searxng

• docker pull searxng/searxng
• docker run -d -p 4000:8080 -e "BASE_URL=http://localhost:4000/" -e "INSTANCE_NAME=searxng" searxng/searxng

F5-TTS

Env

• conda create -n f5tts python=3.10
• conda activate f5tts

(apt install -y ffmpeg)

Python

• pip uninstall torch torchvision torchaudio transformers
• pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
• pip install transformers

Git

• git clone https://github.com/SWivid/F5-TTS.git

Run

• cd F5-TTS
• pip install -e .
• f5-tts_infer-gradio --port 7865 --host 0.0.0.0 --share

Kotaemon AI/RAG

Install on docker

• docker run -e GRADIO_SERVER_NAME=0.0.0.0 -e GRADIO_SERVER_PORT=7860 -p 7860:7860 --name kotaemon -d ghcr.io/cinnamon/kotaemon:main-full 
• no --it --rm

use axolotl for trainning

Env

• no internet
• qlora_root c:\qlora
• gguf_root c:\gguf

Dataset 

• c:/qlora/output_dataset/instruction_dataset.parquet

PS:Axolotl

• docker run --gpus '"all"' --rm -it winglian/axolotl:main-latest

PS:Dataset

• docker cp C:\qlora\output_dataset\instruction_dataset.parquet container_name:/workspace/axolotl/examples/instruction_dataset.parquet

PS:LLM

• docker cp C:\Meta-Llama-3.1-8B container_name:/workspace/axolotl/examples/Meta-Llama-3.1-8B/

Axolotl:Qlora

• open ./examples/llama-3/qlora.yml find and modify path of llm and parquet

Axolotl:Trainning

• CUDA_VISIBLE_DEVICES="" python -m axolotl.cli.preprocess examples/llama-3/qlora.yml
• accelerate launch -m axolotl.cli.train examples/llama-3/qlora.yml

Axolotl:Test(need internet)

• accelerate launch -m axolotl.cli.inference examples/llama-3/qlora.yml --lora_model_dir="./outputs/qlora-out" --gradio

Axolotl:Merged

• python3 -m axolotl.cli.merge_lora examples/llama-3/qlora.yml --lora_model_dir="./outputs/qlora-out"

PS:Export

• docker cp container_name:/workspace/axolotl/outputs/qlora-out/merged C:\merged

GGUF

• convert to merged_f16.gguf

Ollama

• ollama run merged

unsloth

Conda

• conda install -c conda-forge xformers
• pip install xformers
• conda config --add channels conda-forge
• conda update conda

Env

• conda create --name unsloth python=3.11 pytorch-cuda=12.1 pytorch cudatoolkit -c pytorch -c nvidia -y
• conda activate unsloth
• pip install xformers

Install

• pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
• pip install --no-deps trl peft accelerate bitsandbytes

perplexica update

Check

• docker volume ls | perplexica_backend-dbstore
• docker run -it --rm -v perplexica_backend-dbstore:/data busybox ls -l /data

Backup

• docker run --rm -v perplexica_backend-dbstore:/data -v C:/backup:/backup busybox tar cvf /backup/perplexica_backend-dbstore.tar /data

Remove

• docker remove old container

Update

• goto perplexica of directory and run git pull origin master
• check config.toml and docker-compose.yaml

ReBuild

• goto perplexica of directory and docker compose up -d --build

Recovery

• docker run --rm -v perplexica_backend-dbstore:/data -v C:/backup:/backup busybox tar xvf /backup/perplexica_backend-dbstore.tar -C /data

Check

• docker run -it --rm -v perplexica_backend-dbstore:/data busybox ls -l /data

anythingllm update(update 2024.09.23)

Get-New

• docker pull mintplexlabs/anythingllm

Remove

• docker remove old container

Run

• docker run -d -p 3001:3001 --cap-add SYS_ADMIN -v C:/anythingllm/storage:/app/server/storage -v C:/anythingllm/env.txt:/app/server/.env -e STORAGE_DIR="/app/server/storage" --add-host=host.docker.internal:host-gateway --name anythingllm mintplexlabs/anythingllm

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

use github to pull to docker and update

• git clone https://github.com/Mintplex-Labs/anything-llm
• copy ./docker to ./anythingllm
• into ./anything-llm/anythingllm and rename .env.example to .env
• PS>docker compose up -d (--build)

change port number

• .env
  SERVER_PORT=3001
• docker-compose.yml
  ports:
  - "3001:3001"

change name

• docker-compose.yml
  name: anythingllm
  container_name: anythingllm

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

Perplexica - AI Search

Before

• install git & lfs
• install docker
• install ollama and llm

Install

• git clone https://github.com/ItzCrazyKns/Perplexica
• goto directory of perplexica
• rename .\Perplexica\sample.config.toml .\Perplexica\config.toml
• powershell> docker compose up -d (--build)
• open localhost:3000

Default Port Change [3001]

• open config.toml
• find [GENERAL] PORT = 3001 # Port to run the server on
• change 3001 to your_port
• open docker-compose.yaml
• find ports: - 3001:3001
• change 3001 to your_port both
• find 2line like NEXT_PUBLIC
• change 3001 to your_port

Run on public IP

• open config.toml
• find [API_ENDPOINTS] SEARXNG = and OLLAMA =
• change to your_ip
• open docker-compose.yaml
• find 2line like NEXT_PUBLIC_
• change to your_public_ip
• config your win's env 
• OLLAMA_HOST=0.0.0.0

UPDATE

• stop perplexica on docker
• goto directory of perplexica
• git pull origin master
• check config.toml and docker-compose.yaml
• powershell> docker compose up -d --build

Bark

 Bark

• Git
  git clone https://github.com/C0untFloyd/bark-gui
• Anaconda
• Install
  pip install .
  pip install -r requirements.txt
• Run
  python webui.py
• WEB
  Open http://127.0.0.1:7860
• ERROR:bark Audio.__init__() got an unexpected keyword argument 'source'
  pip uninstall gradio
  pip install gradio==3.50.2