engineer Vector Vector Vector Product

GitHub Repo https://github.com/SESHANKCH7171/production-rag-system

SESHANKCH7171/production-rag-system

Production-grade RAG: hybrid BM25+vector retrieval, cross-encoder reranking, DeepEval CI pipeline. Project 1 of Agentic AI Engineer roadmap.

GitHub Repo https://github.com/JayKim88/ai-pe-learning-agent

JayKim88/ai-pe-learning-agent

Multi-agent system for AI Product Engineer learning journey. Meta-learning project: building AI agents to become an AI engineer. LangGraph, Claude API, Vector DB, Python.

GitHub Repo https://github.com/sanikasalunke/E-commerce-_Copilot_Fullstack_AI_Engineering_Project

sanikasalunke/E-commerce-_Copilot_Fullstack_AI_Engineering_Project

A production-grade agentic RAG pipeline for intelligent product search and cart/checkout Q&A, powered by LangChain orchestration, LlamaIndex retrieval, FAISS vector store, and asynchronous Kafka inference workers.

GitHub Repo https://github.com/Jaykrishna4104/social-engineering-simulation

Jaykrishna4104/social-engineering-simulation

The Social-Engineer Toolkit is an open-source penetration testing framework designed for social engineering. SET has a number of custom attack vectors that allow you to make a believable attack quickly. SET is a product of TrustedSec

GitHub Repo https://github.com/linhhlp/Tune-Generative_AI-Vector_Search-Prompt_Engineering

linhhlp/Tune-Generative_AI-Vector_Search-Prompt_Engineering

Tune Generative AI with Vector Search and Prompt Engineering. Cluster the Vector Search to suggest products in different categories.

GitHub Repo https://github.com/n10Hacx/social-engineer-toolkit-https-github.com-trustedsec-social-engineer-toolkit

n10Hacx/social-engineer-toolkit-https-github.com-trustedsec-social-engineer-toolkit

The Social-Engineer Toolkit (SET) Copyright 2015 The Social-Engineer Toolkit (SET) Written by: David Kennedy (ReL1K) Company: TrustedSec DISCLAIMER: This is only for testing purposes and can only be used where strict consent has been given. Do not use this for illegal purposes, period. Please read the LICENSE under readme/LICENSE for the licensing of SET. Features The Social-Engineer Toolkit is an open-source penetration testing framework designed for social engineering. SET has a number of custom attack vectors that allow you to make a believable attack quickly. SET is a product of TrustedSec, LLC – an information security consulting firm located in Cleveland, Ohio. Bugs and enhancements For bug reports or enhancements, please open an issue here: https://github.com/trustedsec/social-engineer-toolkit/issues Supported platforms Linux Windows (experimental) Mac OS X (partial)

GitHub Repo https://github.com/aqib9393/AI-Infrastructure-Engineer

aqib9393/AI-Infrastructure-Engineer

This project implements an end-to-end AI-powered product matching system designed for the AI Infrastructure Engineer challenge. It integrates Visual Language Models (VLMs), Vector Databases (FAISS), and NoSQL Databases (MongoDB) to match visually and semantically similar products. The solution

GitHub Repo https://github.com/omartawfik7/Amazon-Product-Review-Detector-w-NLP-ML

omartawfik7/Amazon-Product-Review-Detector-w-NLP-ML

NLP and machine learning pipeline for detecting fraudulent Amazon reviews. Built with Python, scikit-learn, NLTK, and Flask, featuring TF-IDF vectorization, 18 engineered behavioral KPIs, and an interactive web dashboard.

GitHub Repo https://github.com/bassem-elsodany/distance_metrics_in_vector_search

bassem-elsodany/distance_metrics_in_vector_search

Distance Metrics Detective Story – An interactive Jupyter notebook that explores when to use Cosine, Euclidean, Manhattan, Dot Product, and Hamming distances in vector search. Featuring hands‑on financial contracts dataset, visual comparisons, and a practical decision framework to help engineers select the right similarity measure

GitHub Repo https://github.com/mamaniaharsh7/Multimodal-RAG-Recommendation-System

mamaniaharsh7/Multimodal-RAG-Recommendation-System

Engineered recommendation pipeline integrating OpenCLIP (ViT-B-32), LanceDB vector database, and Gemini LLM, for fashion search (H&M dataset), for 1,500+ products across 10 categories, achieving 95%+ similarity accuracy. 4 search variants: vector search, LLM-enhanced retrieval, full RAG pipeline, multimodal search with weighted text+image fusion.