Error message: fetch failed/about proxy and reverse proxy

[ladypiapia]

I'm a beginner, so I've encountered some seemingly low-level problems that I can't solve at the moment.
I deployed this project locally via docker on my Mac, and here is my docker-compose.ymlfile configuration:

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=https://openai-proxy.oneamaze.com/v1/chat/completions # 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

and here is my api/.envfile configuration:

##########################
# Server configuration: 
##########################

# The server will listen to localhost:3080 by default. You can change the target IP as you want. 
# If you want to make this server available externally, for example to share the server with others 
# or expose this from a Docker container, set host to 0.0.0.0 or your external IP interface. 
# Tips: Setting host to 0.0.0.0 means listening on all interfaces. It's not a real IP.  
# Use localhost:port rather than 0.0.0.0:port to access the server. 
# Set Node env to development if running in dev mode.
HOST=localhost
PORT=3080
NODE_ENV=production 

# Change this to proxy any API request. 
# It's useful if your machine has difficulty calling the original API server. 
# PROXY=
# Change this to your MongoDB URI if different. I recommend appending chatgpt-clone. 
MONGO_URI=mongodb://127.0.0.1:27017/chatgpt-clone

##########################
# OpenAI Endpoint: 
##########################

# Access key from OpenAI platform. 
# Leave it blank to disable this feature. 
OPENAI_KEY=sk-xxxxxxxxxxxxxxx

# Identify the available models, separated by commas *without spaces*. 
# The first will be default. 
# Leave it blank to use internal settings. 
OPENAI_MODELS=gpt-3.5-turbo,gpt-3.5-turbo-0301,text-davinci-003,gpt-4

# Reverse proxy settings for OpenAI: 
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy 
OPENAI_REVERSE_PROXY=https://xxxx.oneamaze.com/v1/chat/completions

##########################
# AZURE Endpoint:   
##########################

# To use Azure with this project, set the following variables. These will be used to build the API URL.
# Chat completion: 
#     `https://{AZURE_OPENAI_API_INSTANCE_NAME}.openai.azure.com/openai/deployments/{AZURE_OPENAI_API_DEPLOYMENT_NAME}/chat/completions?api-version={AZURE_OPENAI_API_VERSION}`;
# You should also consider changing the `OPENAI_MODELS` variable above to the models available in your instance/deployment.
# Note: I've noticed that the Azure API is much faster than the OpenAI API, so the streaming looks almost instantaneous.

# AZURE_OPENAI_API_KEY=
# AZURE_OPENAI_API_INSTANCE_NAME=
# AZURE_OPENAI_API_DEPLOYMENT_NAME=
# AZURE_OPENAI_API_VERSION=
# AZURE_OPENAI_API_COMPLETIONS_DEPLOYMENT_NAME= # Optional, but may be used in future updates
# AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME= # Optional, but may be used in future updates

##########################
# BingAI Endpoint:   
##########################

# Also used for Sydney and jailbreak

# BingAI Tokens: the "_U" cookies value from bing.com 
# Set to "user_provided" to allow the user to provide its token from the UI.
# Leave it blank to disable this endpoint. 
BINGAI_TOKEN="user_provided"

# BingAI Host: 
# Necessary for some people in different countries, e.g. China (https://cn.bing.com) 
# Leave it blank to use default server. 
# BINGAI_HOST=https://cn.bing.com 

##########################
# ChatGPT Endpoint: 
##########################

# ChatGPT Browser Client (free but use at your own risk) 
# Access token from https://chat.openai.com/api/auth/session 
# Exposes your access token to `CHATGPT_REVERSE_PROXY`
# Set to "user_provided" to allow the user to provide its token from the UI.
# Leave it blank to disable this endpoint 
CHATGPT_TOKEN="user_provided"

# Identify the available models, separated by commas. The first will be default. 
# Leave it blank to use internal settings. 
CHATGPT_MODELS=text-davinci-002-render-sha,text-davinci-002-render-paid,gpt-4

# Reverse proxy settings for ChatGPT 
# https://github.com/waylaidwanderer/node-chatgpt-api#using-a-reverse-proxy 
# By default, the server will use the node-chatgpt-api recommended proxy (a third party server). 
# CHATGPT_REVERSE_PROXY= 

##########################
# Search: 
##########################

# ENABLING SEARCH MESSAGES/CONVOS 
# Requires the installation of the free self-hosted Meilisearch or a paid Remote Plan (Remote not tested) 
# The easiest setup for this is through docker-compose, which takes care of it for you. 
SEARCH=false

# REQUIRED FOR SEARCH: MeiliSearch Host, mainly for the API server to connect to the search server. 
# Replace '0.0.0.0' with 'meilisearch' if serving MeiliSearch with docker-compose. 
MEILI_HOST=http://0.0.0.0:7700

# REQUIRED FOR SEARCH: MeiliSearch HTTP Address, mainly for docker-compose to expose the search server. 
# Replace '0.0.0.0' with 'meilisearch' if serving MeiliSearch with docker-compose. 
MEILI_HTTP_ADDR=0.0.0.0:7700

# REQUIRED FOR SEARCH: In production env., a secure key is needed. You can generate your own. 
# This master key must be at least 16 bytes, composed of valid UTF-8 characters. 
# MeiliSearch will throw an error and refuse to launch if no master key is provided, 
# or if it is under 16 bytes. MeiliSearch will suggest a secure autogenerated master key.
# Using docker, it seems recognized as production so use a secure key.
# This is a ready made secure key for docker-compose, you can replace it with your own.
MEILI_MASTER_KEY=DrhYf7zENyR6AlUCKmnz0eYASOQdl6zxH7s7MKFSfFCt

##########################
# User System:
##########################

# Google:
# Add your Google Client ID and Secret here, you must register an app with Google Cloud to get these values
# https://cloud.google.com/
GOOGLE_CLIENT_ID=
GOOGLE_CLIENT_SECRET=
GOOGLE_CALLBACK_URL=/oauth/google/callback

#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

After I finished the deployment, everything was fine and I could register and log in, but I just couldn't ask a question and it returned the following error:

I know that the proxy or reverse proxy configuration must be incorrect, but I don't know exactly how it should be configured.
But the reverse proxy address https://xxxx.oneamaze.com/v1/chat/completions is fine, because curl can return the content correctly:

(base) withot.@WithotdeMacBook-Air chatgpt-clone-0.4.4 % curl https://xxx.oneamaze.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxxxxxxxxxxxxx" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
{"id":"chatcmpl-7GfkorvmcbDZWVLPfZcjcAZgGv1AI","object":"chat.completion","created":1684208106,"model":"gpt-3.5-turbo-0301","usage":{"prompt_tokens":10,"completion_tokens":9,"total_tokens":19},"choices":[{"message":{"role":"assistant","content":"Hello! How may I assist you today?"},"finish_reason":"stop","index":0}]}
(base) withot.@WithotdeMacBook-Air chatgpt-clone-0.4.4 % 

Also if I open ClashX Pro for proxy on my Mac, it works fine and returns answers normally.
I want to deploy it locally on my Mac first, and then deploy it on my server, which should also involve proxying at that time.
I hope you can give me some advice, thank you very much!

[danny-avila]

Hi, thanks for trying the project! Sorry you're having issues with this. This is one thing I noticed in your .env file:

# PROXY=https://xxxxx.oneamaze.com

It looks like your proxy is commented out, you should remove the # symbol and space before PROXY

Let me know if this was the issue. You can also ask on discord as the community is active on there!

[ladypiapia]

Thank you for your reply, but this is not the main reason, I wander how the bottom of this project makes a request to the api of openai, if it requests directly to this https://api.openai.com/v1/chat/completions, I want to change the address of this request to the reverse proxy address I built myself https ://xxx.oneamaze.com/v1/chat/completions so that I can use it properly，But I don't know where to change it or how to set it

[danny-avila]

Thank you for your reply, but this is not the main reason, I wander how the bottom of this project makes a request to the api of openai, if it requests directly to this https://api.openai.com/v1/chat/completions, I want to change the address of this request to the reverse proxy address I built myself https ://xxx.oneamaze.com/v1/chat/completions so that I can use it properly，But I don't know where to change it or how to set it

For the openAI API it would be OPENAI_REVERSE_PROXY in your ./api/.env file

Let us know if you need real time help, there's a couple of us on discord right now

[danny-avila]

I’m going to test with a reverse proxy today and see if there is an issue. I’ll share my configuration if it works

[ladypiapia]

Thanks, looking forward to it!

[danny-avila]

also how did you build the reverse proxy?

[ladypiapia]

I have built a reverse proxy in Vercel under the instruction of this project：https://github.com/LinLin00000000/vercel-proxy-openai

[ladypiapia]

Just set reverse proxy in api/.env:
OPENAI_REVERSE_PROXY=YOUR_REVERSE_PROXY_URL(e.g.https://proxy.xxxx.com/v1/chat/completions)