RateLimitError:

[Ynantao]

openai.error.RateLimitError: Rate limit reached for text-embedding-ada-002 in organization org-W1kYnDA7btlD2UoW1aZEjc8S on requests per min (RPM): Limit 3, Used 3, Requested 1. Please try again in 20s. Visit https://platform.openai.com/account/rate-limits to learn more. You can increase your rate limit by adding a payment method to your account at https://platform.openai.com/account/billing.

[gontxomde]

Have you tried replacing :text-davinci-00\d (regex) to gpt-3.5-turbo?

In this PR (#143) it is mentioned that the usage of openAI is deprecated

[drudilorenzo]

Have you solved the problem? @Ynantao

It's likely due to your status as a "FREE TIER" user. As you invest more in the API, your limits expand accordingly.
See Usage tiers.

[lichen782]

what is minimal requirement of limit quota, like tier-1 is enough or at least tier-3 is required?

[drudilorenzo]

what is minimal requirement of limit quota, like tier-1 is enough or at least tier-3 is required?

Tbh, I don't know, I am trying to assess the cost but reading other issues (e.g. #115 ) I saw different opinions :(

If anyone has a clue about the price of running the experiment would be super useful. I am interested in running it using ~20 different agents but even the price for the base setting with 3 agents is more than enough. If someone knows the price using GPT 3.5 or 4 would be great!