phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): fix streaming to not return usage dict

Browse source 
Fixes https://github.com/BerriAI/litellm/issues/3237
This commit is contained in:
Krrish Dholakia 2024-04-24 08:06:07 -07:00
parent facc5f65aa
commit b10f03706d
24 changed files with 107 additions and 83 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/llms/bedrock.py
View file

@ -1028,7 +1028,7 @@ def completion(
total_tokens=response_body["usage"]["input_tokens"]
+ response_body["usage"]["output_tokens"],
)
model_response.usage = _usage
setattr(model_response, "usage", _usage)
else:
outputText = response_body["completion"]
model_response["finish_reason"] = response_body["stop_reason"]
@ -1071,8 +1071,10 @@ def completion(
status_code=response_metadata.get("HTTPStatusCode", 500),
)
## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here.
if getattr(model_response.usage, "total_tokens", None) is None:
## CALCULATING USAGE - bedrock charges on time, not tokens - have some mapping of cost here.
if not hasattr(model_response, "usage"):
setattr(model_response, "usage", Usage())
if getattr(model_response.usage, "total_tokens", None) is None: # type: ignore
prompt_tokens = response_metadata.get(
"x-amzn-bedrock-input-token-count", len(encoding.encode(prompt))
)
@ -1089,7 +1091,7 @@ def completion(
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
model_response.usage = usage
setattr(model_response, "usage", usage)
model_response["created"] = int(time.time())
model_response["model"] = model