Since I'm on an ARM64 Surface Pro11, I can't use local models. So I was using Claude for the last few days, and I've been very impressed. But today I ran into issues.
Claude suddenly banned my account with no information. I've appealed it, but have not heard back. So I switched to OpenAI's API. It starts processing a request then returns this error message: "Error: Rate limited by the API. Please wait a moment and try again." I tried a few different models and get the same message.
I'm wondering if Librarian is exceeding tokens or requests per minute, and it is tripping AI guardrails. Is there any adjustments to the settings that you would suggest?
Claude settings used until ban:
claude-opus-4-8 (Claude API) (64K) | Grounded | Search: 10732ms | 93 chunks | Generation: 1533 tokens in 24359ms (62.9 tok/s)
Attached: Claude and OpenAI settings
Claude suddenly banned my account with no information. I've appealed it, but have not heard back. So I switched to OpenAI's API. It starts processing a request then returns this error message: "Error: Rate limited by the API. Please wait a moment and try again." I tried a few different models and get the same message.
I'm wondering if Librarian is exceeding tokens or requests per minute, and it is tripping AI guardrails. Is there any adjustments to the settings that you would suggest?
Claude settings used until ban:
claude-opus-4-8 (Claude API) (64K) | Grounded | Search: 10732ms | 93 chunks | Generation: 1533 tokens in 24359ms (62.9 tok/s)
Attached: Claude and OpenAI settings
