Commit graph

21468 commits

Author SHA1 Message Date
Ishaan Jaff
efce84815a test_gemini_fine_tuned_model_request_consistency 2025-03-25 23:54:06 -07:00
Krish Dholakia
6fd18651d1
Support litellm.api_base for vertex_ai + gemini/ across completion, embedding, image_generation (#9516)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 19s
Helm unit test / unit-test (push) Successful in 20s
* test(tests): add unit testing for litellm_proxy integration

* fix(cost_calculator.py): fix tracking cost in sdk when calling proxy

* fix(main.py): respect litellm.api_base on `vertex_ai/` and `gemini/` routes

* fix(main.py): consistently support custom api base across gemini + vertexai on embedding + completion

* feat(vertex_ai/): test

* fix: fix linting error

* test: set api base as None before starting loadtest
2025-03-25 23:46:20 -07:00
Ishaan Jaff
8657816477 fix gemini/gemini-2.0-flash-lite on model cost map 2025-03-25 23:20:43 -07:00
Ishaan Jaff
6e5d2b1ac7 handle failed db connections 2025-03-25 23:14:44 -07:00
Krrish Dholakia
e0880734d9 docs(config_settings.md): cleanup docs 2025-03-25 23:11:45 -07:00
Krrish Dholakia
24b3e80eba ci: update github action 2025-03-25 23:11:45 -07:00
Ishaan Jaff
c61214dcf1
Merge pull request #9523 from BerriAI/litellm_add_gemini_flash_lite
[Feat - New Model] Add VertexAI `gemini-2.0-flash-lite` and Google AI Studio `gemini-2.0-flash-lite`
2025-03-25 23:11:44 -07:00
Ishaan Jaff
c473e2b1c2 setup_google_dns 2025-03-25 23:02:02 -07:00
Ishaan Jaff
3725ba4f63 setup_google_dns 2025-03-25 22:52:31 -07:00
Nicholas Grabar
f68cc26f15 8864 Add support for anyOf union type while handling null fields 2025-03-25 22:37:28 -07:00
Ishaan Jaff
61816dfd04 litellm_assistants_api_testing bump python 2025-03-25 22:31:16 -07:00
Ishaan Jaff
24a329ea5b Set DNS 2025-03-25 22:29:40 -07:00
Ishaan Jaff
9aec7c3878 test_create_delete_assistants 2025-03-25 22:08:06 -07:00
Ishaan Jaff
79ef184345 run ci/cd again 2025-03-25 21:57:45 -07:00
Ishaan Jaff
0a401ee468 test_litellm_proxy_server_config_no_general_settings 2025-03-25 19:27:15 -07:00
Ishaan Jaff
6572ba7a0e fix startup 2025-03-25 19:25:47 -07:00
Ishaan Jaff
b4e745323a add test config 2025-03-25 19:21:51 -07:00
Ishaan Jaff
9d10befa09 test_litellm_proxy_server_config_no_general_settings 2025-03-25 19:16:34 -07:00
Ishaan Jaff
4386558582 litellm_proxy_reliability_tests 2025-03-25 19:11:13 -07:00
Ishaan Jaff
53d9e33e78 fix setup toxi proxy 2025-03-25 18:59:26 -07:00
Ishaan Jaff
9e2d230339 litellm_proxy_reliability_tests 2025-03-25 18:23:52 -07:00
Ishaan Jaff
6f138c79a7 run toxi proxy tests 2025-03-25 18:19:11 -07:00
Ishaan Jaff
83b41f95e7 Setup Toxiproxy 2025-03-25 18:05:41 -07:00
Ishaan Jaff
bf7241abd1 litellm_proxy_reliability_tests 2025-03-25 18:02:01 -07:00
Ishaan Jaff
53a586e876 TOXI_PROXY_DATABASE_URL 2025-03-25 17:59:38 -07:00
Krish Dholakia
6cd6ff801f
ci(publish-migrations.yml): add action for publishing prisma db migrations (#9537)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 18s
Helm unit test / unit-test (push) Successful in 21s
2025-03-25 17:55:59 -07:00
Ishaan Jaff
34c3825d13 fix path 2025-03-25 17:53:30 -07:00
Ishaan Jaff
7b09d88680 fix setup 2025-03-25 17:52:12 -07:00
Ishaan Jaff
c6d5793bf6 add toxi proxy tests to ci/cd 2025-03-25 17:50:27 -07:00
Ishaan Jaff
ce49e27217 fixes for auth checks 2025-03-25 15:44:13 -07:00
Ishaan Jaff
59040167ac fix ProxyErrorTypes 2025-03-25 14:40:11 -07:00
Ishaan Jaff
4c87084ff7 UserAPIKeyAuthExceptionHandler 2025-03-25 14:07:14 -07:00
Krrish Dholakia
e8c4cd8c1a docs: cleanup docs
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 14s
Helm unit test / unit-test (push) Successful in 21s
2025-03-25 12:25:42 -07:00
Krrish Dholakia
1a58e8bfe5 docs(admin_ui_sso.md): add logout url 2025-03-25 12:25:16 -07:00
Krrish Dholakia
ff61ce6751 docs: update release note with patch 2025-03-25 10:17:34 -07:00
Ishaan Jaff
0af9a5e8d0 add gemini/gemini-2.0-flash-lite 2025-03-25 07:51:42 -07:00
Ishaan Jaff
62bb7d6605 add vertex gemini-2.0-flash-lite 2025-03-25 07:48:33 -07:00
Ishaan Jaff
b19529a46e fix docker compose 2025-03-25 07:03:43 -07:00
Krish Dholakia
92883560f0
fix vertex ai multimodal embedding translation (#9471)
All checks were successful
Read Version from pyproject.toml / read-version (push) Successful in 20s
Helm unit test / unit-test (push) Successful in 24s
* remove data:image/jpeg;base64, prefix from base64 image input

vertex_ai's multimodal embeddings endpoint expects a raw base64 string without `data:image/jpeg;base64,` prefix.

* Add Vertex Multimodal Embedding Test

* fix(test_vertex.py): add e2e tests on multimodal embeddings

* test: unit testing

* test: remove sklearn dep

* test: update test with fixed route

* test: fix test

---------

Co-authored-by: Jonarod <jonrodd@gmail.com>
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
2025-03-24 23:23:28 -07:00
Krrish Dholakia
75994d0bf0 test: improve flaky test 2025-03-24 23:15:04 -07:00
superpoussin22
12fdd25841
Update model_prices_and_context_window.json (#9459)
add mistral-small for vertex_ai
2025-03-24 22:44:00 -07:00
Krish Dholakia
a619580bf8
Add vertexai topLogprobs support (#9518)
* Added support for top_logprobs in vertex gemini models

* Testing for top_logprobs feature in vertexai

* Update litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py

Co-authored-by: Tom Matthews <tomukmatthews@gmail.com>

* refactor(tests/): refactor testing to be in correct repo

---------

Co-authored-by: Aditya Thaker <adityathaker28@gmail.com>
Co-authored-by: Tom Matthews <tomukmatthews@gmail.com>
2025-03-24 22:42:38 -07:00
Ishaan Jaff
da16cef4ba Expose MCP tools 2025-03-24 21:36:02 -07:00
Ishaan Jaff
18dfb70023 mcp docs, exposing tools now live 2025-03-24 21:35:29 -07:00
Ishaan Jaff
f1a8b1984a fix mcp test deps 2025-03-24 21:34:18 -07:00
Ishaan Jaff
12639b7ccf fix sagemaker streaming error 2025-03-24 21:29:29 -07:00
Krish Dholakia
bd309a28c5
Merge pull request #9512 from BerriAI/litellm_dev_03_24_2025_p3
fix(invoke_handler.py): remove hard coded chunk on streaming usage
2025-03-24 21:21:36 -07:00
Ishaan Jaff
80f201ff15 bump: version 1.64.0 → 1.64.1 2025-03-24 21:21:18 -07:00
Ishaan Jaff
f2b9a7f2ea pip install "langchain_mcp_adapters==0.0.5" 2025-03-24 21:20:11 -07:00
Ishaan Jaff
863fe3a4d2 fix import mcp router 2025-03-24 21:08:24 -07:00