scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

return actual status code - /count_tokens endpoint

Browse source
This commit is contained in:
Otavio Brito 2026-02-16 21:47:16 -03:00
parent c68383068a
commit f70e39483c
2 changed files with 17 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
litellm/llms/vertex_ai/vertex_ai_partner_models/count_tokens/handler.py
View file

@ -144,13 +144,6 @@ class VertexAIPartnerModelsTokenCounter(VertexBase):
timeout=30.0,
)
# Check for errors
if response.status_code != 200:
error_text = response.text
raise ValueError(
f"Token counting request failed with status {response.status_code}: {error_text}"
)
# Parse response
result = response.json()

24
litellm/proxy/proxy_server.py
View file

@ -7743,13 +7743,23 @@ async def token_counter(request: TokenCountRequest, call_endpoint: bool = False)
)
is True
):
result = await provider_counter.count_tokens(
model_to_use=model_to_use or "",
messages=messages, # type: ignore
contents=contents,
deployment=deployment,
request_model=request.model,
)
try:
result = await provider_counter.count_tokens(
model_to_use=model_to_use or "",
messages=messages, # type: ignore
contents=contents,
deployment=deployment,
request_model=request.model,
)
except httpx.HTTPStatusError as e:
error_message = getattr(e, "message", None) or str(e)
status_code = getattr(e, "status_code", None) or 500
raise ProxyException(
message=error_message,
type="token_counting_error",
param="model",
code=status_code
)
#########################################################
# Transfrom the Response to the well known format
#########################################################