Starting to get 404 when I send a message

[frederikenghave]

Verify latest release

• [X] I verified that the issue exists in the latest chatgpt release

Verify webapp is working

• [X] I verify that the ChatGPT webapp is working properly for this account.

Environment details

Node.js v18.13.0 Windows 10 Chrome Version 109.0.5414.120 (Official Build) (64-bit)

Describe the Bug

I've been using the module with great success, but from today I started running into issues: When I send a message to ChatGPT I get an error code 404:

ChatGPTError: ChatGPTAPI error 404 at ChatGPTAPIBrowser.sendMessage (...node_modules/chatgpt/build/index.js:1604:23) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async ...chatgpt.js:49:21 { statusCode: 404, statusText: ''

Logging in still works for me. It looks like an update from ChatGPT that needs to be incorporated into the module.

[anotherso1a]

same issue. today.

response {
  url: 'https://chat.openai.com/backend-api/conversation',
  ok: false,
  status: 404,
  statusText: '',
  headers: {
    'alt-svc': 'h3=":443"; ma=86400, h3-29=":443"; ma=86400',
    'cf-cache-status': 'DYNAMIC',
    'cf-ray': '7932b6d45f71ced1-SJC',
    'content-encoding': 'br',
    'content-type': 'application/json',
    date: 'Thu, 02 Feb 2023 11:51:18 GMT',
    server: 'cloudflare',
    'strict-transport-security': 'max-age=15724800; includeSubDomains'
  },
  body: {
    detail: {
      message: 'That model does not exist',
      type: 'invalid_request_error',
      param: null,
      code: null
    }
  },
  request: {} // ...

[anotherso1a]

upgrade to @4+ then fixed

[ws02589111]

same issue, my lib version is 4.0.4

[panlina]

Same. 4.0.4. For the first 2 runs it worked normally, and then it started to report That model does not exist.

[LesterDong]

Same. 4.0.4. For the first 2 runs it worked normally, and then it started to report That model does not exist.

+1, Seems openai found the bug and fixed it just now!

[panlina]

Same. 4.0.4. For the first 2 runs it worked normally, and then it started to report That model does not exist.

+1, Seems openai found the bug and fixed it just now!

I tried just now. Seems as you said it does not repro for now.

[panlina]

Same. 4.0.4. For the first 2 runs it worked normally, and then it started to report That model does not exist.

+1, Seems openai found the bug and fixed it just now!

But again, the same error.

[cy948]

find var CHATGPT_MODEL in file node_modules/chatgpt/build/index.js, then change it to the available model could fix it temporary.

- var CHATGPT_MODEL = "text-chat-davinci-002-20230126";
+ var CHATGPT_MODEL = "text-davinci-003";

[ws02589111]

this is official public model, you can use official sdk to access it

[cy948]

我已经收到您的邮件，将在工作时间内2小时回复您。 I have received your email and will reply to you within 2 hours of working time. 

[ikechan8370]

我已经收到您的邮件，将在工作时间内2小时回复您。 I have received your email and will reply to you within 2 hours of working time. 

What's this?

[cy948]

That's a automatic reply from mailbox. 🤷‍♂️

[qbosen]

A temporary solution is to set the model

const api = new ChatGPTAPI({completionParams: {model: 'text-davinci-003'}});

[iota-unum]

A temporary solution is to set the model

const api = new ChatGPTAPI({completionParams: {model: 'text-davinci-003'}});

So this works like a charm, but I want to point out that openai charges for this

[transitive-bullshit]

Update: the text-chat-davinci-002-20230126 model has been disabled by OpenAI, which is what this library's currently using under the hood.

OpenAI released this model in stealth to YC and select partners last week. It was fine-tuned for chat and used to some extent by ChatGPT itself. After @waylaidwanderer discovered it, we updated this lib to use it.

This is a temporary setback as we look for a workaround. It is very likely that OpenAI partners still have access to a similar model. If you have any info on workarounds, please share them with one of the admins or in #general.

As @qbosen mentioned for a temporary workaround, you can override the model to use text-davinci-003 to keep your applications running. This model isn't fine-tuned for chat like ChatGPT, but it will still produce reasonable results.

  const api = new ChatGPTAPI({
    apiKey: process.env.OPENAI_API_KEY,
    completionParams: {
      model: 'text-davinci-003'
    }
  })

NOTE: this method is not free and your OpenAI account will be charged for usage. Double check their pricing to make sure this is okay for your use case.

[transitive-bullshit]

This package's been updated to use the chatgpt model from 2022: https://github.com/transitive-bullshit/chatgpt-api/releases/tag/v4.1.1

Please upgrade to v4.1.1 to try out the latest.