AIDockerCompose

Ecosistema de intérpretes y modelos de IAs vía Docker Compose.

Notas

#!/bin/bash

# Descarga de modelos.
docker exec -it ollama ollama pull gemma

# Descarga y prueba por terminal.
docker exec -it ollama ollama run gemma

Socket Python:

• https://pypi.org/project/websockets/
• https://github.com/python-websockets/websockets/
• https://github.com/python-websockets/websockets/tree/main/src/websockets/sync

Modelos:

• gemma - 5GB
• gemma3 - 3.3GB

Referencias

• https://hub.docker.com/r/ollama/ollama
• https://github.com/ollama/ollama
• https://ollama.com/library
• https://ollama.com/steamdj/llama3.1-cpu-only