working again ; ) I am very busy at the moment so I would be very thankful for contributions and PR's
- Double confirm when deleting conversation
- remember user preferences
- theme changer
- loading / exporting a conversation
- speech output and input (elevenlabs; ex: https://github.com/cogentapps/chat-with-gpt)
- load files, ex: https://github.com/mayooear/gpt4-pdf-chatbot-langchain
- better documentation
- use react / faster backend language ? (newbies may be more confused and discouraged to use it)
feel free to improve the code / suggest improvements
To get started with this project, you'll need to clone the repository and set up a virtual environment. This will allow you to install the required dependencies without affecting your system-wide Python installation.
Before you can set up a virtual environment, you'll need to have Python installed on your system. You can download Python from the official website: https://www.python.org/downloads/
Run the following command to clone the repository:
git clone https://github.com/xtekky/chatgpt-clone.git
To set up a virtual environment, follow these steps:
- Navigate to the root directory of your project.
cd chatgpt-clone
- Run the following command to create a new virtual environment:
python -m venv venv
- Activate the virtual environment by running the following command:
source venv/bin/activate
If you are using fish shell, the command will be slightly different:
source venv/bin/activate.fish
If you're on Windows, the command will be slightly different:
venv\Scripts\activate
- Install the required dependencies by running the following command:
pip install -r requirements.txt
To configure the application, there are a few properties that can be set either via the environment or via config.json. The environment variable takes priority.
Field | Env Variable | config.json | examples |
---|---|---|---|
The OpenAI Api Key | OPENAI_API_KEY | openai_key | sk-... |
The OpenAI Base URL | OPENAI_API_BASE | openai_api_base | https://api.openai.com https://my-reverse-proxy/ |
Use the Base URL if you need to run your queries through a reverse proxy (like this one which will run your queries through Azure's OpenAI endpoints )
To run the application, make sure the virtual environment is active and run the following command:
python run.py
The easiest way to run ChatGPT Clone is by using docker
docker-compose up
Need to change config.json file to below:
{
"site_config": {
"host" : "0.0.0.0",
"port" : 1338,
"debug": false
},
"openai_key": "",
"openai_api_base": "https://localhost:1337/chat/completions",
"proxy": {
"enable": false,
"http": "127.0.0.1:7890",
"https": "127.0.0.1:7890"
}
}
Then change .\server\backend.py:
# url = f"{self.openai_api_base}/v1/chat/completions"
url=self.openai_api_base