Abdul Qadeer@abdul_qadeer525

Ranking system
is under improvement

Events attended

Submissions made

Pakistan

2 years of experience

About me

I am a data scientist who has an interest in developing products to help people.

Socials

🤝 Top Collabolators

Abdul Qadeer

I am a data scientist who has an interest in developing products to help people.

Carlos Salgado

Python Test Engineer and AI/ML Enthusiast. Master's in medical image processing and bachelor's in mechatronics engineering.

I am excited to learn how to embed difficult datasets. I am interested in working with small models. Furthermore, I am interested in testing and finding the best search algorithms for different embedding’s, different tasks, different datasets.

Sandra Ashipala

👋 Hi, I'm Sandra, My journey in software development/engineering has been shaped by diverse teams that unite individuals from varied backgrounds and cultures, fostering an environment where innovation thrives. These international collaborations have not only expanded my professional horizons but also deepened my appreciation for the transformative power of diversity in driving innovation. In addition to my front-end skills, I am currently enhancing my skills in DevOps. Beyond my professional pursuits, I am passionate about contributing to projects that pave the way for a more sustainable future for our planet 🌱.

🤓 Submissions

Anomaly detection in metadata of documents

Using AI to find mistakes in the metadata of PDF documents. The user can upload a document without metadata, the upload is ingested using unstructured.io. Then AI(Mistral) adds metadata, which is displayed in the UI. The user could now copy that out and use to assign metadata to his documents. The user can then upload another document with the human given metadata, or load a lot of documents with correct metadata from a vectorstore (vectara). The user can also provide his own metadata for the document as a textstring. Mistral then compares the two versions of the metadata and tells the user the differences and similarites between both sets of metadata.

Hackathon link