phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test_embedding_response_ratelimit_headers

Browse source
This commit is contained in:
Ishaan Jaff 2025-04-11 17:54:54 -07:00
parent 91c0a794b9
commit 311c70698f
1 changed files with 8 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

11
tests/local_testing/test_embedding.py
View file

@ -1075,9 +1075,14 @@ def test_embedding_response_ratelimit_headers(model):
hidden_params = response._hidden_params
additional_headers = hidden_params.get("additional_headers", {})
print(additional_headers)
assert "x-ratelimit-remaining-requests" in additional_headers
assert int(additional_headers["x-ratelimit-remaining-requests"]) > 0
print("additional_headers", additional_headers)
# Azure is flaky with returning x-ratelimit-remaining-requests, we need to verify the upstream api returns this header
# if upstream api returns this header, we need to verify the header is transformed by litellm
if "llm_provider-x-ratelimit-limit-requests" in additional_headers or "x-ratelimit-limit-requests" in additional_headers:
assert "x-ratelimit-remaining-requests" in additional_headers
assert int(additional_headers["x-ratelimit-remaining-requests"]) > 0
assert "x-ratelimit-remaining-tokens" in additional_headers
assert int(additional_headers["x-ratelimit-remaining-tokens"]) > 0