raphaelty
raphaelty on Hacker News
Posted by
raphaelty on Saturday May 23, 2026 @11:40AM
from the github.com dept.
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
Posted by
raphaelty on Sunday March 01, 2026 @08:47PM
from the github.com dept.
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.
Posted by
raphaelty on Thursday February 12, 2026 @01:10PM
from the show-hn dept.
https://github.com/lightonai/next-plaid
Releasing ColGREP today, made using our open-source multi-vector database, it support grep like filtering while adding an extra input to rank output of grep based on semantic similarity. ColGREP is packed with strong code retrieval models we designed and run 100% locally.
Posted by
raphaelty on Thursday February 12, 2026 @11:22AM
from the huggingface.co dept.
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
Very cool to spot such missing feature from Vision Language Models
Very interesting, willing to try burn
Blog introducing late-interaction models with max-similarity scoring function visualization. pylate-rs is a rust crate providing python and wasm bindings.
Posted by
raphaelty on Tuesday July 08, 2025 @09:40AM
from the lightonai.github.io dept.
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
Posted by
raphaelty on Wednesday June 04, 2025 @05:46AM
from the show-hn dept.
https://github.com/lightonai/fast-plaid
Happy to release FastPlaid, which aim to ease and accelerate ColBERT and ColPali retrieval
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.
Posted by
raphaelty on Friday December 20, 2024 @03:19AM
from the twitter.com dept.
Posted by
raphaelty on Thursday October 03, 2024 @05:33PM
from the show-hn dept.
Posted by
raphaelty on Thursday September 12, 2024 @05:35AM
from the show-hn dept.
https://github.com/lightonai/ducksearch
Releasing a Pythonic BM25 made with DuckDB. Few differences with FTS search extension from DuckDB as this tool pre-compute bm25 score, perform approximation, is batch compatible
Posted by
raphaelty on Thursday August 29, 2024 @11:00AM
from the show-hn dept.
Posted by
raphaelty on Sunday May 26, 2024 @05:39PM
from the show-hn dept.
https://github.com/raphaelsty/LeNLP
LeNLP is a toolbox dedicated to NLP, made with Rust, dedicated to Python
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
Amazed by 3d-force-graph js library
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
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.
The ask button is provided by chatgpt api here
Posted by
raphaelty on Wednesday March 20, 2024 @05:58PM
from the show-hn dept.
https://github.com/raphaelsty/knowledge
My personal knowledge base is hosted on GitHub at https://raphaelsty.github.io/knowledge/. It scans the documents I like every day using GitHub Action, Zotero, HackerNews upvote and Github Likes. It's not yet optimized for smartphones. It cost me $5 to host it for a year.
Posted by
raphaelty on Wednesday February 28, 2024 @06:35AM
from the show-hn dept.
The library is clean and well documented
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
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.