Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

This repository features a comprehensive ML pipeline for supervised learning tasks, covering data collection, cleaning, EDA, feature engineering, model training, and evaluation.

The GPU-powered AI application database. Get your app to market faster using the simplicity of SQL and the latest NLP, ML + LLM models.

This app is intended to dynamically integrate machine learning techniques to explore multivariate data sets.

This project focuses on developing machine learning solutions for various use cases within 5G New Radio (NR) networks, specifically under the Open Radio Access Network (O-RAN) framework.

Gretl implementation of the knn machine-learning algorithm

PostgreSQL vector database extension for building AI applications

Evaluation of Recommendation Systems

This reposirtory is a 'Chat-with-your-PDF' project using RAG approach.

The primary objective is to deploy a robust classifier model that accurately predicts user recommendations, empowering airlines to strategize effectively, understand user behavior, optimize services, and align business strategies with financial objectives.

Tokenize and convert sample text data into vectors using BERT. Load the vector representation of the text to OpenSearch and use kNN for semantic search

This repository contains code for building a K-Nearest Neighbors (KNN) model to predict diabetes based on patient data. Includes data cleaning, hyperparameter tuning, and evaluation metrics.

Basic ML algorithms with python

JVector: the most advanced embedded vector search engine

⚡机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归

scikit-learn compatible estimators for various kNN imputation methods

This repository contains my machine learning models implementation code using streamlit in the Python programming language.

Routines for generating, manipulating, parsing, importing vector embeddings into Postgres tables

The labs for the Travelers EDP June 2024 program.

📚My Best Books Ever project uses a dataset from Zenodo to analyze and recommend books from GoodReads. It includes data cleaning, regression analysis, sentiment analysis, and a KNN-based recommendation system to help users find books based on their preferences.📗