Skip to main content

Youtube Autonomous Docker Ollama Module

A module based on docker to use Ollama and make AI models available through local endpoints.

Important message

This module will no longer be maintained due to the migration to llamacpp (yta-fastapi-docker-llamacpp), which is working faster.


Proyect created based on this post: https://dev.to/savvasstephnds/run-deepseek-locally-using-docker-2pdm. I've modified it a bit by installing a different model, as I used the deepseek-r1:latest instead of the deepseek-r1:7b (you can check the list here: https://www.ollama.com/library/deepseek-r1).


Instructions

  1. Install the docker container that includes ollama. This command will create a local ollama-models folder in which the models will be downloaded (~2.6GB).
docker compose up -d ollama
  1. Check that the container has been succesfully installed and is running locally by accessing to the following url. A Ollama is running message should appear in the web navigator:
http://localhost:11434/
  1. Install Deepseek to be used in the Ollama container we've installed before, that will be downloaded (~5.2GB):
docker compose exec ollama ollama pull deepseek-r1:latest
  1. Request to the http://localhost:11434/api/generate endpoint (using a POST method and providing the model and the parameters needed to obtain a response).
payload = {
    'model': model.value,
    'prompt': prompt,
    'stream': False
}

response = requests.post(
    url = OLLAMA_GENERATE_URL,
    json = payload
)

Other models

*To install any other model, look for it in the list mentioned on top of this readme file and install it with the same command as before. If you want to install the llama3.2-vision:latest, just execute this command below:

docker compose exec ollama ollama pull llama3.2-vision:latest

Final command

Execute this commands once you've cloned the project to set up the docker container and the models:

docker compose up -d ollama
docker compose exec ollama ollama pull deepseek-r1:latest
docker compose exec ollama ollama pull gemma3:latest

To update the image

If you want to update the image because the latest was built a long time ago and you want the most recent, you can use the docker compose pull ollama command that will pull the real latest one.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

yta_docker_ollama-0.0.6.tar.gz (4.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

yta_docker_ollama-0.0.6-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file yta_docker_ollama-0.0.6.tar.gz.

File metadata

  • Download URL: yta_docker_ollama-0.0.6.tar.gz
  • Upload date:
  • Size: 4.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.0 CPython/3.9.0 Windows/10

File hashes

Hashes for yta_docker_ollama-0.0.6.tar.gz
Algorithm Hash digest
SHA256 e6caa8e003b47baf0bcc0ffc1dfe2029b77e274f38f94548d0ea66081bcc99c6
MD5 0446371e86b03d46e17b65f380c415de
BLAKE2b-256 f8f0ce9304c7d5eaf1c7e42b496b4595e0538ba923e34e8a2f1743478aa8b379

See more details on using hashes here.

File details

Details for the file yta_docker_ollama-0.0.6-py3-none-any.whl.

File metadata

  • Download URL: yta_docker_ollama-0.0.6-py3-none-any.whl
  • Upload date:
  • Size: 7.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.0 CPython/3.9.0 Windows/10

File hashes

Hashes for yta_docker_ollama-0.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 b823461877b724be7b5d0bd3e46a8d4be7c607c6860ea8e282985add81a67d52
MD5 49ae0b28c757f31239759c736f5b1ae1
BLAKE2b-256 817bc656b90b381accd5be375f14e28321e272010c32754f54ce9e3e3515961a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page