使用报错了是怎么回事哦

API Error:生成数据错误:HTTP
错误!状态:400,响应:t"error":f"message" :“Bad request! : t1"routify_respo
nsel”: tlntrace_id1":1"213e5c4517712160026263725d12311", I"request_idl" :1"f4
e87630cac14dbca7e@eb126c312bf71m, I"successlm: false, Imstatus1m : 400, 1merror.
sourcel": I"CLIENT_ERRORI " , I"error_messagel" : 1"A11Mode lsFailed :
请求供应商服务器失败",“error_detaillm:tV"error1”:fv"code1":1"12101”,1"me
ssagel":1"API 调用参数有误,请检查文档。Requested token count exceeds the
model’s maximum context length of 202752 tokens • You requested a total of
218083 tokens: 152547 tokens from the input messages and 65536 tokens for
the completion. Please reduce the number of tokens in the input messages
or the completion to fit within the
1imit.1"j3jja,itypell :iBadRequest",icodel :1400"}}
TraceID: 00-2bab303bcc338a17093773dd3324cfec-2c8d892+55e8458d-01]

现在经常会报错了 有大佬晓得咋回事哇

你这个是glm-5的报错吗?它现在不会自动压缩上下文,手动压缩就解决了

2 个赞

楼上说得对,定期手动执行:/compress

1 个赞