#Starting error
1 messages · Page 1 of 1 (latest)
@exotic glacier I know you're having mac specific issues but I recommend using docker as you can avoid a lot of installation issues
you don't need the bash script. just go into the root folder of the project, then use npm run backend
then i having
borgil_b@Borgils-MacBook-Air borgilgpt % npm run backend
[email protected] backend
cd api && npm run start
[email protected] start
node server/index.js
There was an uncaught error: bad auth : authentication failed
Clearing sync timeouts before exiting...
npm ERR! Lifecycle script start failed with error:
npm ERR! Error: command failed
npm ERR! in workspace: [email protected]
npm ERR! at location: /Users/borgil_b/Desktop/borgilgpt/api
this error hehe
am i installed wrong way
just to make sure, you created an .env file correct?
yup
before running npm run backend, do npm ci
do you get any errors as packages install?
when i running npm run backend i got error
not having error on previous two code
so no errors with npm ci
yes
no errors with npm run frontend ?
yes that one too
do you have these variables?
#JWT:
JWT_SECRET_DEV=secret
# Add a secure secret for production if deploying to live domain.
JWT_SECRET_PROD=secret
# Set the expiration delay for the secure cookie with the JWT token
# Delay is in millisecond e.g. 7 days is 1000*60*60*24*7
SESSION_EXPIRY=1000 * 60 * 60 * 24 * 7
# Site URLs:
# Don't forget to set Node env to development in the Server configuration section above
# if you want to run in dev mode
CLIENT_URL_DEV=http://localhost:3090
SERVER_URL_DEV=http://localhost:3080
# Change these values to domain if deploying:
CLIENT_URL_PROD=http://localhost:3080
SERVER_URL_PROD=http://localhost:3080
i guess yes
@exotic glacier i looked up your issue, and it looks like it's an issue with your mongo URI string
oh okay
when you shared your .env earlier I noticed that in your .env your mongo password was user:<password> instead of user:password
oh yeah i fixed it too
there is have proxy section and
0.0.0.0
you removed the < >
yes sir
if you download mongodb compass, you can try out your connection string
it will load your database if the connection string is correct
@exotic glacier you can avoid this completely with docker. you're already halfway through the docker setup. easiest way is to download docker desktop, and you run one command from the root dir
okay is there have a step by step guide using docker
you already downloaded the project and created your .env file
you just need to install docker
and run docker-compose up from the root dir ⤵️
download docker desktop and then run docker -v after installation in your root dir to confirm you have it
then run docker-compose up
Last login: Wed May 17 21:12:03 on ttys000
borgil_b@Borgils-MacBook-Air ~ % cd /Users/borgil_b/desktop/borgilgpt
borgil_b@Borgils-MacBook-Air borgilgpt % docker-compose up
[+] Running 15/17
✔ meilisearch 5 layers [⣿⣿⣿⣿⣿] 0B/0B Pulled 57.0s
✔ ef5531b6e74e Pull complete 3.8s
✔ 63261cf6f1e0 Pull complete 5.2s
✔ 69f3affdd4c7 Pull complete 49.8s
✔ 65fd1ef71440 Pull complete 50.0s
✔ 4d71cfd5e491 Pull complete 50.2s
! api Warning 5.4s
⠦ mongodb 9 layers [⣿⣿⣿⣿⣿⣿⣿⣶⣿] 159.3MB/200MB Pulling 100.6s
✔ 1bc677758ad7 Pull complete 40.1s
✔ 7eb83bb7be98 Pull complete 41.9s
✔ e95121721c4c Pull complete 48.0s
✔ 799041b403ca Pull complete 49.4s
✔ 1828e70ef29a Pull complete 49.7s
✔ 8e3781beae9e Pull complete 49.9s
✔ 5d5753162333 Pull complete 50.1s
⠿ 44dd404b40f4 Extracting 159.3MB/200MB 93.7s
✔ 44599c9d5d1b Download complete 17.4s
invalid character 'c' looking for beginning of value
borgil_b@Borgils-MacBook-Air borgilgpt %
it says this
am i did it correctly
@exotic glacier try visiting the app site
should i dont use the mongodb atlas?
maybe issue is from this
Set up proxy in the local environment (for Mac):
Option 1: Set system-level environment variable
Open Terminal and run export PROXY="http://127.0.0.1:7890"
Change http://127.0.0.1:7890 to your proxy server
Option 2: Set in .env file
Open the .env file in the api directory with a text editor
Add PROXY="http://127.0.0.1:7890" to the file
Change http://127.0.0.1:7890 to your proxy server
Set up proxy in the Docker environment (for Mac):
Open the docker-compose.yml file with a text editor
Under services, find the api section, and then locate the environment section
Add the line - "PROXY=http://127.0.0.1:7890" under the environment section
Change http://127.0.0.1:7890 to your proxy server
Create a .env file in the api directory by running cp api/.env.example api/.env and edit the file with your preferred text editor, adding the required API keys, access tokens, and MongoDB connection string
Run npm ci root directory npm ci
Build the client by running npm run frontend
You don't need to follow the mac instruction to use the project with docker...
i installed docker
still not working
maybe i cant do that
version: "3.4"
services:
client:
image: nginx-client
build:
context: .
target: nginx-client
restart: always
ports:
- 3080:80
volumes:
- /client/node_modules
depends_on:
- api
api:
container_name: chat-clone
ports:
- 3080:3080 # Change it to 9000:3080 to use nginx
depends_on:
- mongodb
image: node-api # Comment this & uncomment below to build from docker hub image
build:
context: .
target: node-api
# image: chatgptclone/app:latest # Uncomment this & comment above to build from docker hub image
restart: always
env_file:
- ./api/.env
environment:
- HOST=0.0.0.0
- NODE_ENV=production
- MONGO_URI=mongodb://mongodb:27017/chatgpt-clone
# - CHATGPT_REVERSE_PROXY=http://host.docker.internal:8080/api/conversation # if you are hosting your own chatgpt reverse proxy
- MEILI_HOST=http://meilisearch:7700
- MEILI_HTTP_ADDR=meilisearch:7700
volumes:
- /client/node_modules
- ./api:/api
- /api/node_modules
mongodb:
container_name: chat-mongodb
ports:
- 27018:27017
image: mongo
restart: always
volumes:
- ./data-node:/data/db
command: mongod --noauth
meilisearch:
container_name: chat-meilisearch
image: getmeili/meilisearch:v1.0
ports:
- 7700:7700
env_file:
- ./api/.env
environment:
- MEILI_HOST=http://meilisearch:7700
- MEILI_HTTP_ADDR=meilisearch:7700
volumes:
- ./meili_data:/meili_data
should i connect my mongodb with this file?
it means successfully installed, right?
@exotic glacier do you have docker desktop installed? can you show what it displays? you dont need to run from terminal after you've composed once
also, were you visiting http://localhost:3080/ ?
running npm run backend, it still gets error
you don't need to run npm run backend with docker
docker is starting, screenshot after it's started
close all your other terminals too
after that, click on containers and screenshot that
@exotic glacier ok, go back to the root directory of the project. Run docker-compose up
you should see it show up in containers
after that it should show up in containers, right
it says building
am i doing correctly
that's good!
you didnt screenshot docker
when the project is done building look back at the container section, it should be there
Thank you guys for helping me
I appreciate that
it appears now
try to access the web interface 🤞
specifically http://localhost:3080/
also click on the arrow facing down left of the name for more details
Wow it is now working guys
I dont know how to say thank you
Life saving guys
🙏
I'm happy for you, have fun with the project!!!
do you have the proxy set up in the .env ? if so try to comment the line
You mean this
yup remove that
I can't read the error msg in the photo, can you copy paste it?
You have better eyes than me!
It is from openAI?
@exotic glacier note that anytime you change env variables, you will need to run docker-compose up
yes
Hehe sorry
Is it possible to create new account and get another API?
they do not offer free credit anymore
you need to add a credit card and pay for the usage
you can still configure and use the free version in the app
as well as Bing
Should I need to contact with salesman to purchase
An API for accessing new AI models developed by OpenAI
You fill out your account and payment info there
Okay guys it is worked
I payed about $5
And it is works like charm
Thanks for doing this
😊🎉
That's great! Enjoy!
with the api you are less restricted, but there are still some level of restrictions in place......
If you wan't, we have preset collections (including one with various jailbreaks) here -> #🤖|agents (look at the pinned posts)
Hello guys
Are guys there
Which model is combined with Bing AI
It says as an ai language model...
I'm not sure what you mean, it's using microsoft BIngChat... If you want to know how BingChat works, it's using GPT-4 with another layer, the Prometheus Engine (if I remember correctly), to process the user inputs and web search...
Yes, but it's free!
I payed $5 at chatgpt and gpt4 still not working, do you know what it is
GPT4 and Bing are using different keys
By using Bing you have access to "gpt4" through microsoft instead of using OpenAI
As for having access to gpt4 from openai , you have 2 options
first one is to wait, the access is still limited and not everyone has access to gpt4 api yet
second one is to subscribe to chatgpt plus for 20$ / month
the access for gpt4 api is very limited, I don't even have access yet
If you want an AI with web access, better use Bing (or Sydney) for now
you select it by clicking on this icon on the text box
this menu will open
to use it you need to get the content of the _u cookie from bing.com (it is explained better in the instructions)
that is what google bard uses
you history is alway recorded in your own database
if you want to delete some conversation you can use
You're welcome!
Hello everyone, how are you all doing?
I'm curious about creating a sports game predictor using this ChatGPT clone. I want to integrate it with a sports odds API and Stathead team data, allowing me to ask ChatGPT to predict outcomes for various American sports. I'm wondering if it's possible to accomplish this.
@exotic glacier yes it's possible with the new update to this project
it's not yet live, but we will have a soft launch on plugins/tools for the AI to use. it should be pretty strait forward to build your own tools from there. The main thing is to write documentation for it
I'm trying to integrate
Could someone assist me in importing sports historical data into a ChatGPT clone and provide guidance on the process?