Notebooks for fine-tuning a BERT model and training a LSTM model for financial QA

A notebook used to perform image classification and clustering of Human Trafficking images.

Jupyter notebooks to help with search relevancy measurements, optimized for Quepid.

A notebook example illustrating Graphyp

Collection of different kernels related to Machine Learning, NLP, Deep Learning, AI and cryptocurrencies..

Some information retrieval algorithms and datastructures (inverted index, ranking (bm25, tf, idf scores), fuzzy search, ...)

compilation of notebooks

Notebooks with source code for self-study experiment with LLM chain and agent for information retrieval on Nebulous: Fleet Command datasets.

A notebook on review classification for movies featured on the imdb page

Cheng-Lin Li's Data Scientist Notebook

📔 [WiP] Writing of the prediction model and plataform for NEURONE.

a notebook and python code aimed at demonstrating information retrieval using binary independence model

A next-generation notebook that uses embeddings for semantic search and 3D visualization of notes.

Information Retrieval Project: This repository contains a suite of Python tools and a Jupyter notebook for simple data processing, inverted indexing, and boolean querying, complemented by detailed experimental analyses.

Foundational notes and hands-on notebooks for Retrieval Augmented Generation (RAG), focusing on embeddings, retrieval, and grounded generation

This repository contains jypytor notebook for query refinement and uses MAP and TNSE graphs to visualize the query shifting.

Lightweight Jupyter‑notebook prototype that recommends related arXiv papers by analyzing abstracts (simple NLP/embedding-based similarity) to surface relevant reading suggestions.

An interactive insurance policy query-answering notebook with a Retrieval-Augmented Generation (RAG) pipeline with semantic search, caching, and GPT-based response generation.

Hybrid RAG with three retrievers—Lexical (BM25), Semantic (embeddings), and Hybrid (Reciprocal Rank Fusion) — parallel retrieval, Llama 3 generation, and side-by-side evaluation with reproducible notebooks.

A Python-based Jupyter notebook system for high-recall text retrieval in large databases, leveraging active learning to efficiently label instances and train models for identifying relevant documents.