Commit graph

3 commits

Author SHA1 Message Date
Krish Dholakia
069aee9f70
fix(transformation.py): correctly translate 'thinking' param for lite… (#9904)
All checks were successful
Helm unit test / unit-test (push) Successful in 21s
Read Version from pyproject.toml / read-version (push) Successful in 40s
* fix(transformation.py): correctly translate 'thinking' param for litellm_proxy/ route

Fixes https://github.com/BerriAI/litellm/issues/9892

* test: update test
2025-04-11 23:25:13 -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
f9cee4c46b
(Bug Fix) Using LiteLLM Python SDK with model=litellm_proxy/ for embedding, image_generation, transcription, speech, rerank (#8815)
* test_litellm_gateway_from_sdk

* fix embedding check for openai

* test litellm proxy provider

* fix image generation openai compatible models

* fix litellm.transcription

* test_litellm_gateway_from_sdk_rerank

* docs litellm python sdk

* docs litellm python sdk with proxy

* test_litellm_gateway_from_sdk_rerank

* ci/cd run again

* test_litellm_gateway_from_sdk_image_generation

* test_litellm_gateway_from_sdk_embedding

* test_litellm_gateway_from_sdk_embedding
2025-02-25 16:22:37 -08:00