franciscobspadaro / llama3-project-fbs-dev Goto Github PK

• Tenha o Docker instalado para executar o arquivo docker-compose.yml para iniciar projetos com ollama + open-webui
• clonar esse repositorio e digitar no terminal :
  • docker-compose up -d

acessar:

http://127.0.0.1:3000/auth/

http://localhost:3000 > not working

baixando um modelo de ia pelo open-webui

all models here : https://github.com/ollama/ollama

docs:

https://hub.docker.com/r/ollama/ollama

https://github.com/ollama/ollama?tab=readme-ov-file

• baixar ollama com docker :

  • docker pull ollama/ollama

• executar ollama version cpu only :

  • docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

• listar containers:

  • docker ps

• acessar container e executar comandos no terminal do container :

  • exemplo : docker exec -it bash
  • docker exec -it acff4a1b5aa2 bash

• executar modelo :

  • ollama run llama3

• listar modelos :

  • ollama list

• remover modelo :

  • ollama remove llama3

• iniciar ou parar o ollama

  • docker container stop ollama
  • docker container start ollama

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/ollama-webui/ollama-webui:main