News for hackers. Stuff that matters.

raphaelty

Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @08:47AM (#38319541)
It's because of the loss of the model. I ask the model to produce a higher similarity between the query and the positive document rather than between the query and the negative document. I'll add more losses soon so there are more choices
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @08:44AM (#38319521)
Nice, it might already be compatible with BGE, I'll try it and add it to the documentation soon
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @07:40AM (#38318887)
Yes exactly
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @07:23AM (#38318734)
In the documentation there is an evaluation module with detailed informations. The idea is to gather relevant pairs of queries and documents that are not part of the training set. Then the idea is to measure, using various metrics, how your model can retrieve accurate documents.
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @07:20AM (#38318703)
Hi, there is a single loss right now, but I plan to add some Sentence Transformers losses. ColBERT is slow as a retriever, but is quite efficient as a Ranker on GPU (way faster than cross-encoder). I plan to release pre-trained checkpoints on HuggingFace with benchmarks using BEIRand inference speed info.
Re:Minimalist semantic search with Cherche 2.0 on Monday May 08, 2023 @12:33PM (#35863629)
Cherche 2.0 is now available, and it's been optimized for batch-computing, along with other new features. Whether you're a practitioner, researcher, or hacker interested in semantic search, Cherche might be a good fit for your needs.
I build my personnal search engine which record things I like on twitter, blog posts etc.. It automatically calls those APIs using Github Action and store them in an open source database (json file)

I actualy use it at least twice a week to retrieve content I bookmarked, so I'm happy to have created such a tool.

The app: https://raphaelsty.github.io/knowledge/?query=bayesian

The Github: https://github.com/raphaelsty/knowledge

Re:Neural Search for medium sized corpora on Monday January 10, 2022 @01:40PM (#29879422)
I think 10 million documents is a large corpus. A retriever like Sklearn TfIdf will have a hard time handling it in a reasonable time. The main goal of Cherche is to prototype a neural search engine quickly and with a large choice of retrievers and rankers for corpus sizes < 1 million documents which is a common use case in the industry.

Search implements a wrapper of the Python ElasticSearch client that is scalable and dedicated to corpora composed of tens of millions of documents.

Re:Neural Search for medium sized corpora on Monday January 10, 2022 @09:39AM (#29875450)
Thank you for these great resources.
Re:Neural search library in Python for medium-sized corpora on Sunday January 09, 2022 @10:57AM (#29864352)
Hi,

1) The dependency on the Elasticsearch python client allows Elasticsearch to be used as a retriever. The same goes for Lunr. It might be interesting to separate the different dependencies.

2) Of course I'll update it.

Re:Neural search library in Python for medium-sized corpora on Sunday January 09, 2022 @10:50AM (#29864267)
I'm more used to reading than posting on Hacker News. I'll do better next time. :)

Neural search library in Python for medium-sized corpora

https://github.com/raphaelsty/chercheCherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers. Cherche is meant to be used with small to medium sized corpora. Cherche's main strength is its ability to build diverse and end-to-end pipelines.

( Read More... | 4 comments | 4 points | on HN )
Re:Knowledge Graphs Emb. With PyTorch on Saturday October 17, 2020 @11:17AM (#24810599)
Knowledges graphs are structured resources in the form of graphs that contain knowledge. These resources are used in a large number of applications linked to the machine learning.

I just published a library dedicated to knowledges graphs embeddings. The Mkb API is inspired by Scikit Learn. I provide modular tools for building latent graph representations.