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

fix: fix streaming with httpx client

Browse source 
prevent overwriting streams in parallel streaming calls
This commit is contained in:
Krrish Dholakia 2024-05-31 10:55:18 -07:00
parent aada7b4bd3
commit 93c3635b64
9 changed files with 182 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/replicate.py
View file

@ -251,7 +251,7 @@ async def async_handle_prediction_response(
logs = ""
while True and (status not in ["succeeded", "failed", "canceled"]):
print_verbose(f"replicate: polling endpoint: {prediction_url}")
await asyncio.sleep(0.5)
await asyncio.sleep(0.5) # prevent replicate rate limit errors
response = await http_handler.get(prediction_url, headers=headers)
if response.status_code == 200:
response_data = response.json()