phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor sagemaker to be async

Browse source
This commit is contained in:
Ishaan Jaff 2024-08-15 18:18:02 -07:00
parent b1aed699ea
commit df4ea8fba6
5 changed files with 798 additions and 603 deletions
Download patch file Download diff file Expand all files Collapse all files

21
litellm/utils.py
View file

@ -9848,11 +9848,28 @@ class CustomStreamWrapper:
completion_obj["tool_calls"] = [response_obj["tool_use"]]
elif self.custom_llm_provider == "sagemaker":
print_verbose(f"ENTERS SAGEMAKER STREAMING for chunk {chunk}")
response_obj = self.handle_sagemaker_stream(chunk)
from litellm.types.llms.bedrock import GenericStreamingChunk
if self.received_finish_reason is not None:
raise StopIteration
response_obj: GenericStreamingChunk = chunk
completion_obj["content"] = response_obj["text"]
if response_obj["is_finished"]:
self.received_finish_reason = response_obj["finish_reason"]
if (
self.stream_options
and self.stream_options.get("include_usage", False) is True
and response_obj["usage"] is not None
):
model_response.usage = litellm.Usage(
prompt_tokens=response_obj["usage"]["inputTokens"],
completion_tokens=response_obj["usage"]["outputTokens"],
total_tokens=response_obj["usage"]["totalTokens"],
)
if "tool_use" in response_obj and response_obj["tool_use"] is not None:
completion_obj["tool_calls"] = [response_obj["tool_use"]]
elif self.custom_llm_provider == "petals":
if len(self.completion_stream) == 0:
if self.received_finish_reason is not None: