Chroma update

 

Backup

• docker volume ls
• docker run --rm -v chroma_chroma-data:/data -v C:/backup:/backup busybox tar cvf /backup/chroma_chroma-data.tar /data

Remove

• docker remove old container

Get-New

• get new version from https://github.com/chroma-core/chroma/releases
• docker pull ghcr.io/chroma-core/chroma:0.5.4
• docker run -p 8000:8000 ghcr.io/chroma-core/chroma:0.5.4

Recovery

• docker run --rm -v chroma_chroma-data:/data -v C:/backup:/backup busybox tar xvf /backup/chroma_chroma-data.tar -C /data
• docker run -it --rm -v chroma_chroma-data:/data busybox ls -l /data

SenseVoice

Get 

• git clone https://github.com/FunAudioLLM/SenseVoice.git

Env

• conda create -n sensevoice python=3.8
• conda activate sensevoice

Install

• cd sensevoice
• pip install -r requirements.txt

Run

• python webui.py

Change port

• demo.launch(server_port=your_portnumber,share=True,server_name='your_ip')

Chroma for AI(update 2024.09.23)

Get1

•  docker pull ghcr.io/chroma-core/chroma:0.5.4

Get2

• git clone https://github.com/chroma-core/chroma.git
• docker compose up -d

Update1

• watch version on https://github.com/chroma-core/chroma
• docker pull ghcr.io/chroma-core/chroma:version

Update2

•  goto chroma of directory
• PS>docker compose up -d --build

-----------------------------------------------

you can use github to pull to docker

• git clone https://github.com/chroma-core/chroma
• cd ./chroma and copy compose-env.windows .env
• rename docker-compose.yml to docker-compose-any.yml
• copy docker-compose.server.example.yml to docker-compose.yml
• PS>docker compose up -d (--build)

LangFlow

Github

• git clone https://github.com/langflow-ai/langflow.git

Docker

• cd langflow
• copy ./docker_example ./langflow (or your_name_for_docker)
• open and config(ChangePort) langflow/langflow  (or your_name_for_docker)/docker-compose.yml
• PowerShell>
  cd langflow/langflow  (or your_name_for_docker)
  docker compose up -d (--build)

Run

• Open http://localhost:7860/store and Click API_Key
• Login https://www.langflow.store/ and get API-Key

ChatTTS

It good than Bark

Github

• git clone https://github.com/2noise/ChatTTS.git
• cd ChatTTS

Env

• conda create -n chattts python=3.8
• conda activate chattts

Install

• pip install --upgrade -r requirements.txt
• pip install -r requirements.txt

Run

• python examples/web/webui.py

Change port, public link

• open ChatTTS\examples\web\webui.py
• find
  demo.launch()
• and add args
  server_name='0.0.0.0'
  server_port=7860
  share=True

LivePortrait

• ffmpeg (https://www.ffmpeg.org/)
  download > win > Windows builds from gyan.dev > release builds > ffmpeg-release-full.7z
  move bin/*.exe to windows/system32/
• conda create -n liveportrait python=3.9 and activate it
• d1: git clone https://github.com/KwaiVGI/LivePortrait
• d2: git clone from hugiingface https://huggingface.co/KwaiVGI/LivePortrait
  move both directory insightface and liveportrait to d1 ./pretrained_weights/ 
• run for cmd
  first: python  inference.py to create sample in d1 ./animations
  custom: python  inference.py -s d1 .\LivePortrait\assets\examples\source\?.jpg d1 .\LivePortrait\assets\examples\driving\?.mp4 and see outpurt in d1 ./animations
• run for webgui
  python app.py and open 127.0.0.1:8890
  public: modify d1 .\LivePortrait\src\config\argument_config.py server_ip, server_port, and share for true