Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)
| Date | Stars |
|---|---|
| 2026-07-24 | 673 |
| 2026-07-25 | 673 |
| 2026-07-28 | 673 |
| 2026-07-30 | 673 |
| 2026-08-06 | 673 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
> 🧪 We're looking for beta testers for our <a href='https://answerbot.app'>virtual assistant</a> widget. <a href = 'mailto:[email protected]'>Contact us</a> if you're interested in using it on your website. <p align="center"> <img src="https://github.com/koursaros-ai/nboost/raw/master/.github/banner.svg?sanitize=true" alt="Nboost" width="70%"> </p> <p align="center"> <a href="https://cloud.drone.io/koursaros-ai/nboost"> <img src="https://cloud.drone.io/api/badges/koursaros-ai/nboost/status.svg" /> </a> <a href="https://pypi.org/project/nboost/"> <img src="https://img.shields.io/pypi/pyversions/nboost.svg" /> </a> <a href="https://pypi.org/project/nboost/"> <img alt="PyPI" src="https://img.shields.io/pypi/v/nboost.svg"> </a> <a href='https://nboost.readthedocs.io/en/latest/'> <img src='https://readthedocs.org/projects/nboost/badge/?version=latest' alt='Documentation Status' /> </a> <a href="https://www.codacy.com/app/koursaros-ai/nboost?utm_source=github.com&utm_medium=referral&utm_content=koursaros-ai/nboost&utm_campaign=Badge_Grade"> <img src="https://api.codacy.com/project/badge/Grade/a9ce545b9f3846ba954bcd449e090984"/> </a> <a href="https://codecov.io/gh/koursaros-ai/neural_rerank"> <img src="https://codecov.io/gh/koursaros-ai/neural_rerank/branch/master/graph/badge.svg" /> </a> <a href='https://github.com/koursaros-ai/nboost/blob/master/LICENSE'> <img alt="PyPI - License" src="https://img.shields.io/pypi/l/nboost.svg"> </a> </p> <p align="center"> <a href="#what-is-it">Highlights</a> • <a href="#overview">Overview</a> • <a href="#benchmarks">Benchmarks</a> • <a href="#install-nboost">Install</a> • <a href="#getting-started">Getting Started</a> • <a href="#kubernetes">Kubernetes</a> • <a href="https://nboost.readthedocs.io/">Documentation</a> • <a href="#tutorials">Tutorials</a> • <a href="#contributing">Contributing</a> • <a href="./CHANGELOG.md">Release Notes</a> • <a href="https://koursaros-ai.github.io/">Blog</a> </p> <h2 align="center">What is it</h2> ⚡**NBoost** is a scalable, search-engine-boosting platform for developing and deploying state-of-the-art models to improve the relevance of search results. <p align="center"> <img src="https://github.com/koursaros-ai/nboost/raw/master/.github/overview.svg?sanitize=true" width="100%"> </p> Nboost leverages finetuned models to produce domain-specific neural search engines. The platform can also improve other downstream tasks requiring ranked input, such as question answering. <a href = 'mailto:[email protected]'>Contact us to request domain-specific models or leave feedback</a> <h2 align="center">Overview</h2> The workflow of NBoost is relatively simple. Take the graphic above, and imagine that the server in this case is Elasticsearch. <p align="center"> <img src="https://github.com/koursaros-ai/nboost/raw/master/.github/conventional.svg?sanitize=true" width="80%"> </p> In a **conventional search request**, the user sends a query to *Elasticsearch* and gets back the results. <p align="center"> <img src="https://github.com/koursaros-ai/nboost/raw/master/.github/nboost.svg?sanitize=true" width="80%"> </p> In an **NBoost search request**, the user sends a query to the *model*. Then, the model asks for results from *Elasticsearch* and picks the best ones to return to the user. <h2 align="center">Benchmarks</h2> > 🔬 Note that we are evaluating models on differently constructed sets than they were trained on (MS Marco vs TREC-CAR), suggesting the generalizability of these models to many other real world search problems. <center> Fine-tuned Models | Dependency | Eval Set | Search Boost<a href='#benchmarks'><sup>[1]</sup></a> | Speed on GPU ----------------------------------------------------------------------------
Excerpt of 23,688 characters
Read on GitHub
739
514
6
2
2
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:82e19d4c16756409, topic:deep-learning, topic:pytorch, topic:tensorflow