{"id":49,"date":"2026-08-17T00:34:49","date_gmt":"2026-08-17T03:34:49","guid":{"rendered":"https:\/\/telapreta.dev.br\/blog\/index.php\/docker-ollama-openwebui-ia-soberana\/"},"modified":"2026-08-17T16:44:43","modified_gmt":"2026-08-17T19:44:43","slug":"docker-ollama-openwebui-ia-soberana","status":"publish","type":"post","link":"https:\/\/telapreta.dev.br\/blog\/index.php\/docker-ollama-openwebui-ia-soberana\/","title":{"rendered":"Docker Ollama + OpenWebUI: Sua IA Soberana e Barata Rodando Localmente"},"content":{"rendered":"
\n

Tenha o seu pr\u00f3prio ChatGPT privado, sem pagar mensalidades e com 100% de privacidade dos dados da sua empresa ou homelab.<\/em><\/p>\n

\n

\ud83e\udd16 O que \u00e9 o Ollama e o Open WebUI?<\/h2>\n

O Ollama<\/strong> permite executar modelos open-source avan\u00e7ados (como Llama 3, Mistral, Qwen e DeepSeek) localmente na sua m\u00e1quina ou servidor. Combinado com o Open WebUI<\/strong>, voc\u00ea obt\u00e9m uma interface id\u00eantica ao ChatGPT com suporte a arquivos, RAG e m\u00faltiplos usu\u00e1rios.<\/p>\n

\ud83d\udc33 Deploy com Docker Compose<\/h2>\n
\nversion: '3.8'\n\nservices:\n  ollama:\n    image: ollama\/ollama:latest\n    container_name: ollama\n    ports:\n      - \"11434:11434\"\n    volumes:\n      - ollama_storage:\/root\/.ollama\n    restart: unless-stopped\n\n  open-webui:\n    image: ghcr.io\/open-webui\/open-webui:main\n    container_name: open-webui\n    ports:\n      - \"8080:8080\"\n    environment:\n      - OLLAMA_BASE_URL=http:\/\/ollama:11434\n    volumes:\n      - openwebui_storage:\/app\/backend\/data\n    restart: unless-stopped\n\nvolumes:\n  ollama_storage:\n  openwebui_storage:\n<\/pre>\n
\u26a1 Baixando os Modelos<\/h2>\n
Para baixar seu primeiro modelo, execute dentro do container:<\/p>\n
\ndocker exec -it ollama ollama run llama3\n<\/pre>\n
\n
Artigo originalmente publicado por Fabio Silva<\/strong> \u2014 Arquiteto de Solu\u00e7\u00f5es em Cloud, DevOps e IA Generativa.<\/em><\/p>\n<\/div>\n
\n
\n
      <\/span>      <\/span>      <\/span>    <\/div>\n
      \ud83d\udcc4 app.py \u2014 Visual Studio Code [Linux x64]<\/span>    <\/div>\n
Copilot Enabled \ud83e\udd16<\/div>\n<\/p><\/div>\n
\n
      \u26a1<\/span> app.py    <\/div>\n<\/p><\/div>\n
\n
# GitHub Copilot AI Code Execution<\/span>\r\nimport<\/span> os\r\nimport<\/span> sys\r\n\r\ndef<\/span> main<\/span>():\r\n    print<\/span>(\"Running in VS Code Linux Environment...\"<\/span>)\r\n\r\nif<\/span> __name__ == \"__main__\"<\/span>:\r\n    main<\/span>()<\/pre>\n<\/p><\/div>\n
\n
      \ud83d\udda5\ufe0f TERMINAL (bash)<\/span> \u2014 ubuntu@telapreta-server:~<\/span>    <\/div>\n
      fabio@ubuntu-linux<\/span>:~\/projects<\/span>$ gh copilot explain "def main():"<\/span>    <\/div>\n<\/p><\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"
Tenha o seu pr\u00f3prio ChatGPT privado, sem pagar mensalidades e com 100% de privacidade dos dados da sua empresa ou homelab. \ud83e\udd16 O que \u00e9 o Ollama e o Open WebUI? O Ollama permite executar modelos open-source avan\u00e7ados (como Llama 3, Mistral, Qwen e DeepSeek) localmente na sua m\u00e1quina ou servidor. Combinado com o Open … Ler mais<\/a><\/p>\n","protected":false},"author":1,"featured_media":50,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,5],"tags":[],"class_list":["post-49","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ia-agentes","category-infraestrutura"],"_links":{"self":[{"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/posts\/49","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/comments?post=49"}],"version-history":[{"count":3,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/posts\/49\/revisions"}],"predecessor-version":[{"id":226,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/posts\/49\/revisions\/226"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/media\/50"}],"wp:attachment":[{"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/media?parent=49"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/categories?post=49"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/telapreta.dev.br\/blog\/index.php\/wp-json\/wp\/v2\/tags?post=49"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}