phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix(utils.py): fix watson streaming

Browse source
This commit is contained in:
Krrish Dholakia 2024-04-29 08:09:59 -07:00
parent 0a6b6302f1
commit ab954243e8
1 changed files with 0 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

15
litellm/utils.py
View file

@ -10154,21 +10154,6 @@ class CustomStreamWrapper:
elif self.custom_llm_provider == "watsonx":
response_obj = self.handle_watsonx_stream(chunk)
completion_obj["content"] = response_obj["text"]
print_verbose(f"completion obj content: {completion_obj['content']}")
if response_obj.get("prompt_tokens") is not None:
prompt_token_count = getattr(
model_response.usage, "prompt_tokens", 0
)
model_response.usage.prompt_tokens = (
prompt_token_count + response_obj["prompt_tokens"]
)
if response_obj.get("completion_tokens") is not None:
model_response.usage.completion_tokens = response_obj[
"completion_tokens"
]
model_response.usage.total_tokens = getattr(
model_response.usage, "prompt_tokens", 0
) + getattr(model_response.usage, "completion_tokens", 0)
if response_obj["is_finished"]:
self.received_finish_reason = response_obj["finish_reason"]
elif self.custom_llm_provider == "text-completion-openai":