Cohere and Qdrant Multilingual Semantic Search Hackathon

Team formation and Hack Commences

This is an awesome guide for beginners by Kacper Lukawski

Introduction to Vector Databases - by Qdrant 

Introduction, Lablab.ai mission and vision, Paweł Czech and Mathias Asberg

Kick-Off Stream

Intodiction Talk from Hackathon tech partners about possibilities and challenges you will have during this event

Cohere x Qdrant opening

You will discover lablab.ai platform, also Hackathon challenge, tech and prizes

Hackatho guide

Intro to Semantic Search part 1

Intro to Semantic Search part 2

Tips & Tricks for using Qdrant

Qdrant x Cohere: Powering Semantic Search

It's the last moment you can submit your solution for the Hackathon

Submission Deadline

metaprank

shutty

Recommendations cold-start problem is not actually a problem, if you leverage content and item metadata to build your recommendations. To showcase this idea we build a movie recommender, so you can visually see the difference between collaborative-filtering and content recommendations. 

We made two PRs to an existing open-source project Metarank:
* support semantic recommendations with cohere-ai and sentence-transformers embeddings
* use qdrant as a vector search engine to quickly perform vector similarity search

With these two PRs merged building such a recommender is just a matter of a few lines of YAML code.

But the semantic-similarity approach is not only about movies, but can be applied more generically in traditional places like e-commerce. For example, in fashion with high inventory churn, being able to recommend something for new clothes having zero feedback is really valuable.

Content-based semantic recommendations with cohere-ai embeddings, qdrant vector search, and metarank to glue things together.

"metaprank team on Cohere and Qdrant Multilingual Semantic Search Hackathon Hackathon"

Team Idea

Submission