News for hackers. Stuff that matters.

raphaelty

Introducing a new version of knowledge which is my search engine / bookmark system in which I designed my own AI feed without the noise of X
Re:A semantic Code Search CLI but with grep filters on Sunday March 01, 2026 @08:47PM (#47212887)
While semantic search shine at various tasks including advanced search engine and recommender systems, it did not shine that much on coding task so far appart from benchmarks available in papers. We think standard semantic code search tools lack of advanced filtering features. A key element to code search is to be able to reduce "search space", i.e reduce the set of likely candidates given the intent of the user or the coding agent. We think semantic search alone is not enough and needs to be paired with advanced filters such as GREP filters to succeed.
Very interesting, wondering if there are other heavily used algorithm which could benefit a lot from a "Flash" version but don't have one today
Re:Do LLMs Identify Fonts? on Wednesday July 30, 2025 @04:52AM (#44732111)
Very cool to spot such missing feature from Vision Language Models
Re:Multiplatform Matrix Multiplication Kernels on Friday July 18, 2025 @05:19PM (#44609951)
Very interesting, willing to try burn
Re:Information Retrieval, spawn Colbert in ms on Tuesday July 08, 2025 @09:40AM (#44499863)
Blog introducing late-interaction models with max-similarity scoring function visualization. pylate-rs is a rust crate providing python and wasm bindings.
Very interesting work! Starred the project. Would love to see such features integrated into the compiler itself Anyway, fully agree with you on the complementarity of ML and Rust
I created my personnal search engine to index and retrieve content I like. I like the idea of keeping track of content you like without too much effort.

https://github.com/raphaelsty/knowledge

I did not find yet a solution that suit me for knowledge which is not an online webpage / pdf.

Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @09:55AM (#39778537)
Thank you for this ! Knowledge is primarly inspired by http://www.semanlink.net/sl/home
Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @05:23AM (#39776376)
Author here, I like the idea to have a public and personal search-engine. I'd love to deep dive in some people bookmarks such as expert in NLP field in order to get clue / a point of view on problem I want to solve but those informations are not available most of the time
Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @05:16AM (#39776333)
Amazed by 3d-force-graph js library
Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @04:18AM (#39775955)
It upload content some of my friends like (github stars) and they have very good taste, so when I'm looking for a document / information on a new topic in machine learning or databases I like to give it a chance
Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @04:04AM (#39775870)
I did develop this when I was PhD student in NLP. I think it's fine to learn to develop a personal search system if you want to learn.
Re:Show HN: Personal Knowledge Base Visualization on Thursday March 21, 2024 @03:54AM (#39775824)
The ask button is provided by chatgpt api here
Re:Xplique Is a Neural Networks Explainability Toolbox on Friday February 02, 2024 @09:50AM (#39229163)
The library is clean and well documented
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @02:14PM (#38323235)
You could recommend content based on user query, tag content produced by the user, use colbert as part of a ChatBot to show evidences to the user questions
Re:Show HN: ColBERT Build from Sentence Transformers on Saturday November 18, 2023 @09:03AM (#38319703)
Yes, ColBERT is fast because you can pre-compute most embeddings. It's important to compute documents embeddings only once. neural-cherche do not compute embeddings on the fly and the retrieve method ask for queries and documents embeddings rather than queries and documents texts.

Documents and queries embeddings can be obtained using .encode_documents and .encode_queries methods

I save most of my embeddings (python dictionnary with documents id as key and embeddings as values) using joblib in a Bucket in the cloud. I don't really know if it's a good pratice but it does scale fine to few millions documents for offline (no real-time) applications.

Older »