Chat Everywhere by Explorator Labs

中文版

Chat Everywhere is an app designed to showcase the capabilities of Large Language Models and make them accessible to everyone without login or geo-restrictions. Our community has contributed valuable feedback during the app's development, resulting in additional features not found in the official ChatGPT.

Additional Features

• Folder structures
• Prompt templates
• Import/Export conversations
• Delete message
• Multi language support

  ^Thanks to the open-source community

• Share conversations
• Internet connected enhance mode (Beta)
• Respond Language selection (Coming up)
• Store conversations (Coming up)

Origins

This project is forked from Chatbot UI, an initiative by Mckay to build a superior and open-source user interface compared to the official one.

Project Funding plan

Explorator Labs is committed to lowering barriers to accessing technology like ChatGPT by pledging a fixed monthly budget, making this project available without the need for login or payment.

As the popularity of Chat Everywhere has grown, we are facing challenges in covering the increased costs, which now exceed USD $2k per month. In the coming weeks, we will introduce a paid account feature to support the project's sustainability and enable us to develop more advanced functionalities for all users!

Tech Stack

• React.js
• Next.js
• Supabase
• LangChainJS
• Vercel

Getting Started (Work in progress)

1. Clone Repo

git clone https://github.com/exploratortech/chat-everywhere

2. Install Dependencies

npm i

3. Provide OpenAI API Key

Create a .env.local file in the root of the repo with your OpenAI API Key:

OPENAI_API_KEY=YOUR_KEY

4. Run App

npm run dev

5. Use It

Start chatting and enjoy!

Set up the web browser tool endpoint for Online mode

1. Ensure that the environment variable WEB_CONTENT_FUNCTION_SECRET is set in the project's root folder and in ./firebase/functions/.
2. Deploy the Firebase functions using npm run deploy.
3. Update the WEB_CONTENT_FUNCTION_ENDPOINT after completing the initial deployment.

# Set up ai-images bucket for AI Painter feature for Local development

1. Create a supabase bucket ai-images and make it public in the Local supabase server.

Set up image-to-prompt feature bucket for Local development

1. Create a supabase bucket image-to-prompt and make it public in the Local supabase server.
2. Go to file pages/api/image-to-prompt.ts and uncomment the function replaceLocalhost
3. Update the variable ngrokHost and localSupabaseHost
4. Uncomment the line where url is passed to url: replaceLocalhost(url), in function nextLegDescribe
5. Now that your supabase bucket is accessible from the internet, so that the next leg api can access it.

Set up the Teacher Portal for Local development

1. Create a supabase bucket student_message_submissions_image and make it public in the Local supabase server.

Database migration guide

1. Make the changes in local Supabase emulator
2. Generate a new migration file with supabase migration new migration_file_name
3. Get database difference with supabase db diff
4. Apply appropriate changes to the new migration file

Install Redis for local development

1. Install instructions: https://redis.io/docs/latest/operate/oss_and_stack/install/install-redis/install-redis-on-mac-os/

• After the installation, there is no need to run the Redis server manually. We are using the containerized version of Redis for local development.
• If you already have Redis installed and have another Redis server running on the default port(6379), you can change the port by modifying the docker-compose.yml file.

2. Run Serverless Redis Server(SRS) for local development

Reference: https://upstash.com/docs/oss/sdks/ts/redis/developing

docker compose up

3. Update the .env file with the Redis URL

UPSTASH_REDIS_REST_URL="http://localhost:8079"
UPSTASH_REDIS_REST_TOKEN="example_token"