Add ResearchRadar project

[marwan37]

No description provided.

[dagshub]

Join the discussion on DagsHub!

[strickvl]

You'll also need to update the main README.md at the base of this repo.

[strickvl]

Looks pretty good to me, just some small nits.

Also, you should be sure to run our formatting script on your code before merging (scripts/format.sh).

[htahir1]

V cool - wonder if we can give it a cool name ? Like DocumentClassifier

[strickvl]

V cool - wonder if we can give it a cool name ? Like DocumentClassifier

Ah yes I forgot to mention that too. I think there's still a little bit more to be done around the 'make it a project' thing. DocumentClassifier feels maybe a bit boring. I thought maybe something like this might work?

"ResearchRadar: AI Literature Discovery and Classification Pipeline"

This project demonstrates how AI researchers can build an automated pipeline to discover, classify, and organize research papers relevant to their specific subfields. Using ZenML's end-to-end ML pipelines, researchers can train models to automatically identify papers that align with their research interests—whether it's reinforcement learning, computer vision, NLP, or emerging areas like multimodal models—from across various sources including preprint servers, journals, and conference proceedings.

The system showcases how researchers can fine-tune models to recognize subtle distinctions between related subfields, saving countless hours normally spent manually filtering through the overwhelming volume of AI research being published daily. The comparative analysis pipeline demonstrates whether custom-trained models outperform commercial APIs when identifying highly specialized technical content, helping research teams make informed decisions about their literature review infrastructure.

This framework is ideal for academic labs, industry research groups, and individual AI researchers who need to maintain comprehensive awareness of relevant publications without spending hours each week manually sifting through papers. By deploying the trained model to Hugging Face, teams can create shared resources that help all members stay current with literature relevant to their collective research agenda, streamlining collaboration and reducing duplicate effort in literature reviews.

We'd need a paragraph somewhere in the docs where we explain that this specific implementation focus on LLMOps etc, but that it's easily adapted to user needs. WDYT?

[marwan37]

@strickvl thanks a lot for reviewing this so quickly! I think "ResearchRadar" is super cool. The description is pretty great too 🤓

[marwan37]

@strickvl @htahir1 The workflow is failing due to version incompatibility: runner uses ZenML 0.80.0 client
(requiring projects) but likely connects to a 0.75 server (lacking project endpoints). This is triggering
"Error: Method Not Allowed" on all project related commands. I think we'll need to either update the server or
downgrade the runner's client version for now?

[htahir1]

We're gonna rethink the workflow anyway tbh so lets just ignore that for now

[strickvl]

2 nits, but otherwise LGTM!

[htahir1]

Approved! @marwan37 after this you'd need to add it to the projects-backend repo here https://github.com/zenml-io/zenml-projects-backend and on the website https://zenml.io/projects.. also https://docs.zenml.io/user-guides