openai.error.RateLimitError: Rate limit reached for 10KTPM-200RPM in organization org-mSnj0BKpxchO5RMRJ0Q7zro0 on tokens per min. Limit: 10000 / min. Please try again in 6ms.

[gphett]

trafficstars

need to insert a pause so we do not get this error

[gphett]

from openai.error import RateLimitError

async def _achat_completion_stream(self, messages: list[dict]) -> str: retry_delay = 60 # Time in seconds to wait before retrying max_retries = 10 # Maximum number of retries

for attempt in range(max_retries):
    try:
        response = await openai.ChatCompletion.acreate(**self._cons_kwargs(messages), stream=True)

        # Create variables to collect the stream of chunks
        collected_chunks = []
        collected_messages = []
        # Iterate through the stream of events
        async for chunk in response:
            collected_chunks.append(chunk)  # Save the event response
            chunk_message = chunk["choices"][0]["delta"]  # Extract the message
            collected_messages.append(chunk_message)  # Save the message
            if "content" in chunk_message:
                print(chunk_message["content"], end="")
        print()

        full_reply_content = "".join([m.get("content", "") for m in collected_messages])
        usage = self._calc_usage(messages, full_reply_content)
        self._update_costs(usage)
        return full_reply_content

    except RateLimitError as e:
        logger.warning(f"Rate limit error: {e}. Retrying in {retry_delay} seconds...")
        await asyncio.sleep(retry_delay)

logger.error(f"Reached maximum retries ({max_retries}) for rate limit error.")
raise RateLimitError("Maximum retries reached for rate limit error.")

This seems to have fixed it for me

[dvizcaya91]

I think tenacity is supposed to be the one that handles the retries, but this is so far the only solution that worked for me. Thanks

[pablospe]

Perhaps you could provide a Pull Request?

[geekan]

check https://github.com/geekan/MetaGPT/blob/main/config/config.yaml RPM para

[thatiodeguy]

T

from openai.error import RateLimitError

async def _achat_completion_stream(self, messages: list[dict]) -> str: retry_delay = 60 # Time in seconds to wait before retrying max_retries = 10 # Maximum number of retries

for attempt in range(max_retries):
    try:
        response = await openai.ChatCompletion.acreate(**self._cons_kwargs(messages), stream=True)

        # Create variables to collect the stream of chunks
        collected_chunks = []
        collected_messages = []
        # Iterate through the stream of events
        async for chunk in response:
            collected_chunks.append(chunk)  # Save the event response
            chunk_message = chunk["choices"][0]["delta"]  # Extract the message
            collected_messages.append(chunk_message)  # Save the message
            if "content" in chunk_message:
                print(chunk_message["content"], end="")
        print()

        full_reply_content = "".join([m.get("content", "") for m in collected_messages])
        usage = self._calc_usage(messages, full_reply_content)
        self._update_costs(usage)
        return full_reply_content

    except RateLimitError as e:
        logger.warning(f"Rate limit error: {e}. Retrying in {retry_delay} seconds...")
        await asyncio.sleep(retry_delay)

logger.error(f"Reached maximum retries ({max_retries}) for rate limit error.")
raise RateLimitError("Maximum retries reached for rate limit error.")

This seems to have fixed it for me

This worked for me as well, thank you!