An implementation of https://www.insider.com/tiktok-programmer-ai-girlfriend-waifu-euthanized-stopped-working-chatgpt-2023-1
🤖 ChatGPT chan is an open-source collection of tools to have your own personal assistant in your projects. With this, you can leverage the power of OpenAI's ChatGPT language model to build conversational interfaces, automate tasks, and more. The library provides a simple API for integrating voice assistant into your projects, making it easy for developers to add AI capabilities to their applications.
https://odysee.com/@rushi:2/chatgptchandemo2:4
- Python39
- Docker
git clone https://github.com/mmabrouk/chatgpt-wrapper.git
cd chatgpt-wrapper/emotion_detection
docker build -t emotion_detector .
docker run --rm -it --host net --gpus all emotion_detector
git clone https://github.com/mmabrouk/chatgpt-wrapper.git
cd chatgpt-wrapper/diffusion_model
pip install transformers
# generate a huggingface token
huggingface-cli login
# move that token to `diffusion_model/`
sh build.sh
sh run.sh
My usecase is to host on raspberry pi's, the run.sh
will start a webserver on port 8088, and A GET request with a text prompt like
http://127.0.0.1:8088/?prompt=panda eating ice cream
To reduce the time lag, the images have been cached to chatgptpy/anime_expressions
categorized by emotions
This includes image slideshow, cached stable diffusion expressions, text to speech, speech to text, chatgpt unofficial api
git clone https://github.com/mmabrouk/chatgpt-wrapper.git
cd chatgpt-wrapper/chatgptpy
Register for azure neural tts api here
put the keys and region in ~/.bashrc
SPEECH_KEY=<aws_speech_key>
SPEECH_REGION=<azure_region>
source ~/.bashrc
Fire up the emotion_detection server and the optional stable diffusion server from steps 1 and 2
map the IPs in chatgptpy/main.py
EMOTION_DETECTION_IP='http://127.0.0.1:5004'
STABLE_DIFFUSION_IP='http://127.0.0.1:8088'
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install git+https://github.com/mmabrouk/chatgpt-wrapper
python main.py
-
Chatgpt wrapper fails sometimes, and we need to switch to some other implementation of chatgpt API and this process goes on
-
The
chatgpt-wrapper
usesplaywright
, Docker implementation of which seems challenging
-
chatgpt-wrapper, pyChatGPT, acheong08/ChatGPT for unofficial ChatGPT API
-
michellejieli for emotion_text_classifier