Hello 😃, thank you for being here! GPT_ChatHist is a small app that allows you to interact with OpenAI's GPT-3.5-turbo through a local web interface. It saves your dialogue history locally, allowing you to continue multiple chat sessions. If you prefer a version without a web interface, check out GPT_ChatHist_no_web.
- Easily resume your dialogue with ChatGPT.
- Access dialogue history to analyze, review, or utilize past conversations for various purposes.
- OpenAI does not use data submitted by customers via the API to train or improve models unless you explicitly opt-in to share your data. OpenAI's API Data Usage Policies.
- Clone the repository or download the source code.
- Create a virtual environment
python -m venv .venv
- Activate the virtual environment:
-
Windows:
.venv\Scripts\activate.bat -
Linux/Mac:
source .venv/bin/activate
- Install the required packages:
pip install -r requirements.txt
- Change
OPEN_API_KEYinconfig.yamlto your OpenAI API Key If you do not have an Open AI API key, please follow the Open AI blogpost.
- Activate the virtual environment (if not already active).
- Run the app:
python web_chat.py
- Open a web browser and navigate to http://127.0.0.1:5000/ to access the app interface. Enter your preferred chat name and start interacting with the AI.
Every message you send will contain all previous chat history.
- Keep in mind that the model has a token limit (e.g., 4096 tokens for GPT-3). If your conversation exceeds this limit, you will need to truncate or remove some messages from the list to fit within the allowed token count.
- If your conversation is very large, it can consume a significant portion of your token limit.