Empty bot response - `POST /v1/chat/completions` yields "404 Not Found"

[sebastienfi]

Thank you for providing such a powerful tool for the community. I do own GPT-4 access, and can't wait to try this with painful documents of mine.

I've encountered an issue while using the app, I wanted to bring this to your attention. Bootstrap and pnpm run dev works flawless - great job! I am able to send a message. But I never get an answer from the bot.

Terminal tells me the POST on https://api.openai.com/v1/chat/completions yields a 404. UI shows an empty bot response. I removed sensitive information.

Terminal message:

error [Error: Request failed with status code 404] {
  config: {
    transitional: {
      silentJSONParsing: true,
      forcedJSONParsing: true,
      clarifyTimeoutError: false
    },
    adapter: [Function: httpAdapter],
    transformRequest: [ [Function: transformRequest] ],
    transformResponse: [ [Function: transformResponse] ],
    timeout: 0,
    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/3.2.1',
      Authorization: 'Bearer <removed>',
      'Content-Length': 2823
    },
    method: 'post',
    responseType: 'stream',
    data: `{"model":"gpt-4","temperature":0,"top_p":1,"frequency_penalty":0,"presence_penalty":0,"n":1,"stream":true,"messages":[{"role":"user","content":"You are an AI assistant providing helpful advice. You are given the following extracted parts of a long document and a question. Provide a conversational answer based on the context provided.\\nYou should only provide hyperlinks that reference the context below. Do NOT make up hyperlinks.\\nIf you can't find the answer in the context below, just say \\"Hmm, I'm not sure.\\" Don't try to make up an answer.\\nIf the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.\\n\\nQuestion: <removed>\\n=========\\nAnswer in Markdown:"}]}`,
    url: 'https://api.openai.com/v1/chat/completions'
  },
  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)],
      prefinish: [Function: requestOnPrefinish]
    },
    _eventsCount: 7,
    _maxListeners: undefined,
    outputData: [],
    outputSize: 0,
    writable: true,
    destroyed: false,
    _last: true,
    chunkedEncoding: false,
    shouldKeepAlive: false,
    maxRequestsOnConnectionReached: false,
    _defaultKeepAlive: true,
    useChunkedEncodingByDefault: true,
    sendDate: false,
    _removedConnection: false,
    _removedContLen: false,
    _removedTE: false,
    _contentLength: null,
    _hasBody: true,
    _trailer: '',
    finished: true,
    _headerSent: true,
    _closed: false,
    socket: TLSSocket {
      _tlsOptions: [Object],
      _secureEstablished: true,
      _securePending: false,
      _newSessionPending: false,
      _controlReleased: true,
      secureConnecting: false,
      _SNICallback: null,
      servername: 'api.openai.com',
      alpnProtocol: false,
      authorized: true,
      authorizationError: null,
      encrypted: true,
      _events: [Object: null prototype],
      _eventsCount: 9,
      connecting: false,
      _hadError: false,
      _parent: null,
      _host: 'api.openai.com',
      _readableState: [ReadableState],
      _maxListeners: undefined,
      _writableState: [WritableState],
      allowHalfOpen: false,
      _sockname: null,
      _pendingData: null,
      _pendingEncoding: '',
      server: undefined,
      _server: null,
      ssl: [TLSWrap],
      _requestCert: true,
      _rejectUnauthorized: true,
      parser: null,
      _httpMessage: [Circular *1],
      [Symbol(res)]: [TLSWrap],
      [Symbol(verified)]: true,
      [Symbol(pendingSession)]: null,
      [Symbol(async_id_symbol)]: 137487,
      [Symbol(kHandle)]: [TLSWrap],
      [Symbol(kSetNoDelay)]: false,
      [Symbol(lastWriteQueueSize)]: 0,
      [Symbol(timeout)]: null,
      [Symbol(kBuffer)]: null,
      [Symbol(kBufferCb)]: null,
      [Symbol(kBufferGen)]: null,
      [Symbol(kCapture)]: false,
      [Symbol(kBytesRead)]: 0,
      [Symbol(kBytesWritten)]: 0,
      [Symbol(connect-options)]: [Object],
      [Symbol(RequestTimeout)]: undefined
    },
    _header: 'POST /v1/chat/completions HTTP/1.1\r\n' +
      'Accept: application/json, text/plain, */*\r\n' +
      'Content-Type: application/json\r\n' +
      'User-Agent: OpenAI/NodeJS/3.2.1\r\n' +
      'Authorization: Bearer <removed>\r\n' +
      'Content-Length: 2823\r\n' +
      'Host: api.openai.com\r\n' +
      'Connection: close\r\n' +
      '\r\n',
    _keepAliveTimeout: 0,
    _onPendingData: [Function: nop],
    agent: Agent {
      _events: [Object: null prototype],
      _eventsCount: 2,
      _maxListeners: undefined,
      defaultPort: 443,
      protocol: 'https:',
      options: [Object: null prototype],
      requests: [Object: null prototype] {},
      sockets: [Object: null prototype],
      freeSockets: [Object: null prototype] {},
      keepAliveMsecs: 1000,
      keepAlive: false,
      maxSockets: Infinity,
      maxFreeSockets: 256,
      scheduling: 'lifo',
      maxTotalSockets: Infinity,
      totalSocketCount: 1,
      maxCachedSessions: 100,
      _sessionCache: [Object],
      [Symbol(kCapture)]: false
    },
    socketPath: undefined,
    method: 'POST',
    maxHeaderSize: undefined,
    insecureHTTPParser: undefined,
    path: '/v1/chat/completions',
    _ended: false,
    res: IncomingMessage {
      _readableState: [ReadableState],
      _events: [Object: null prototype],
      _eventsCount: 1,
      _maxListeners: undefined,
      socket: [TLSSocket],
      httpVersionMajor: 1,
      httpVersionMinor: 1,
      httpVersion: '1.1',
      complete: true,
      rawHeaders: [Array],
      rawTrailers: [],
      aborted: false,
      upgrade: false,
      url: '',
      method: null,
      statusCode: 404,
      statusMessage: 'Not Found',
      client: [TLSSocket],
      _consuming: false,
      _dumped: false,
      req: [Circular *1],
      responseUrl: 'https://api.openai.com/v1/chat/completions',
      redirects: [],
      [Symbol(kCapture)]: false,
      [Symbol(kHeaders)]: [Object],
      [Symbol(kHeadersCount)]: 14,
      [Symbol(kTrailers)]: null,
      [Symbol(kTrailersCount)]: 0,
      [Symbol(RequestTimeout)]: undefined
    },
    aborted: false,
    timeoutCb: null,
    upgradeOrConnect: false,
    parser: null,
    maxHeadersCount: null,
    reusedSocket: false,
    host: 'api.openai.com',
    protocol: 'https:',
    _redirectable: Writable {
      _writableState: [WritableState],
      _events: [Object: null prototype],
      _eventsCount: 3,
      _maxListeners: undefined,
      _options: [Object],
      _ended: true,
      _ending: true,
      _redirectCount: 0,
      _redirects: [],
      _requestBodyLength: 2823,
      _requestBodyBuffers: [],
      _onNativeResponse: [Function (anonymous)],
      _currentRequest: [Circular *1],
      _currentUrl: 'https://api.openai.com/v1/chat/completions',
      [Symbol(kCapture)]: false
    },
    [Symbol(kCapture)]: false,
    [Symbol(kNeedDrain)]: false,
    [Symbol(corked)]: 0,
    [Symbol(kOutHeaders)]: [Object: null prototype] {
      accept: [Array],
      'content-type': [Array],
      'user-agent': [Array],
      authorization: [Array],
      'content-length': [Array],
      host: [Array]
    }
  },
  response: {
    status: 404,
    statusText: 'Not Found',
    headers: {
      date: 'Wed, 22 Mar 2023 11:22:14 GMT',
      'content-type': 'application/json; charset=utf-8',
      'content-length': '179',
      connection: 'close',
      vary: 'Origin',
      'x-request-id': '<removed>',
      'strict-transport-security': 'max-age=15724800; includeSubDomains'
    },
    config: {
      transitional: [Object],
      adapter: [Function: httpAdapter],
      transformRequest: [Array],
      transformResponse: [Array],
      timeout: 0,
      xsrfCookieName: 'XSRF-TOKEN',
      xsrfHeaderName: 'X-XSRF-TOKEN',
      maxContentLength: -1,
      maxBodyLength: -1,
      validateStatus: [Function: validateStatus],
      headers: [Object],
      method: 'post',
      responseType: 'stream',
      data: `{"model":"gpt-4","temperature":0,"top_p":1,"frequency_penalty":0,"presence_penalty":0,"n":1,"stream":true,"messages":[{"role":"user","content":"You are an AI assistant providing helpful advice. You are given the following extracted parts of a long document and a question. Provide a conversational answer based on the context provided.\\nYou should only provide hyperlinks that reference the context below. Do NOT make up hyperlinks.\\nIf you can't find the answer in the context below, just say \\"Hmm, I'm not sure.\\" Don't try to make up an answer.\\nIf the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.\\n\\nQuestion: <removed>\\n=========\\nAnswer in Markdown:"}]}`,
      url: 'https://api.openai.com/v1/chat/completions'
    },
    request: <ref *1> ClientRequest {
      _events: [Object: null prototype],
      _eventsCount: 7,
      _maxListeners: undefined,
      outputData: [],
      outputSize: 0,
      writable: true,
      destroyed: false,
      _last: true,
      chunkedEncoding: false,
      shouldKeepAlive: false,
      maxRequestsOnConnectionReached: false,
      _defaultKeepAlive: true,
      useChunkedEncodingByDefault: true,
      sendDate: false,
      _removedConnection: false,
      _removedContLen: false,
      _removedTE: false,
      _contentLength: null,
      _hasBody: true,
      _trailer: '',
      finished: true,
      _headerSent: true,
      _closed: false,
      socket: [TLSSocket],
      _header: 'POST /v1/chat/completions HTTP/1.1\r\n' +
        'Accept: application/json, text/plain, */*\r\n' +
        'Content-Type: application/json\r\n' +
        'User-Agent: OpenAI/NodeJS/3.2.1\r\n' +
        'Authorization: Bearer <removed>\r\n' +
        'Content-Length: 2823\r\n' +
        'Host: api.openai.com\r\n' +
        'Connection: close\r\n' +
        '\r\n',
      _keepAliveTimeout: 0,
      _onPendingData: [Function: nop],
      agent: [Agent],
      socketPath: undefined,
      method: 'POST',
      maxHeaderSize: undefined,
      insecureHTTPParser: undefined,
      path: '/v1/chat/completions',
      _ended: false,
      res: [IncomingMessage],
      aborted: false,
      timeoutCb: null,
      upgradeOrConnect: false,
      parser: null,
      maxHeadersCount: null,
      reusedSocket: false,
      host: 'api.openai.com',
      protocol: 'https:',
      _redirectable: [Writable],
      [Symbol(kCapture)]: false,
      [Symbol(kNeedDrain)]: false,
      [Symbol(corked)]: 0,
      [Symbol(kOutHeaders)]: [Object: null prototype]
    },
    data: IncomingMessage {
      _readableState: [ReadableState],
      _events: [Object: null prototype],
      _eventsCount: 1,
      _maxListeners: undefined,
      socket: [TLSSocket],
      httpVersionMajor: 1,
      httpVersionMinor: 1,
      httpVersion: '1.1',
      complete: true,
      rawHeaders: [Array],
      rawTrailers: [],
      aborted: false,
      upgrade: false,
      url: '',
      method: null,
      statusCode: 404,
      statusMessage: 'Not Found',
      client: [TLSSocket],
      _consuming: false,
      _dumped: false,
      req: [ClientRequest],
      responseUrl: 'https://api.openai.com/v1/chat/completions',
      redirects: [],
      [Symbol(kCapture)]: false,
      [Symbol(kHeaders)]: [Object],
      [Symbol(kHeadersCount)]: 14,
      [Symbol(kTrailers)]: null,
      [Symbol(kTrailersCount)]: 0,
      [Symbol(RequestTimeout)]: undefined
    }
  },
  isAxiosError: true,
  toJSON: [Function: toJSON]
}

[mayooear]

Does your API key work outside of the repo?

[sebastienfi]

The API Key works like a charm, and if it didn't, wouldn't we be seeing a 403 ?

[mayooear]

I see here that the data was actually sent to the endpoint?

data:{"model":"gpt-4","temperature":0,"top_p":1,"frequency_penalty":0,"presence_penalty":0,"n":1,"stream":true,"messages":[{"role":"user","content":"You are an AI assistant providing helpful advice. You are given the following extracted parts of a long document and a question. Provide a conversational answer based on the context provided.\nYou should only provide hyperlinks that reference the context below. Do NOT make up hyperlinks.\nIf you can't find the answer in the context below, just say \"Hmm, I'm not sure.\" Don't try to make up an answer.\nIf the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.\n\nQuestion: \n=========\nAnswer in Markdown:"}]}`,

Although I don't see you passing the "context" from the vectorstore?

[4tal]

Same exact issue for me, tried to downgrade to 3.5 turbo and still

[mayooear]

Same exact issue for me, tried to downgrade to 3.5 turbo and still

can you share your error?

[nschlaepfer]

Im having something similar. My text chat form GPT is not showing up thought it was a CSS issue. Here is my: Terminal: us-central1-gcp error [Error: PineconeClient: Error calling query: Error: PineconeClient: Error calling queryRaw: FetchError: The request failed and the interceptors did not return an alternative response]

[ForeverArt]

Same exact issue for me, tried to downgrade to 3.5 turbo and then it works.

[mayooear]

Im having something similar. My text chat form GPT is not showing up thought it was a CSS issue. Here is my: Terminal: us-central1-gcp error [Error: PineconeClient: Error calling query: Error: PineconeClient: Error calling queryRaw: FetchError: The request failed and the interceptors did not return an alternative response]

Have you followed README.md including changing configs in config folder, .env variables, and configuring your pinecone dashboard? Also reviewed other issues solutions on this repo?

[EthanNguyen55]

I have the same error i noticed that when ingesting there is no 'creating vector store' message and when trying fetching like shown in the video the vector comes up empty

[ssaroha]

@mayooear I have similar issue.

pasting logs

us-west4-gcp error [Error: Request failed with status code 404] { config: { transitional: { silentJSONParsing: true, forcedJSONParsing: true, clarifyTimeoutError: false }, adapter: [Function: httpAdapter], transformRequest: [ [Function: transformRequest] ], transformResponse: [ [Function: transformResponse] ], timeout: 0, 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/3.2.1', Authorization: 'Bearer sk-xxxxxxxxxxx', 'Content-Length': 2296 }, method: 'post', responseType: 'stream', data:{"model":"gpt-4","temperature":0,"top_p":1,"frequency_penalty":0,"presence_penalty":0,"n":1,"stream":true,"messages":[{"role":"user","content":"You are an AI assistant providing helpful advice. You are given the following extracted parts of a long document and a question. Provide a conversational answer based on the context provided.\nYou should only provide hyperlinks that reference the context below. Do NOT make up hyperlinks.\nIf you can't find the answer in the context below, just say \"Hmm, I'm not sure.\" Don't try to make up an answer.\nIf the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.\n\nQuestion: what is this legal case about?\n=========\nthe case before us. Qualified immunity shields public officials from money \ndamages only. See Wood v. Strickland, 420 U. S. 308, 314, n. 6 (1975). In \nthis case, Frederick asked not just for damages, but also for declaratory \nand injunctive relief. App. 13. Justice Breyer’s proposed decision on \nqualified immunity grounds would dispose of the damages claims, but \nFrederick’s other claims would remain unaddressed. To get around that \nproblem, Justice Breyer hypothesizes that Frederick’s suspension—the \ntarget of his request for injunctive relief—“may well be justified on non­\nspeech-related grounds.” See post, at 433 (opinion concurring in judg­\nment in part and dissenting in part). That hypothesis was never consid­\nered by the courts below, never raised by any of the parties, and is belied \nby the record, which nowhere suggests that the suspension would have\n\nrelied as its chief support on the Lochner v. New York, 198 U. S. 45 (1905), \nline of cases, 262 U. S., at 399, a line of cases that has long been criticized, \nUnited Haulers Assn., Inc. v. Oneida-Herkimer Solid Waste Management \nAuthority, 550 U. S. 330 (2007). Tinker also relied on Pierce v. Society \nof Sisters, 268 U. S. 510 (1925). Pierce has nothing to say on this issue \neither. Pierce simply upheld the right of parents to send their children \nto private school. Id., at 535.\n=========\nAnswer in Markdown:"}]}`, url: 'https://api.openai.com/v1/chat/completions' }, 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: false, _last: false, chunkedEncoding: false, shouldKeepAlive: true, maxRequestsOnConnectionReached: false, _defaultKeepAlive: true, useChunkedEncodingByDefault: true, sendDate: false, _removedConnection: false, _removedContLen: false, _removedTE: false, strictContentLength: false, _contentLength: 2296, _hasBody: true, _trailer: '', finished: true, _headerSent: true, _closed: false, socket: TLSSocket { _tlsOptions: [Object], _secureEstablished: true, _securePending: false, _newSessionPending: false, _controlReleased: true, secureConnecting: false, _SNICallback: null, servername: 'api.openai.com', alpnProtocol: false, authorized: true, authorizationError: null, encrypted: true, _events: [Object: null prototype], _eventsCount: 9, connecting: false, _hadError: false, _parent: null, _host: 'api.openai.com', _closeAfterHandlingError: false, _readableState: [ReadableState], _maxListeners: undefined, _writableState: [WritableState], allowHalfOpen: false, _sockname: null, _pendingData: null, _pendingEncoding: '', server: undefined, _server: null, ssl: [TLSWrap], _requestCert: true, _rejectUnauthorized: true, timeout: 5000, parser: null, _httpMessage: [Circular 1],

  [Symbol(verified)]: true,
  [Symbol(pendingSession)]: null,
  [Symbol(async_id_symbol)]: 135401,
  [Symbol(kHandle)]: [TLSWrap],
  [Symbol(lastWriteQueueSize)]: 0,
  [Symbol(timeout)]: Timeout {
    _idleTimeout: 5000,
    _idlePrev: [TimersList],
    _idleNext: [Timeout],
    _idleStart: 101298,
    _onTimeout: [Function: bound ],
    _timerArgs: undefined,
    _repeat: null,
    _destroyed: false,
    [Symbol(refed)]: false,
    [Symbol(kHasPrimitive)]: false,
    [Symbol(asyncId)]: 135403,
    [Symbol(triggerId)]: 0
  },
  [Symbol(kBuffer)]: null,
  [Symbol(kBufferCb)]: null,
  [Symbol(kBufferGen)]: null,
  [Symbol(kCapture)]: false,
  [Symbol(kSetNoDelay)]: false,
  [Symbol(kSetKeepAlive)]: true,
  [Symbol(kSetKeepAliveInitialDelay)]: 60,
  [Symbol(kBytesRead)]: 0,
  [Symbol(kBytesWritten)]: 0,
  [Symbol(connect-options)]: [Object]
},
_header: 'POST /v1/chat/completions HTTP/1.1\r\n' +
  'Accept: application/json, text/plain, */*\r\n' +
  'Content-Type: application/json\r\n' +
  'User-Agent: OpenAI/NodeJS/3.2.1\r\n' +
  'Authorization: Bearer sk-xxxxxx\r\n' +
  'Content-Length: 2296\r\n' +
  'Host: api.openai.com\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: 443,
  protocol: 'https:',
  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: 6,
  maxCachedSessions: 100,
  _sessionCache: [Object],
  [Symbol(kCapture)]: false
},
socketPath: undefined,
method: 'POST',
maxHeaderSize: undefined,
insecureHTTPParser: undefined,
joinDuplicateHeaders: undefined,
path: '/v1/chat/completions',
_ended: false,
res: IncomingMessage {
  _readableState: [ReadableState],
  _events: [Object: null prototype],
  _eventsCount: 1,
  _maxListeners: undefined,
  socket: [TLSSocket],
  httpVersionMajor: 1,
  httpVersionMinor: 1,
  httpVersion: '1.1',
  complete: true,
  rawHeaders: [Array],
  rawTrailers: [],
  joinDuplicateHeaders: undefined,
  aborted: false,
  upgrade: false,
  url: '',
  method: null,
  statusCode: 404,
  statusMessage: 'Not Found',
  client: [TLSSocket],
  _consuming: false,
  _dumped: false,
  req: [Circular *1],
  responseUrl: 'https://api.openai.com/v1/chat/completions',
  redirects: [],
  [Symbol(kCapture)]: false,
  [Symbol(kHeaders)]: [Object],
  [Symbol(kHeadersCount)]: 14,
  [Symbol(kTrailers)]: null,
  [Symbol(kTrailersCount)]: 0
},
aborted: false,
timeoutCb: [Function: emitRequestTimeout],
upgradeOrConnect: false,
parser: null,
maxHeadersCount: null,
reusedSocket: false,
host: 'api.openai.com',
protocol: 'https:',
_redirectable: Writable {
  _writableState: [WritableState],
  _events: [Object: null prototype],
  _eventsCount: 3,
  _maxListeners: undefined,
  _options: [Object],
  _ended: true,
  _ending: true,
  _redirectCount: 0,
  _redirects: [],
  _requestBodyLength: 2296,
  _requestBodyBuffers: [],
  _onNativeResponse: [Function (anonymous)],
  _currentRequest: [Circular *1],
  _currentUrl: 'https://api.openai.com/v1/chat/completions',
  [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],
  'content-length': [Array],
  host: [Array]
},
[Symbol(errored)]: null,
[Symbol(kUniqueHeaders)]: null

}, response: { status: 404, statusText: 'Not Found', headers: { date: 'Sun, 26 Mar 2023 17:39:13 GMT', 'content-type': 'application/json; charset=utf-8', 'content-length': '179', connection: 'keep-alive', vary: 'Origin', 'x-request-id': '22d492be731f3ab2d64f0f59f37dce90', 'strict-transport-security': 'max-age=15724800; includeSubDomains' }, config: { transitional: [Object], adapter: [Function: httpAdapter], transformRequest: [Array], transformResponse: [Array], timeout: 0, xsrfCookieName: 'XSRF-TOKEN', xsrfHeaderName: 'X-XSRF-TOKEN', maxContentLength: -1, maxBodyLength: -1, validateStatus: [Function: validateStatus], headers: [Object], method: 'post', responseType: 'stream', data: {"model":"gpt-4","temperature":0,"top_p":1,"frequency_penalty":0,"presence_penalty":0,"n":1,"stream":true,"messages":[{"role":"user","content":"You are an AI assistant providing helpful advice. You are given the following extracted parts of a long document and a question. Provide a conversational answer based on the context provided.\\nYou should only provide hyperlinks that reference the context below. Do NOT make up hyperlinks.\\nIf you can't find the answer in the context below, just say \\"Hmm, I'm not sure.\\" Don't try to make up an answer.\\nIf the question is not related to the context, politely respond that you are tuned to only answer questions that are related to the context.\\n\\nQuestion: what is this legal case about?\\n=========\\nthe case before us. Qualified immunity shields public officials from money \\ndamages only. See Wood v. Strickland, 420 U. S. 308, 314, n. 6 (1975). In \\nthis case, Frederick asked not just for damages, but also for declaratory \\nand injunctive relief. App. 13. Justice Breyer’s proposed decision on \\nqualified immunity grounds would dispose of the damages claims, but \\nFrederick’s other claims would remain unaddressed. To get around that \\nproblem, Justice Breyer hypothesizes that Frederick’s suspension—the \\ntarget of his request for injunctive relief—“may well be justified on non­\\nspeech-related grounds.” See post, at 433 (opinion concurring in judg­\\nment in part and dissenting in part). That hypothesis was never consid­\\nered by the courts below, never raised by any of the parties, and is belied \\nby the record, which nowhere suggests that the suspension would have\\n\\nrelied as its chief support on the Lochner v. New York, 198 U. S. 45 (1905), \\nline of cases, 262 U. S., at 399, a line of cases that has long been criticized, \\nUnited Haulers Assn., Inc. v. Oneida-Herkimer Solid Waste Management \\nAuthority, 550 U. S. 330 (2007). Tinker also relied on Pierce v. Society \\nof Sisters, 268 U. S. 510 (1925). Pierce has nothing to say on this issue \\neither. Pierce simply upheld the right of parents to send their children \\nto private school. Id., at 535.\\n=========\\nAnswer in Markdown:"}]}, url: 'https://api.openai.com/v1/chat/completions' }, request: <ref 1> ClientRequest { _events: [Object: null prototype], _eventsCount: 7, _maxListeners: undefined, outputData: [], outputSize: 0, writable: true, destroyed: false, _last: false, chunkedEncoding: false, shouldKeepAlive: true, maxRequestsOnConnectionReached: false, _defaultKeepAlive: true, useChunkedEncodingByDefault: true, sendDate: false, _removedConnection: false, _removedContLen: false, _removedTE: false, strictContentLength: false, _contentLength: 2296, _hasBody: true, _trailer: '', finished: true, _headerSent: true, _closed: false, socket: [TLSSocket], _header: 'POST /v1/chat/completions HTTP/1.1\r\n' + 'Accept: application/json, text/plain, /*\r\n' + 'Content-Type: application/json\r\n' + 'User-Agent: OpenAI/NodeJS/3.2.1\r\n' + 'Authorization: Bearer sk-xxxxx\r\n' + 'Content-Length: 2296\r\n' + 'Host: api.openai.com\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/chat/completions', _ended: false, res: [IncomingMessage], aborted: false, timeoutCb: [Function: emitRequestTimeout], upgradeOrConnect: false, parser: null, maxHeadersCount: null, reusedSocket: false, host: 'api.openai.com', protocol: 'https:', _redirectable: [Writable],

  [Symbol(kBytesWritten)]: 0,
  [Symbol(kNeedDrain)]: false,
  [Symbol(corked)]: 0,
  [Symbol(kOutHeaders)]: [Object: null prototype],
  [Symbol(errored)]: null,
  [Symbol(kUniqueHeaders)]: null
},
data: IncomingMessage {
  _readableState: [ReadableState],
  _events: [Object: null prototype],
  _eventsCount: 1,
  _maxListeners: undefined,
  socket: [TLSSocket],
  httpVersionMajor: 1,
  httpVersionMinor: 1,
  httpVersion: '1.1',
  complete: true,
  rawHeaders: [Array],
  rawTrailers: [],
  joinDuplicateHeaders: undefined,
  aborted: false,
  upgrade: false,
  url: '',
  method: null,
  statusCode: 404,
  statusMessage: 'Not Found',
  client: [TLSSocket],
  _consuming: false,
  _dumped: false,
  req: [ClientRequest],
  responseUrl: 'https://api.openai.com/v1/chat/completions',
  redirects: [],
  [Symbol(kCapture)]: false,
  [Symbol(kHeaders)]: [Object],
  [Symbol(kHeadersCount)]: 14,
  [Symbol(kTrailers)]: null,
  [Symbol(kTrailersCount)]: 0
}

}, isAxiosError: true, toJSON: [Function: toJSON] } ^[[6~^C  ELIFECYCLE  Command failed.

`

[mayooear]

url: 'https://api.openai.com/v1/chat/completions' }, 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: requestOnFinis

Is this the query portion after the ingestion was completed successfully?

Downgrade from gpt-4 to gpt-3.5-turbo for the openAIChat model

[sebastienfi]

url: 'https://api.openai.com/v1/chat/completions' }, 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: requestOnFinis

Is this the query portion after the ingestion was completed successfully?

Downgrade from gpt-4 to gpt-3.5-turbo for the openAIChat model

That does not seem to be the same issue. Original issue reports a successful ingestion, then a 404 at querying prompt response.

[sebastienfi]

I can confirm that it works when downgrading to gpt-3.5-turbo. Yet this might be seen as a workaround, but having less tokens to provide an answer is a real pain.

[text2sql]

i am having the same issue "Error calling queryRaw: FetchError:" i am on gpt-3.5-turbo

[adampaigge]

Also having this issue with 404 across both gpt4 and 3.5 turbo. successful ingestion, same debug log as the above. Has the API chnaged?