Default for all online requests to 10 minutes timeout

[RyanMarten]

No description provided.

[madiator]

Verified it helps o1 run

[RyanMarten]

Minimal reproduction for posterity (before fix)

from bespokelabs.curator import LLM
from datasets import Dataset

dataset = Dataset.from_dict({"prompt": ["Write me a very very very long story about a person's journey through life."]})

prompter = LLM(
    prompt_func=lambda row: row["prompt"],
    model_name="gpt-4o-mini",
    response_format=None,
)

dataset = prompter(dataset)
print(dataset.to_pandas())

2024-12-16 16:01:42,963 - bespokelabs.curator.request_processor.base_online_request_processor - INFO - Running OpenAIOnlineRequestProcessor completions with model: gpt-4o-mini
2024-12-16 16:01:42,971 - bespokelabs.curator.request_processor.base_online_request_processor - INFO - Automatically set max_requests_per_minute to 30000
2024-12-16 16:01:42,971 - bespokelabs.curator.request_processor.base_online_request_processor - INFO - Automatically set max_tokens_per_minute to 150000000
Processing OpenAIOnlineRequestProcessor requests:   0%|                                                                                                                                       | 0/1 [00:00<?, ?it/s]2024-12-16 16:02:43,888 - bespokelabs.curator.request_processor.base_online_request_processor - WARNING - Encountered 'TimeoutError: ' during attempt 1 of 10 while processing request 0
^CTraceback (most recent call last):