phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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
Details
Helm unit test / unit-test (push) Successful in 20s
Details

Browse source 
* 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
This commit is contained in:
Krish Dholakia 2025-03-25 23:46:20 -07:00 • committed by GitHub
parent 8657816477
commit 6fd18651d1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 223 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py
View file

@ -111,7 +111,7 @@ class VertexEmbedding(VertexBase):
)
try:
response = client.post(api_base, headers=headers, json=vertex_request) # type: ignore
response = client.post(url=api_base, headers=headers, json=vertex_request) # type: ignore
response.raise_for_status()
except httpx.HTTPStatusError as err:
error_code = err.response.status_code