Unicode URLencoded strings exceeded max prompt length

[manageseverin]

When I asked it to search for a specific product in specific country it does not take into account the urls that contain urlencoded unicode strings and crashes with "This model's maximum context length "

    raise self.handle_error_response(
openai.error.InvalidRequestError: This model's maximum context length is 8191 tokens, however you requested 8451 tokens (8451 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.

[kinance]

@manageseverin can you provide more debug info, e.g. call stack? It probably duplicates #2906

[github-actions]

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

[github-actions]

This issue was closed automatically because it has been stale for 10 days with no activity.