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

fix exception mapping for streaming

Browse source
This commit is contained in:
Krrish Dholakia 2023-09-23 15:04:34 -07:00
parent f984e5f380
commit 889679a0dd
8 changed files with 766 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/llms/replicate.py
View file

@ -77,14 +77,16 @@ def handle_prediction_response_streaming(prediction_url, api_token, print_verbos
}
status = ""
while True and (status not in ["succeeded", "failed", "canceled"]):
time.sleep(0.0001)
time.sleep(0.0001) # prevent being rate limited by replicate
response = requests.get(prediction_url, headers=headers)
if response.status_code == 200:
response_data = response.json()
status = response_data['status']
print(f"response data: {response_data}")
if "output" in response_data:
output_string = "".join(response_data['output'])
new_output = output_string[len(previous_output):]
yield new_output
yield {"output": new_output, "status": status}
previous_output = output_string
status = response_data['status']