Deploying an LLM-Powered Django App | Ollama + Fly GPUs
Learn how to run LLMs locally, integrate with your Python/Django apps, self-host Ollama with one file and finally deploy an LLM-Powered Django app using self-hosted Ollama running on Fly GPUs.
Source code: https://github.com/katiayn/django-fridge
Ollama demo app: https://github.com/katiayn/fly-katia-...
Related videos:
Fly.io networking: • Fly Domains Explained | .fly.dev, .interna...
Related links:
Ollama website: https://ollama.com/
Ollama Python Package on PyPI: https://pypi.org/project/ollama/
How to install flyctl: https://fly.io/docs/flyctl/install/
Fly GPU: https://fly.io/gpu
Fly GPUs Docs: https://fly.io/docs/gpus/
Regions with GPUs: https://fly.io/docs/gpus/#regions-wit...
Fly.io Django Lander: https://fly.io/django
Fly.io Django Blog: https://fly.io/django-beats/
Get $50 credits to try out Fly.io: https://fly.io/hello/katia
Video re-uploaded for sound quality improvements.