https://qdrant.tech/blog/qdrant-summer-of-code-24/

 

  * Product
      + Use cases
      + Solutions
      + Benchmarks
      + Demos
      + Pricing
  * Resources
      + Documentation
      + Articles
      + Blog
      + Roadmap
      + Changelog
      + Trust Center
  * Community
      +   Github
      +   Discord
      +   Twitter
      +   Newsletter
      +   Contact us
  * Cloud GitHub

[logo_with_]

  * Home
  * /
  * Blog
  * /
  * Qdrant Summer of Code 24

Qdrant Summer of Code 24

February 21, 2024 * Andre Zayarni
Qdrant Summer of Code 24
Share
   

Google Summer of Code (#GSoC) is celebrating its 20th anniversary
this year with the 2024 program. Over the past 20 years, 19K new
contributors were introduced to #opensource through the program under
the guidance of thousands of mentors from over 800 open-source
organizations in various fields. Qdrant participated successfully in
the program last year. Both projects, the UI Dashboard with
unstructured data visualization and the advanced Geo Filtering, were
completed in time and are now a part of the engine. One of the two
young contributors joined the team and continues working on the
project.

We are thrilled to announce that Qdrant was NOT accepted into the
GSoc 2024 program for unknown reasons, but instead, we are
introducing our own Qdrant Summer of Code program with a stipend for
contributors! To not reinvent the wheel, we follow all the timelines
and rules of the official Google program.

Our project ideas.

We have prepared some excelent project ideas. Take a look and choose
if you want to contribute in Rust or a Python-based project.

 WASM-based dimension reduction viz 

Implement a dimension reduction algorithm in Rust and compile to WASM
and integrate the WASM code with Qdrant Web UI.

 Efficient BM25 and Okapi BM25, which uses the BERT Tokenizer 

BM25 and Okapi BM25 are popular ranking algorithms. Qdrant's
FastEmbed supports dense embedding models. We need a fast, efficient,
and massively parallel Rust implementation with Python bindings for
these.

 ONNX Cross Encoders in Python [?][?]

Export a cross-encoder ranking models to operate on ONNX runtime and
integrate this model with the Qdrant's FastEmbed to support efficient
re-ranking

 Ranking Fusion Algorithms implementation in Rust 

Develop Rust implementations of various ranking fusion algorithms
including but not limited to Reciprocal Rank Fusion (RRF). For
complete list, see: https://github.com/AmenRa/ranx and create Python
bindings for the implemented Rust modules.

 Setup Jepsen to test Qdrant's distributed guarantees 

Design and write Jepsen tests based on implementations for other
Databases and create a report or blog with the findings.

See all details on our Notion page: https://www.notion.so/qdrant/
GSoC-2024-ideas-1dfcc01070094d87bce104623c4c1110

Contributor application period begins on March 18th. We will accept
applications via email. Let's contribute and celebrate together!

In open-source, we trust! 

Related Posts

View all blog posts  
Introducing Qdrant Cloud on Microsoft Azure

Introducing Qdrant Cloud on Microsoft Azure

Learn the benefits of Qdrant Cloud on Azure.

By Manuel Meyer * January 17, 2024
 
Open Source Vector Search Engine and Vector Database - Andrey
Vasnetsov

Open Source Vector Search Engine and Vector Database - Andrey
Vasnetsov

Andrey Vasnetsov, CTO and Co-founder of Qdrant, presents an in-depth
look into the intricacies of their open-source vector search engine
and database, detailing its optimized architecture, data structure
challenges, and innovative filtering techniques for efficient vector
similarity searches.

By Demetrios Brinkmann * January 10, 2024
 
Building LLM Powered Applications in Production - Hamza Farooq |
Vector Space Talks

Building LLM Powered Applications in Production - Hamza Farooq |
Vector Space Talks

Hamza Farooq presents the future of large language models, complex
search, and copilot, discussing real-world applications and the
challenges of implementing these technologies in production.

By Demetrios Brinkmann * January 9, 2024

Stay updated with Qdrant

We will update you on new features and news regarding
Qdrant and Vector Similarity Search.

[                    ]
[                    ]
Subscribe
Product

  * Use cases
  * Solutions
  * Benchmarks
  * Demos
  * Pricing

Community

  *   Github
  *   Discord
  *   Twitter
  *   Newsletter
  *   Contact us

Company

  * Jobs
  * Privacy Policy
  * Terms
  * Impressum
  * Credits

Latest Publications

[icon]

Use Qdrant's Binary Quantization to enhance OpenAI embeddings

[icon]

Combining our most popular features to support scalable machine
learning solutions.

[icon]

Discover points by constraining the space.

  *  
  *  
  *  
  *  
  *  

(c) 2024 Qdrant. All Rights Reserved

Thanks for using Qdrant!

x

Subscribe to our e-mail newsletter if you want to be updated on new
features and news regarding Qdrant.

Like what we are doing? Consider giving us a  on Github.

[                    ]
[                    ] Subscribe