Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Retry for replicate completion response of status=processing #7901

Merged
merged 1 commit into from
Jan 24, 2025
Merged

Retry for replicate completion response of status=processing #7901

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 16 additions & 6 deletions litellm/llms/replicate/chat/handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -196,11 +196,16 @@ def completion(
)
return CustomStreamWrapper(_response, model, logging_obj=logging_obj, custom_llm_provider="replicate") # type: ignore
else:
for _ in range(litellm.DEFAULT_MAX_RETRIES):
for retry in range(litellm.DEFAULT_REPLICATE_POLLING_RETRIES):
time.sleep(
1
) # wait 1s to allow response to be generated by replicate - else partial output is generated with status=="processing"
litellm.DEFAULT_REPLICATE_POLLING_DELAY_SECONDS + 2 * retry
) # wait to allow response to be generated by replicate - else partial output is generated with status=="processing"
response = httpx_client.get(url=prediction_url, headers=headers)
if (
response.status_code == 200
and response.json().get("status") == "processing"
):
continue
return litellm.ReplicateConfig().transform_response(
model=model,
raw_response=response,
Expand Down Expand Up @@ -259,11 +264,16 @@ async def async_completion(
)
return CustomStreamWrapper(_response, model, logging_obj=logging_obj, custom_llm_provider="replicate") # type: ignore

for _ in range(litellm.DEFAULT_REPLICATE_POLLING_RETRIES):
for retry in range(litellm.DEFAULT_REPLICATE_POLLING_RETRIES):
await asyncio.sleep(
litellm.DEFAULT_REPLICATE_POLLING_DELAY_SECONDS
) # wait 1s to allow response to be generated by replicate - else partial output is generated with status=="processing"
litellm.DEFAULT_REPLICATE_POLLING_DELAY_SECONDS + 2 * retry
) # wait to allow response to be generated by replicate - else partial output is generated with status=="processing"
response = await async_handler.get(url=prediction_url, headers=headers)
if (
response.status_code == 200
and response.json().get("status") == "processing"
):
continue
return litellm.ReplicateConfig().transform_response(
model=model,
raw_response=response,
Expand Down