Powered by BigDL, ChatGLM3, LLaMA, Clip, Whisper, Tag2Text, multilingual-e5-large, LangChain and inspired by showlab/Vlog, we turn a video into a long document which records visual and audio information. Then we can chat over the record only using Intel CPU.

• 2023.11.16 We replaced LLaMA with ChatGLM3-6b-32k. And we use a multilingual sentence embedding model "multilingual-e5-large". Now VChat has native Chinese Q & A capabilities

English	Chinese

conda create -n vchat python=3.9 -y
conda activate vchat
cd VChat-BigDL
pip install -U -r requirements.txt

conda install -c conda-forge ffmpeg -y

python download_ckpt.py

✅Please save weights to ./checkpoints.

python model_low_bit_optimize.py

python main_gradio.py

You can find the tutorial of VChat here.

Could not create share link. Missing file: D:\anaconda3\envs\vchat\lib\site-packages\gradio\frpc_windows_amd64_v0.2.

Please check your internet connection. This can happen if your antivirus software blocks the download of this file. You can install manually by following these steps:

1. Download this file: https://cdn-media.huggingface.co/frpc-gradio-0.2/frpc_linux_amd64
2. Rename the downloaded file to: frpc_linux_amd64_v0.2
3. Move the file to this location: .\anaconda3\envs\vchat\lib\site-packages\gradio.
4. Give this file executable permissions (For Linux users)

chmod +x frpc_linux_amd64_v0.2

Multiple people using the same demo at the same time will cause an error because the asynchronous running logic is not implemented.

This project is based on BigDL, Vlog, Tag2Text, Whisper, ChatGLM3, LLaMA, multilingual-e5-large, KTS, LangChain, Douyin_Tiktok_Scraper_PyPi.