Developed a high-performance food ordering app using React, Tailwind, React Router and Redux-toolkit leveraging Swiggy’s Live API to deliver real-time data to users.
-
Updated
Jul 9, 2024 - JavaScript
Developed a high-performance food ordering app using React, Tailwind, React Router and Redux-toolkit leveraging Swiggy’s Live API to deliver real-time data to users.
The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.
🍱 semantic-chunking ⇢ semantically create chunks from large document for passing to LLM workflows
A recursive text chunker that attempts to break the text on meaningful boundaries.
Gene's SMTP server — receive Internet mail with less fuss
FastCDC implementation in Python https://pypi.org/project/fastcdc/
Efficiently handle JSON array files in Node.js with minimal memory usage. Perfect for efficiently processing large data volumes without worrying about memory limitations
Question-Answering App Over Your Own Data with LLamaindex and ElasticSearch !
Ongoing - AstroGPT revolutionizes astrology with features like Kundli, daily horoscope, live chat, and a ChatGPT-powered bot. 🚀 Achieved 20% faster loading and 15% better responsiveness, supporting 7 languages and managing 10+ APIs efficiently. 💻 Tailwind CSS for sleek UI, upcoming dynamic search. 🔍 And a lot more !
A fast and lightweight pure Python library for splitting text into semantically meaningful chunks.
*DEPRECATED* Cloudflare worker for LangChunk
Source code for chunking code in multiple different languages
A Rollup integration tool for CoCreate applications, enabling file watching, automated chunking, lazy loading, and file uploading. It leverages CoCreate.config for streamlined project builds and development workflows.
A Webpack integration tool for CoCreate applications, enabling file watching, automated chunking, lazy loading, and file uploading. It leverages CoCreate.config for streamlined project builds and development workflows.
This project is a Streamlit application that allows users to upload PDF files, process them into text chunks, and perform similarity searches on the text. Users can adjust chunking parameters and view the most similar chunks retrieved.
Chunk array of objects by their size in JSON
Byte-Pair Encoding tokenizer for training large language models on huge datasets
Given a directory of source code, find the project name, contributors, collect the source code and output it all in JSON chunks with an upper token limit
Alternative casync implementation
Add a description, image, and links to the chunking topic page so that developers can more easily learn about it.
To associate your repository with the chunking topic, visit your repo's landing page and select "manage topics."