soulteary / docker-chatgpt Goto Github PK

< 10MB, One-click self-hosted ChatGPT, allowing access to various data sources and non-OpenAI models.

Home Page: https://github.com/soulteary/sparrow

License: Do What The F*ck You Want To Public License

chatgpt chatgpt-app chatgpt-client openai openai-chatgpt docker-chatgpt self-hosted chatgpt-plugins midjourney-api midjourney-api-bot

docker-chatgpt's Introduction

Docker ChatGPT

ENGLISH | 中文文档

One-click local version of ChatGPT, allowing access to various data sources and non-OpenAI models.

Key features

Privacy is in your hands, no stats report.
Client is Blazing fast.
Allow you add any custom data source, data types.
Consistent with the official function interaction.

Usage Example

Check the example directory, choose the right configuration and use.

Screenshots

Conversation with the image.	Conversation with the plugin.

Customize the Model Switcher.	App Settings.

Quick Overview

Download the project, or select the appropriate example configuration file to get started. ( eg: examples/01.use-OpenAI-API/docker-compose.yml )

# download the latest version
git clone https://github.com/soulteary/docker-chatgpt.git
# or use zipball
wget https://github.com/soulteary/docker-chatgpt/archive/refs/heads/main.zip

Update the configuration file according to your actual situation.

OPENAI_API_KEY: "sk-......"
# If your network is not directly accessible OpenAI API, enable proxy and set you own proxy server addr.
# OPENAI_API_PROXY_ENABLE: "on"
# OPENAI_API_PROXY_ADDR: "http://127.0.0.1:1234"

Use docker to launch the project.

docker compose up
# or run in the daemon mode
docker compose up -d

Open your browser, visit http://localhost:8090, and enjoy.

How to Upgrade

The Client will be updated along with the project to keep it consistent with the officially supported functions.

You can update the project by updating the mirror version used in this repository.

# x86_64
docker pull soulteary/chatgpt
# Mac M1/M2
docker pull soulteary/docker-chatgpt:arm64

Backend services will continue to complete and support new data source types.

You can download the latest version of the automatically built image by using the following command:

docker pull soulteary/sparrow
# or use the latest version
docker pull soulteary/sparrow:v0.9.2

Then, restart the project with docker compose down && docker compose up -d to complete the upgrade.

For more advanced usage, and previous practices, such as searching various vertical websites through it, using MidJoruney to draw pictures, you can refer to the video in the Sparrow project documentation.

Welcome to submit your code in the project to support your data type.

Performance

The reason for the good experience of the project is because it is very fast and has a very good score.

In addition, the daily operation of the program as a service only requires about 10MB of hard disk space, about 10MB of content, and about 1% of CPU resources.

About Private

The project does not need to connect to any external network except for the backend service address that will be connected in the configuration.

You can prohibit the privacy leakage you are worried about by setting firewall rules or cloud server export access rules.

This does not affect the use of the program as it does not require an additional network connection.

Credits

Backend: ChatGPT Style client-compatible Backend Server, open source implementation. soulteary/sparrow

License

WTFPL license

docker-chatgpt's People

Contributors

Stargazers

Watchers

Forkers

vbarter weiplanet chaunceydust chenpo3725 bradserbu lrochetta colonnade-consulting-ltd winscat leeeex timyy jinxiaoye1987 andassis beanluo robin-li 5l1v3r1 urbanreality soitun

docker-chatgpt's Issues

Error with docker URLs?

I get the following issue at the front end (hosting on a VPS, not locally, which has other containers for other services and thus a shared network - Nginx Proxy Manager):

An error occurred. Either the engine you requested does not exist or there was another issue processing your request. If this issue persists please contact us through our help center at help.openai.com.

docker-compose.yml

version: '3'

services:

  chatgpt-client:
    image: soulteary/chatgpt
    restart: always
    environment:
      APP_PORT: 8090
      # the ChatGPT client domain, keep the same with chatgpt-client: `APP_HOSTNAME` option
      APP_HOSTNAME: "http://localhost:8090"
      # the ChatGPT backend upstream, or connect a sparrow dev server `"http://host.docker.internal:8091"`
      APP_UPSTREAM: "http://sparrow:8091"
    networks:
      - nginxproxymanager_default

  sparrow:
    image: soulteary/sparrow
    restart: always
    environment:
      # [Basic Settings]
      # => The ChatGPT Web Client Domain
      WEB_CLIENT_HOSTNAME: "http://chatgpt-client:8090"
      # => Service port, default: 8091
      # APP_PORT: 8091

      # [Private OpenAI API Server Settings] *optional
      # => Enable OpenAI 3.5 API
      ENABLE_OPENAI_API: "on"
      # => OpenAI API Key
      OPENAI_API_KEY: "sk-iTsAsEcReT"
      # => Enable OpenAI API Proxy
      # OPENAI_API_PROXY_ENABLE: "on"
      # => OpenAI API Proxy Address, eg: `"http://127.0.0.1:1234"` or ""
      # OPENAI_API_PROXY_ADDR: "http://127.0.0.1:1234"
    logging:
        driver: "json-file"
        options:
            max-size: "10m"
    networks:
      - nginxproxymanager_default

networks:
  nginxproxymanager_default:
    external: true

Feature: Claude in ChatGPT

verification completed, update when free.

8fe6f03

New Version: 23.05.29

x86 Docker Image
M1 Docker Image

Configuration issue

  MIDJOURNEY_API_SECRET: "123123"
  # => Midjourney API Address, eg: `"ws://...."`, or `"ws://host.docker.internal:8092/ws"`
  MIDJOURNEY_API_URL: "ws://localhost:8092/ws"

Do you need to set up the service locally by yourself? Are there any sample projects?

Where is the source code of web-client?

I am interested in the origins of the source code for 'web-client'. Could you please link to it? Also, what is the reason for the packer on web-client, to save space? Thanks!

core dumped when run on MacOS with Apple Silicon

logs like this:

qemu: uncaught target signal 11 (Segmentation fault) - core dumped

Does it support ARM?

Error Code : 429

Error Code 429 - Rate limit reached for requests

关于 Client 部分，我能否自己部署

使用我自己的 api key，主要是自己用用，我试了下你的代码，魔改后可以正常运行，速度真的快 👍。

虽然我想白嫖，但如果只是允许我是使用目前 docker 镜像也可以。