics (#10992) 
* fix: trace route on prometheus metrics

* fix: show route on prometheus metrics for total fails

* test: trace route on metrics

* fix: tests for route in prom metrics

* test: fix test metrics

* test: fix test_proxy_failure_metrics
 2025-05-20 22:55:55 -07:00
Krish DholakiaandGitHub aeb9ea0a7f Litellm add new gemini models (#10998) 
* build(model_prices_and_context_window.json): add new gemini image gen model

* build(model_prices_and_context_window.json): add more gemini models
 2025-05-20 22:54:15 -07:00
Krish DholakiaandGitHub f0c8254665 Add new gemini preview models + Fix cohere v2 embedding 'embedding_types' param mapping (#10991) 
* build(model_prices_and_context_window.json): add new gemini preview models

Fixes https://github.com/BerriAI/litellm/issues/10985

* fix(cohere/embed): Fix encoding format <-> embedding types param mapping

Fixes https://github.com/BerriAI/litellm/issues/10939

* fix(aim.py): fix syntax error
 2025-05-20 22:39:31 -07:00
Jugal D. BhattandGitHub 195aec5551 added support to credential delete to support slashes in the curl (#10987) 
* added support to credential delete to support slashes in the curl

* add support for get and update too
 2025-05-20 19:08:48 -07:00
Ishaan JaffandGitHub 3a6802fef1 [Feat] - Add Support for Showing Passthrough endpoint Error Logs on LiteLLM UI (#10990) 
* fix: add error logging for passthrough endpoints

* feat: add error logging for passthrough endpoints

* fix: post_call_failure_hook track errors on pt

* fix: use constant for MAXIMUM_TRACEBACK_LINES_TO_LOG

* docs MAXIMUM_TRACEBACK_LINES_TO_LOG

* test: ensure failure callback triggered

* fix: move _init_kwargs_for_pass_through_endpoint
 2025-05-20 18:29:39 -07:00
slytechnicalandGitHub 98e9db340c [Feature] Add supports_computer_use to the model list (#10881) 
* Add support for supports_computer_use in model info

* Corrected list of supports_computer_use models

* Further fix computer use compatible claude models, fix existing test that predated supports_computer_use in the model list

* Move computer use test case into existing test_utils file

* Moved tests in to test_utils.py
 2025-05-20 17:07:43 -07:00
Krrish Dholakia 058503ea11 test: skip test - model EOL v1.70.2-nightly 2025-05-20 15:57:12 -07:00
Krrish Dholakia b122ead5b3 test: update tests 2025-05-20 13:08:47 -07:00
Krrish Dholakia a676f69cab docs: cleanup v1.70.1.dev2 2025-05-19 22:10:04 -07:00
Ishaan JaffandGitHub af73a8e3a9 fix: vertex show clear exception on failed refresh (#10969) 
* fix: vertex show clear exception on failed refresh

* fix: show clear debug log
v1.67.0-stable.patch2 		2025-05-19 21:51:15 -07:00
Ishaan JaffGitHubCopilot
 		7d8ed6f362 [Fix] List Guardrails - Show config.yaml guardrails on litellm ui (#10959) 
* fix: listing guardrails defined on litellm config

* fix: list guardrails on litellm config

* fix: list guardrails on litellm config

* test: list guardrails on litellm config

* fix: linting

* Update litellm/proxy/guardrails/guardrail_endpoints.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* fix: GuardrailInfoLiteLLMParamsResponse

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-05-19 21:25:23 -07:00
Krrish Dholakia d099092bc1 build: ui/ 
new build
 2025-05-19 21:23:45 -07:00
Jugal D. BhattandGitHub c6260fe31a add cla to docs (#10963) 
* add cla to docs

* cla docs clarity
 2025-05-19 21:23:22 -07:00
Krrish Dholakia b486849bc2 build(ui/): new ui build 2025-05-19 21:22:55 -07:00
Krrish Dholakia 1857f5d264 test: update test 2025-05-19 21:21:44 -07:00
Krrish Dholakia 584660b3cd bump: version 1.70.1 → 1.70.2 2025-05-19 21:03:33 -07:00
Krish DholakiaandGitHub d282babd3e Validate migrating keys to teams + Fix mistral image url on async translation (#10966) 
* feat(key_management_endpoints.py): add validation checks for migrating key to team

Ensures requests with migrated key can actually succeed

Prevent migrated keys from failing in prod due to team missing required permissions

* fix(mistral/): fix image url handling for mistral on async call

* fix(key_management_endpoints.py): improve check for running team validation on key update
 2025-05-19 21:01:53 -07:00