Commit Graph
21267 Commits
Author SHA1 Message Date
Krrish Dholakia b5851769fc fix: fix import 2025-04-04 20:26:11 -07:00
Krrish Dholakia 6395bd8d65 test: mark flaky test 2025-04-04 20:25:05 -07:00
Krish DholakiaandGitHub c555c15ad7 fix(router.py): support reusable credentials via passthrough router (#9758)
* fix(router.py): support reusable credentials via passthrough router

enables reusable vertex credentials to be used in passthrough

* test: fix test

* test(test_router_adding_deployments.py): add unit testing
2025-04-04 18:40:14 -07:00
Ishaan JaffandGitHub 8d76da03fe Merge pull request #9759 from BerriAI/litellm_reliability_fix_db_txs
[Reliability] v2 DB Deadlock Reduction Architecture – Add Max Size for In-Memory Queue + Backpressure Mechanism
2025-04-04 17:12:20 -07:00
Ishaan Jaff 150e77cd7d Merge branch 'main' into litellm_reliability_fix_db_txs 2025-04-04 16:46:46 -07:00
Ishaan Jaff 5c2bc796b1 test fix test_hf_chat_template 2025-04-04 16:45:20 -07:00
Krish DholakiaandGitHub e1f7bcb47d Fix VertexAI Credential Caching issue (#9756)
* refactor(vertex_llm_base.py): Prevent credential misrouting for projects

Fixes https://github.com/BerriAI/litellm/issues/7904

* fix: passing unit tests

* fix(vertex_llm_base.py): common auth logic across sync + async vertex ai calls

prevents credential caching issue across both flows

* test: fix test

* fix(vertex_llm_base.py): handle project id in default cause

* fix(factory.py): don't pass cache control if not set

bedrock invoke does not support this

* test: fix test

* fix(vertex_llm_base.py): add .exception message in load_auth

* fix: fix ruff error
2025-04-04 16:38:08 -07:00
Ishaan Jaff decb6649ec test_queue_flush_limit 2025-04-04 16:29:06 -07:00
Ishaan Jaff e77a178a37 test_queue_size_reduction_with_large_volume 2025-04-04 16:21:29 -07:00
Ishaan Jaff dc063fdfec test_queue_size_reduction_with_large_volume 2025-04-04 15:59:35 -07:00
Ishaan Jaff 5bed0b7557 aggregated values 2025-04-04 15:55:14 -07:00
Ishaan Jaff eb48cbdec6 aggregate_queue_updates 2025-04-04 15:54:07 -07:00
Ishaan JaffandGitHub cdd351a03b Merge pull request #9745 from BerriAI/litellm_sso_fixes_dev
[Feat] Allow assigning SSO users to teams on MSFT SSO
2025-04-04 15:40:19 -07:00
Ishaan Jaff 888446256c fix vertex failing test 2025-04-04 15:37:48 -07:00
Ishaan Jaff 93068cb142 flush_all_updates_from_in_memory_queue 2025-04-04 15:34:56 -07:00
Ishaan Jaff 065477abb4 add _get_aggregated_spend_update_queue_item 2025-04-04 15:32:27 -07:00
Ishaan Jaff 9abaefea62 add logic for max size in memory queue 2025-04-04 15:31:40 -07:00
Ishaan Jaff 363fb0c46f add MAX_SIZE_IN_MEMORY_QUEUE 2025-04-04 15:31:09 -07:00
Ishaan Jaff 3374c54ba2 add MAX_SIZE_IN_MEMORY_QUEUE constant 2025-04-04 15:30:53 -07:00
Ishaan Jaff 12b3923579 update circle ci requirements 2025-04-04 14:45:14 -07:00
Ishaan Jaff cba1dacc7d ui new build 2025-04-04 14:39:55 -07:00
Krrish Dholakia ad90871ad6 fix(factory.py): don't pass cache control if not set
bedrock invoke does not support this
2025-04-04 12:37:34 -07:00
Ishaan JaffandGitHub e67d16d5bd Merge pull request #9748 from BerriAI/litellm_ui_allow_testing_image_endpoints
[Feat] UI - Test Key v2 page - allow testing image endpoints + polish the page
2025-04-03 22:39:45 -07:00
Ishaan Jaff c8468b71c8 fix linting ui 2025-04-03 22:32:56 -07:00
Ishaan Jaff f6c2b86903 fix typo 2025-04-03 22:21:11 -07:00
Adrian LyjakandGitHub d640bc0a00 fix #8425, passthrough kwargs during acompletion, and unwrap extra_body for openrouter (#9747) 2025-04-03 22:19:40 -07:00
Ishaan Jaff 0745f306c7 test_microsoft_sso_handler_with_empty_response 2025-04-03 22:17:06 -07:00
Ishaan Jaff 984114adf0 fix sso callback 2025-04-03 22:13:46 -07:00
Krrish Dholakia bdad9961e3 docs: cleanup 2025-04-03 22:12:51 -07:00
Krrish Dholakia abea69352a docs(document_understanding.md): Fix https://github.com/BerriAI/litellm/issues/9704 2025-04-03 22:12:31 -07:00
Ishaan Jaff d55d37ad99 ui new chat ui endpoints 2025-04-03 22:11:04 -07:00
Ishaan Jaff e91dc1e00f refactor chat playground 2025-04-03 21:57:05 -07:00
Ishaan Jaff 353c882574 clean up endpoint selector 2025-04-03 21:33:39 -07:00
Ishaan Jaff 72d7b26811 fix allow selecting endpoint on test key page 2025-04-03 21:00:42 -07:00
Ishaan Jaff f1bc99a137 MSFT make it easier for using group ids with MSFT v1.65.3.dev5 2025-04-03 20:43:22 -07:00
Albert ÖrwallandGitHub bd5a8d582b Fix prompt caching for Anthropic tool calls (#9706)
* Add prompt cache support to Anhtropic tool calls

* Fix linting issue and add test
2025-04-03 20:19:21 -07:00
Ishaan Jaff add24d5999 debug show SSO callback result 2025-04-03 20:06:21 -07:00
Ishaan Jaff 747894864c use litellm mapping 2025-04-03 20:05:11 -07:00
Krish DholakiaandGitHub cb4a9d1365 UI Improvements + Fixes - remove 'default key' on user signup + fix showing user models available for personal key creation (#9741)
* fix(create_user_button.tsx): don't auto create key on user signup

prevents unknown key from being created whenever user signs up

* fix(top_key_view.tsx): show key hash on hover for new usage tab

* fix(create_key_button.tsx): fix showing user models they have access to during personal key creatio
2025-04-03 20:00:45 -07:00
Ishaan Jaff b361329e07 use 1 file for fetch model options 2025-04-03 19:27:44 -07:00
Ishaan Jaff 6ffe3f1e46 working image generation on chat ui 2025-04-03 14:43:56 -07:00
Ishaan Jaff e44318c605 refactor to have 1 folder for llm api calls 2025-04-03 14:32:20 -07:00
Ishaan Jaff ef6bf02ac4 test_nova_optional_params_tool_choice v1.65.3-nightly 2025-04-03 12:27:21 -07:00
sajdaandGitHub 4a4328b5bb fix:Gemini Flash 2.0 implementation is not returning the logprobs (#9713)
* fix:Gemini Flash 2.0 implementation is not returning the logprobs

* fix: linting error by adding a helper method called _process_candidates
2025-04-03 11:53:41 -07:00
Krish DholakiaandGitHub 6dda1ba6dd LiteLLM Minor Fixes & Improvements (04/02/2025) (#9725)
* Add date picker to usage tab + Add reasoning_content token tracking across all providers on streaming (#9722)

* feat(new_usage.tsx): add date picker for new usage tab

allow user to look back on their usage data

* feat(anthropic/chat/transformation.py): report reasoning tokens in completion token details

allows usage tracking on how many reasoning tokens are actually being used

* feat(streaming_chunk_builder.py): return reasoning_tokens in anthropic/openai streaming response

allows tracking reasoning_token usage across providers

* Fix update team metadata + fix bulk adding models on Ui  (#9721)

* fix(handle_add_model_submit.tsx): fix bulk adding models

* fix(team_info.tsx): fix team metadata update

Fixes https://github.com/BerriAI/litellm/issues/9689

* (v0) Unified file id - allow calling multiple providers with same file id (#9718)

* feat(files_endpoints.py): initial commit adding 'target_model_names' support

allow developer to specify all the models they want to call with the file

* feat(files_endpoints.py): return unified files endpoint

* test(test_files_endpoints.py): add validation test - if invalid purpose submitted

* feat: more updates

* feat: initial working commit of unified file id translation

* fix: additional fixes

* fix(router.py): remove model replace logic in jsonl on acreate_file

enables file upload to work for chat completion requests as well

* fix(files_endpoints.py): remove whitespace around model name

* fix(azure/handler.py): return acreate_file with correct response type

* fix: fix linting errors

* test: fix mock test to run on github actions

* fix: fix ruff errors

* fix: fix file too large error

* fix(utils.py): remove redundant var

* test: modify test to work on github actions

* test: update tests

* test: more debug logs to understand ci/cd issue

* test: fix test for respx

* test: skip mock respx test

fails on ci/cd - not clear why

* fix: fix ruff check

* fix: fix test

* fix(model_connection_test.tsx): fix linting error

* test: update unit tests
2025-04-03 11:48:52 -07:00
fengjiajieandGitHub 5a18eebdb6 Fix: Use request body in curl log for Gemini streaming mode (#9736) 2025-04-03 09:45:27 -07:00
Ishaan Jaff e0dbd328be test_bedrock_nova_json.py 2025-04-03 08:37:59 -07:00
Ishaan Jaff 44b34299a8 docs db deadlocks 2025-04-02 23:14:55 -07:00
Ishaan Jaff 82b8eb79c2 doc update 2025-04-02 23:11:22 -07:00
Tobias HermannandGitHub 5785600c4e [Feat] Add VertexAI gemini-2.0-flash (#9723) 2025-04-02 22:33:23 -07:00