phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #2208 from BerriAI/litellm_enforce_team_limits

Browse source 
Litellm enforce team limits
This commit is contained in:
Krish Dholakia 2024-02-26 23:10:01 -08:00 • committed by GitHub
commit 365e7ed5b9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 302 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/utils.py
View file

@ -1183,7 +1183,7 @@ class Logging:
verbose_logger.debug(f"success callbacks: {litellm.success_callback}")
## BUILD COMPLETE STREAMED RESPONSE
complete_streaming_response = None
if self.stream:
if self.stream and isinstance(result, ModelResponse):
if (
result.choices[0].finish_reason is not None
): # if it's the last chunk
@ -8682,6 +8682,8 @@ class CustomStreamWrapper:
completion_obj["content"] = response_obj["text"]
print_verbose(f"completion obj content: {completion_obj['content']}")
if hasattr(chunk, "id"):
model_response.id = chunk.id
if response_obj["is_finished"]:
model_response.choices[0].finish_reason = response_obj[
"finish_reason"
@ -8704,6 +8706,8 @@ class CustomStreamWrapper:
model_response.system_fingerprint = getattr(
response_obj["original_chunk"], "system_fingerprint", None
)
if hasattr(response_obj["original_chunk"], "id"):
model_response.id = response_obj["original_chunk"].id
if response_obj["logprobs"] is not None:
model_response.choices[0].logprobs = response_obj["logprobs"]