eyucoder / chatgpt-pro Goto Github PK

I git checkout local_setup and ran cd client && npm run dev on Windows

ChatGPT never responds and I got this error when I checked Chrome console
http://localhost:3000/davinci 404 (Not Found)

Please help

Although I understand they just generally released the API access yesterday, I understand that by the end of the month, everyone using the API will have access to it. With that in mind, it seems like it would make sense to allow that as a model selection. While we're at it, would there be any reason that we wouldn't add in a few models in there?

How to enable live steaming?

thanks for your amazing website, does not work, please solve error 500

localhost/:1 Uncaught (in promise) Error: A listener indicated an asynchronous response by returning true, but the message channel closed before a response was received
:3000/dalle:1 Failed to load resource: the server responded with a status of 404 (Not Found)
localhost/:1 Uncaught (in promise) SyntaxError: Unexpected token '<', "<!DOCTYPE "... is not valid JSON
localhost/:1 Unchecked runtime.lastError: A listener indicated an asynchronous response by returning true, but the message channel closed before a response was received
3localhost/:1 Uncaught (in promise) Error: A listener indicated an asynchronous response by returning true, but the message channel closed before a response was received

Server is running on port 3001

frontend port 3000

i get issue after submitting any text, otherwise website loads fine

This is a suggestion: Write the answer letter by letter like ChatGPT.
It's cooler and it's also give the impression that it's faster, and we can read before the response is finish.
I just find this (I didn't try yet) : https://www.npmjs.com/package/write-like-chat-gpt

There also no conversation history, meaning that it do not know what we were previously talking about. There's no context.

EX:
Question: What is the United-States Capital?
Response: The capital of the United States is Washington, D.C.
Question: What is the population?
Response: : I'm sorry, but I need more information to answer your question. Population of what?

There are a lot of examples on GitHub who show how to do it.

Help me!

Hello everyone,
I wanted to try to run the client and server locally.
I followed the guide in the readme but when I launch the server I get errors:

[0] WARNING in ./node_modules/timeago.js/esm/utils/dom.js
[0] Module Warning (from ./node_modules/source-map-loader/dist/cjs.js):
[0] Failed to parse source map from 'C:\Users\gabri\chatgpt-clone\client\node_modules\timeago.js\src\utils\dom.ts' file: Error: ENOENT: no such file or directory, open 'C:\Users\gabri\chatgpt-clone\client\node_modules\timeago.js\src\utils\dom.ts'
[0]
[0] webpack compiled with 8 warnings
[1] [ioredis] Unhandled error event: Error: connect ECONNREFUSED 127.0.0.1:6379
[1]     at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1300:16)
[1] [ioredis] Unhandled error event: Error: connect ECONNREFUSED 127.0.0.1:6379
[1]     at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1300:16)
[1] [ioredis] Unhandled error event: Error: connect ECONNREFUSED 127.0.0.1:6379
[1]     at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1300:16)
[1] [ioredis] Unhandled error event: Error: connect ECONNREFUSED 127.0.0.1:6379
[1]     at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1300:16)

I checked the folder:

Directory di C:\Users\gabri\chatgpt-clone\client\node_modules\timeago.js

27/01/2023  15:56    <DIR>          .
27/01/2023  15:59    <DIR>          ..
27/01/2023  15:56    <DIR>          dist
27/01/2023  15:56    <DIR>          esm
27/01/2023  15:56    <DIR>          lib
26/10/1985  09:15             1.073 LICENSE
26/10/1985  09:15             3.005 package.json
26/10/1985  09:15             5.082 README.md

And in fact there is no src folder.
Also it gives me connection refused error on port 6379 but I don't have anything else occupying the port and I'm on local, so I guess I don't need to do a nat on router (in any case I tried it anyway before bothering you but didn't solve it).

Can anyone help me figure out where I'm going wrong?
thanks in advance

Readme doesn't explain how to populate the client .env config.

it seems you limited the length of each prompt, it is not practical for English proofing texts and research, can you please return it to its initial form?

I tried clicking the ChatGPT or Dell.E button on the web page, but I still can't access the ChatGPT database after entering text. It has been changed to gpt-3.5-turbo model.

error 500, please have a check

Is it possible for you give some instructions on how to deploy this?
I love the demo and want to play with it a little and see if I can add some more functionality too it.
But it is awesome the way it is now.

It would be nice for ChatGPT to remember the past questions and answers.

is there any plan to use the latest chatGPT API?

HI there, I followed the instruction to run "npm run dev" and got the following error message:

npm run dev

[email protected] dev
concurrently "npm start" "npm run server"

[0]
[0] > [email protected] start
[0] > react-scripts start
[0]
[1]
[1] > [email protected] server
[1] > nodemon server/server.js
[1]
[1] 'nodemon' �����ڲ����ⲿ���Ҳ���ǿ����еij���
[1] ���������ļ���
[1] npm run server exited with code 1

==============================
the app did't start properly and stopped with a blank screen ...

Wonder if anyone happen to know how to fix it? Thanx in advance.

I am not able to implement this code

hej @EyuCoder love your chatgpt project!👏
How about integrating getitAI's open Plugin Store for easy plugin installs? (https://www.getit.ai/gpt-plugins) Let's chat for 15 mins: https://calendly.com/d/z4j-cb5-h2y/getitai-devs

it gives error 500

The output doesn't seem to be the same

it gives error 500 again. please solve it

The installation is complete. Select ChatGPT/Dell.e and enter text. Question text can be generated. But the words and graphics of "Thinking..." don't have any answers.

The reason I wanted to make a web-based clone was to have the functionality of the web app but use my own API key, however, it appears that every message sends a new chat completion request, ignoring the rest of the conversation.

If this was Python I would be happy to do it myself and provide the code - obviously, it's expensive to send the entire conversation back and forth but it should at least be an option. Otherwise, it would seem more genuine to present the user with UI that conveys this fact - such as a single input & response field, and then a "new chat" begins after that, since that is what is happening on the backend.

Hello! I found a tiny issue.
If I look at the code, it looks the clone has SSO with Google, but we can send HTTP requests to the backend directly without authentication.

It gives rise to excessive use of APIs and bypasses the rate limit middleware.

wdyt?