Closed muzibaby closed 1 year ago
但是为什么其他人可以呢?可以到群里先沟通问一下
有删除聊天记录吗?这个之前已经适配过 system message 了。
如果问题能复现依旧存在,欢迎重开 issue
您自己试过吗?
Regards,
Vigo Song
---- 回复的原邮件 ----
| 发件人 | @.> |
| 发送日期 | 2023年08月10日 01:02 |
| 收件人 | songquanpeng/one-api @.> |
| 抄送人 | vigo @.>,
Author @.> |
| 主题 | Re: [songquanpeng/one-api] FastGPT使用文心一言 API,应用配置上知识库的时候,对话会出错! oneapi-0.5.2-alpha.5 oneapi-0.5.3-alpha.1 实测都不行 (Issue #369) |
但是为什么其他人可以呢?可以到群里先沟通问一下
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
我自己没有环境,我问过部署过的人,确定能复现才会开始 debug
好的,谢谢,我再确认下
Regards,
Vigo Song
---- 回复的原邮件 ----
| 发件人 | @.> |
| 发送日期 | 2023年08月13日 11:43 |
| 收件人 | songquanpeng/one-api @.> |
| 抄送人 | vigo @.>,
Author @.> |
| 主题 | Re: [songquanpeng/one-api] FastGPT使用文心一言 API,应用配置上知识库的时候,对话会出错! oneapi-0.5.2-alpha.5 oneapi-0.5.3-alpha.1 实测都不行 (Issue #369) |
我自己没有环境,我问过部署过的人,确定能复现才会开始 debug
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
更新了 FastGPT-3.9.4 配合 oneapi-0.5.3-alpha.1 ,清空了数据,重新创建应用,知识库,关联知识库后,对话还是出错,不关联知识库正常对话,确认有这个问题,其他同学应该没这么用过。
日志: Error: Request failed with status code 500 at createError (/app/node_modules/.pnpm/registry.npmmirror.com+axios@0.26.1/node_modules/axios/lib/core/createError.js:16:15) at settle (/app/node_modules/.pnpm/registry.npmmirror.com+axios@0.26.1/node_modules/axios/lib/core/settle.js:17:12) at IncomingMessage.handleStreamEnd (/app/node_modules/.pnpm/registry.npmmirror.com+axios@0.26.1/node_modules/axios/lib/adapters/http.js:322:11) at IncomingMessage.emit (node:events:526:35) at endReadableNT (node:internal/streams/readable:1376:12) at process.processTicksAndRejections (node:internal/process/task_queues:82:21) { config: { transitional: { silentJSONParsing: true, forcedJSONParsing: true, clarifyTimeoutError: false }, adapter: [Function: httpAdapter], transformRequest: [ [Function: transformRequest] ], transformResponse: [ [Function: transformResponse] ], timeout: 60000, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: { Accept: 'application/json, text/plain, /', 'Content-Type': 'application/json', 'User-Agent': 'OpenAI/NodeJS/3.3.0', Authorization: 'Bearer sk-5sslNl97GBDKY4P81173A3Bc6fBd4a05Be0826B9F1D0EdA9', auth: 'auth', 'Content-Length': 53 }, method: 'post', baseURL: 'http://172.29.91.79:3001/v1', data: '{"model":"text-embedding-ada-002","input":["您好"]}', url: 'http://172.29.91.79:3001/v1/embeddings' }, request: <ref *1> ClientRequest { _events: [Object: null prototype] { abort: [Function (anonymous)], aborted: [Function (anonymous)], connect: [Function (anonymous)], error: [Function (anonymous)], socket: [Function (anonymous)], timeout: [Function (anonymous)], finish: [Function: requestOnFinish] }, _eventsCount: 7, _maxListeners: undefined, outputData: [], outputSize: 0, writable: true, destroyed: true, _last: false, chunkedEncoding: false, shouldKeepAlive: true, maxRequestsOnConnectionReached: false, _defaultKeepAlive: true, useChunkedEncodingByDefault: true, sendDate: false, _removedConnection: false, _removedContLen: false, _removedTE: false, strictContentLength: false, _contentLength: 53, _hasBody: true, _trailer: '', finished: true, _headerSent: true, _closed: true, socket: Socket { connecting: false, _hadError: false, _parent: null, _host: null, _closeAfterHandlingError: false, _readableState: [ReadableState], _events: [Object: null prototype], _eventsCount: 6, _maxListeners: undefined, _writableState: [WritableState], allowHalfOpen: false, _sockname: null, _pendingData: null, _pendingEncoding: '', server: null, _server: null, timeout: 5000, parser: null, _httpMessage: null,
[Symbol(kHandle)]: [TCP],
[Symbol(lastWriteQueueSize)]: 0,
[Symbol(timeout)]: Timeout {
_idleTimeout: 5000,
_idlePrev: [TimersList],
_idleNext: [TimersList],
_idleStart: 634280,
_onTimeout: [Function: bound ],
_timerArgs: undefined,
_repeat: null,
_destroyed: false,
[Symbol(refed)]: false,
[Symbol(kHasPrimitive)]: false,
[Symbol(asyncId)]: 18290,
[Symbol(triggerId)]: 18288
},
[Symbol(kBuffer)]: null,
[Symbol(kBufferCb)]: null,
[Symbol(kBufferGen)]: null,
[Symbol(kCapture)]: false,
[Symbol(kSetNoDelay)]: true,
[Symbol(kSetKeepAlive)]: true,
[Symbol(kSetKeepAliveInitialDelay)]: 1,
[Symbol(kBytesRead)]: 0,
[Symbol(kBytesWritten)]: 0
},
_header: 'POST /v1/embeddings HTTP/1.1\r\n' +
'Accept: application/json, text/plain, */*\r\n' +
'Content-Type: application/json\r\n' +
'User-Agent: OpenAI/NodeJS/3.3.0\r\n' +
'Authorization: Bearer sk-5sslNl97GBDKY4P81173A3Bc6fBd4a05Be0826B9F1D0EdA9\r\n' +
'auth: auth\r\n' +
'Content-Length: 53\r\n' +
'Host: 172.29.91.79:3001\r\n' +
'Connection: keep-alive\r\n' +
'\r\n',
_keepAliveTimeout: 0,
_onPendingData: [Function: nop],
agent: Agent {
_events: [Object: null prototype],
_eventsCount: 2,
_maxListeners: undefined,
defaultPort: 80,
protocol: 'http:',
options: [Object: null prototype],
requests: [Object: null prototype] {},
sockets: [Object: null prototype] {},
freeSockets: [Object: null prototype],
keepAliveMsecs: 1000,
keepAlive: true,
maxSockets: Infinity,
maxFreeSockets: 256,
scheduling: 'lifo',
maxTotalSockets: Infinity,
totalSocketCount: 1,
[Symbol(kCapture)]: false
},
socketPath: undefined,
method: 'POST',
maxHeaderSize: undefined,
insecureHTTPParser: undefined,
joinDuplicateHeaders: undefined,
path: '/v1/embeddings',
_ended: true,
res: IncomingMessage {
_readableState: [ReadableState],
_events: [Object: null prototype],
_eventsCount: 4,
_maxListeners: undefined,
socket: null,
httpVersionMajor: 1,
httpVersionMinor: 1,
httpVersion: '1.1',
complete: true,
rawHeaders: [Array],
rawTrailers: [],
joinDuplicateHeaders: undefined,
aborted: false,
upgrade: false,
url: '',
method: null,
statusCode: 500,
statusMessage: 'Internal Server Error',
client: [Socket],
_consuming: false,
_dumped: false,
req: [Circular *1],
responseUrl: 'http://172.29.91.79:3001/v1/embeddings',
redirects: [],
[Symbol(kCapture)]: false,
[Symbol(kHeaders)]: [Object],
[Symbol(kHeadersCount)]: 6,
[Symbol(kTrailers)]: null,
[Symbol(kTrailersCount)]: 0
},
aborted: false,
timeoutCb: null,
upgradeOrConnect: false,
parser: null,
maxHeadersCount: null,
reusedSocket: false,
host: '172.29.91.79',
protocol: 'http:',
_redirectable: Writable {
_writableState: [WritableState],
_events: [Object: null prototype],
_eventsCount: 3,
_maxListeners: undefined,
_options: [Object],
_ended: true,
_ending: true,
_redirectCount: 0,
_redirects: [],
_requestBodyLength: 53,
_requestBodyBuffers: [],
_onNativeResponse: [Function (anonymous)],
_currentRequest: [Circular *1],
_currentUrl: 'http://172.29.91.79:3001/v1/embeddings',
_timeout: null,
[Symbol(kCapture)]: false
},
[Symbol(kCapture)]: false,
[Symbol(kBytesWritten)]: 0,
[Symbol(kNeedDrain)]: false,
[Symbol(corked)]: 0,
[Symbol(kOutHeaders)]: [Object: null prototype] {
accept: [Array],
'content-type': [Array],
'user-agent': [Array],
authorization: [Array],
auth: [Array],
'content-length': [Array],
host: [Array]
},
[Symbol(errored)]: null,
[Symbol(kHighWaterMark)]: 16384,
[Symbol(kRejectNonStandardBodyWrites)]: false,
[Symbol(kUniqueHeaders)]: null
}, response: { status: 500, statusText: 'Internal Server Error', headers: { 'content-type': 'application/json; charset=utf-8', date: 'Mon, 14 Aug 2023 02:38:53 GMT', 'content-length': '155' }, config: { transitional: [Object], adapter: [Function: httpAdapter], transformRequest: [Array], transformResponse: [Array], timeout: 60000, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: [Object], method: 'post', baseURL: 'http://172.29.91.79:3001/v1', data: '{"model":"text-embedding-ada-002","input":["您好"]}', url: 'http://172.29.91.79:3001/v1/embeddings' }, request: <ref 1> ClientRequest { _events: [Object: null prototype], _eventsCount: 7, _maxListeners: undefined, outputData: [], outputSize: 0, writable: true, destroyed: true, _last: false, chunkedEncoding: false, shouldKeepAlive: true, maxRequestsOnConnectionReached: false, _defaultKeepAlive: true, useChunkedEncodingByDefault: true, sendDate: false, _removedConnection: false, _removedContLen: false, _removedTE: false, strictContentLength: false, _contentLength: 53, _hasBody: true, _trailer: '', finished: true, _headerSent: true, _closed: true, socket: [Socket], _header: 'POST /v1/embeddings HTTP/1.1\r\n' + 'Accept: application/json, text/plain, /*\r\n' + 'Content-Type: application/json\r\n' + 'User-Agent: OpenAI/NodeJS/3.3.0\r\n' + 'Authorization: Bearer sk-5sslNl97GBDKY4P81173A3Bc6fBd4a05Be0826B9F1D0EdA9\r\n' + 'auth: auth\r\n' + 'Content-Length: 53\r\n' + 'Host: 172.29.91.79:3001\r\n' + 'Connection: keep-alive\r\n' + '\r\n', _keepAliveTimeout: 0, _onPendingData: [Function: nop], agent: [Agent], socketPath: undefined, method: 'POST', maxHeaderSize: undefined, insecureHTTPParser: undefined, joinDuplicateHeaders: undefined, path: '/v1/embeddings', _ended: true, res: [IncomingMessage], aborted: false, timeoutCb: null, upgradeOrConnect: false, parser: null, maxHeadersCount: null, reusedSocket: false, host: '172.29.91.79', protocol: 'http:', _redirectable: [Writable],
[Symbol(kBytesWritten)]: 0,
[Symbol(kNeedDrain)]: false,
[Symbol(corked)]: 0,
[Symbol(kOutHeaders)]: [Object: null prototype],
[Symbol(errored)]: null,
[Symbol(kHighWaterMark)]: 16384,
[Symbol(kRejectNonStandardBodyWrites)]: false,
[Symbol(kUniqueHeaders)]: null
},
data: { error: [Object] }
}, isAxiosError: true, toJSON: [Function: toJSON] }
---------------oneapi-------------------------- [SYS] 2023/08/14 - 10:38:53 | relay error (channel #2): invalid character '<' looking for beginning of value
增加了模型映射后:
出现如下错误: [SYS] 2023/08/14 - 13:15:33 | relay error (channel #2): embeddings max batch size is 16, and can not be 0
如果直接采用微信一言的 chat 配合 opeanai的 text-embedding-ada-002,提示如下错误: [SYS] 2023/08/14 - 13:14:22 | relay error (channel #2): invalid character '<' looking for beginning of value
3.9因为限定词是用Human role,和文心不匹配。v4版本切换成system是可以的
请问是否有意向再兼容 3.X 版本嘛。
那看来不是 One API 的问题
请问是否有意向再兼容 3.X 版本嘛。
没有,已经不维护了
FastGPT-4.0 使用 Embeding-V1 过来 也不支持
FastGPT-4.0 使用 Embeding-V1 过来 也不支持
你有使用最新版本吗?我记得好像修复了,可以去tag那里下载最新版本
例行检查
问题描述 使用 FastGPT main 最新分支,配置 oneapi之后了,使用 ChatGPT 对话正常,但是使用文心一言之后,给应用配置了知识库之后,会话就会发生错误。 复现步骤 请求消息体如下: Sending request with body: {
model: 'gpt-3.5-turbo-16k',
apiKey: 'sk-5sslNl97GBDKY4P81173A3Bc6fBd4a05Be0826B9F1D0EdA9',
temperature: 0,
maxToken: 4000,
messages: [
{
},
{
},
{ _id: '64ccd019ab86e5f6b04db0a7', obj: 'Human', value: '李逵' }
],
stream: true,
res: ServerResponse {
_events: [Object: null prototype] {
},
_eventsCount: 3,
_maxListeners: undefined,
outputData: [],
outputSize: 0,
writable: true,
destroyed: false,
_last: false,
chunkedEncoding: false,
shouldKeepAlive: true,
maxRequestsOnConnectionReached: false,
_defaultKeepAlive: true,
useChunkedEncodingByDefault: true,
sendDate: true,
_removedConnection: false,
_removedContLen: false,
_removedTE: false,
strictContentLength: false,
_contentLength: null,
_hasBody: true,
_trailer: '',
finished: false,
_headerSent: false,
_closed: false,
socket: Socket {
},
_header: null,
_keepAliveTimeout: 5000,
_onPendingData: [Function: bound updateOutgoingData],
req: IncomingMessage {
},
_sent100: false,
_expect_continue: false,
_maxRequestsPerSocket: 0,
setHeader: [Function (anonymous)],
statusCode: 200,
flush: [Function: flush],
write: [Function (anonymous)],
end: [Function (anonymous)],
on: [Function: on],
writeHead: [Function: writeHead],
status: [Function (anonymous)],
send: [Function (anonymous)],
json: [Function (anonymous)],
redirect: [Function (anonymous)],
setPreviewData: [Function (anonymous)],
clearPreviewData: [Function (anonymous)],
revalidate: [Function (anonymous)],
[Symbol(kOutHeaders)]: [Object: null prototype] {
},
}
}
api response time: 1.216s
{
message: 'the length of messages must be an odd number',
type: 'baidu_error',
param: '',
code: 336003
}
预期结果 希望可以正常使用知识库对话的功能 相关截图 如果没有的话,请删除此节。