kawakamimoeki / baran Goto Github PK
View Code? Open in Web Editor NEWText Splitter for Large Language Model (LLM) datasets.
Home Page: https://rubygems.org/gems/baran
License: MIT License
Text Splitter for Large Language Model (LLM) datasets.
Home Page: https://rubygems.org/gems/baran
License: MIT License
I noticed that when splitting text, the chunks have a cursor
position which changes by length of 2. I had assumed this was meant to point to the character position for the start of the text?
In this block of code:
https://github.com/kawakamimoeki/baran/blob/main/lib/baran/text_splitter.rb#L21C7-L26C10
Is the intention to do cursor += chunk[:text].length
rather than cursor += chunk.length
?
immediately didn't work. Not sure what's up
Hi,
i would like to ask if you would consider adding metadata to text chunks. A example use case would be to store the page number a chunk was extracted from, like a PDF. We started a discussion over at langchainrb about this patterns-ai-core/langchainrb#318
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.