mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
fix(utils.py): fix streaming to not return usage dict
Fixes https://github.com/BerriAI/litellm/issues/3237
This commit is contained in:
parent
70c98617da
commit
48c2c3d78a
24 changed files with 107 additions and 83 deletions
|
@ -185,9 +185,9 @@ def completion(
|
|||
else:
|
||||
try:
|
||||
if len(completion_response["generated_text"]) > 0:
|
||||
model_response["choices"][0]["message"][
|
||||
"content"
|
||||
] = completion_response["generated_text"]
|
||||
model_response["choices"][0]["message"]["content"] = (
|
||||
completion_response["generated_text"]
|
||||
)
|
||||
except:
|
||||
raise NLPCloudError(
|
||||
message=json.dumps(completion_response),
|
||||
|
@ -205,7 +205,7 @@ def completion(
|
|||
completion_tokens=completion_tokens,
|
||||
total_tokens=prompt_tokens + completion_tokens,
|
||||
)
|
||||
model_response.usage = usage
|
||||
setattr(model_response, "usage", usage)
|
||||
return model_response
|
||||
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue