DEV Community

Join us for the Open Source AI Challenge with pgai and Ollama: $3,000 in Prizes!

dev.to staff on October 30, 2024

We are thrilled to team up with Timescale to bring the community our newest challenge. We think you'll like this one. Running through November 10,...

Read full post

Jônatas Davi Paganini • Oct 30

This looks awesome! I love hackathons!

Jess Lee • Oct 30

Good luck everyone!

programORdie • Oct 31

I don't think my 5 years old laptop with 512mb of GPU ram will be able to run a 7B LLM 😂

Trang Le • Nov 4 • Edited

So many questions since I'm not familiar with LLMs at all:

Does one need existing data stored in PostgreSQL?
Since extensions like pgai and pgvector are written in Python, I assume the AI application should also be written in Python?

Emad Mokhtar • Nov 6

No need to write in Python. You can create a Posgres function and invoke this function as SQL statement from any PG client.

select generate_dag_response("prompt");

This means the chat response is generated from pgai and you are getting it back via Postgres.

Andy Piper • Oct 30 • Edited

Is this compatible with the Open Source AI Definition just ratified by the OSI, please? I don't see Ollama on the list of endorsements there.

MrDoe • Nov 2

Depends on the model you are using. Ollama is basically just a wrapper for llama.cpp and llama.cpp serves as a host for the interference with an LLM. Both, Ollama and Llama.cpp are published under open source licenses, but there are models which are not open source.

Andy Piper • Nov 4

Yes, so the answer is (I think) that this contest is not compatible with the OSI Open Source AI Definition. Thanks.

Dela • Oct 31

If we want to utilize Ollama model, does that mean that we have to host the model ourselves and open the access to public?

Trang Le • Nov 5

Did you get an answer for your question? I think we have to deploy the model, otherwise how would the judges try the mout?

Douglas Fugazi • Oct 30

YAY!!!

Raj Acharya • Oct 31

hell yeah

Emad Mokhtar • Nov 6

I built a CLI that needs to connect to TimeScaleDB and OpenAI. How can I share the credentials with the judges? Otherwise, they can't run the app and I would rather not publish them to my repo.