log Vector Product

GitHub Repo https://github.com/Vikneshwara-kumar/Product_Matching_Pipeline

Vikneshwara-kumar/Product_Matching_Pipeline

This repository offers an AI-driven Product Matching Pipeline utilizing the CLIP model with Triton Inference Server, Qdrant for vector similarity searches, and MongoDB for product metadata and logging. A user-friendly Streamlit UI enables easy interaction and visualization, making it ideal for e-commerce, retail analytics, and inventory management.

GitHub Repo https://github.com/SuloniPraveen/AI-Agent-for-Production-Debugging

SuloniPraveen/AI-Agent-for-Production-Debugging

A FastAPI + LangGraph service that helps debug production-style incidents: you upload logs, ask questions in chat, and the agent retrieves relevant log chunks (vector search), then answers with evidence (chunk citations) and actionable remediation,not just raw citations.

GitHub Repo https://github.com/RiyadspX/Production-Ready-RAG-AI-Agent

RiyadspX/Production-Ready-RAG-AI-Agent

This ais a production-grade Retrieval-Augmented Generation (RAG) system integrating Qdrant as the vector database and Inngest for event-driven orchestration. Implemented observability, logging, retries, and rate-limiting mechanisms to ensure reliability and scalability in real-world usage.

GitHub Repo https://github.com/ThirugnanamIT/Vibe_Matcher_Prototype

ThirugnanamIT/Vibe_Matcher_Prototype

This project prototypes a **"Vibe Matcher"** semantic recommendation system. It converts product descriptions and user queries into **vector embeddings** using Sentence-Transformers, then ranks top-3 matches via **cosine similarity** to demonstrate scalable, vibe-based product discovery. It includes latency logging and edge case handling.

GitHub Repo https://github.com/Dhyan-Chinnappa/Production-Ready-RAG-AI-Agent-in-Python

Dhyan-Chinnappa/Production-Ready-RAG-AI-Agent-in-Python

This project shows a production-ready RAG (Retrieval-Augmented Generation) AI agent in Python. It covers system architecture, document loading and indexing, vector databases, APIs, and production features like logging, retries, rate limiting, and scalability for real-world deployment.

GitHub Repo https://github.com/guduchango/mini-store-qa-demo

guduchango/mini-store-qa-demo

Mini Python project using ChromaDB + Ollama to answer questions about a JSON product catalog. Demo of vector search + LLM in a dockerized FastAPI app. Logs visible with docker-compose up.

GitHub Repo https://github.com/SurajitMaity404/Smart-Product-Pricing-Prediction_MLM_1

SurajitMaity404/Smart-Product-Pricing-Prediction_MLM_1

This LightGBM regression model forecasts product prices from catalog text (IPQ counts, stats, brand hashing, SVD vectors) and optional image features (RGB means, histograms). Trained via 5-fold CV on log-transformed targets, it optimizes for SMAPE and outputs submission predictions.

GitHub Repo https://github.com/raju-AI-portfolio/Customer-Query-Response-Automation-using-N8N-RAG-Based-Workflow-

raju-AI-portfolio/Customer-Query-Response-Automation-using-N8N-RAG-Based-Workflow-

RAG-based customer support automation built using N8N. The workflow captures customer queries via Telegram, retrieves relevant product information from documents using Pinecone vector search, generates context-aware responses with OpenAI, logs interactions in Google Sheets, and delivers instant AI-powered replies automatically.

GitHub Repo https://github.com/CoreyVidal/Google-products-vector-logos

CoreyVidal/Google-products-vector-logos

A collection of only the highest quality and most accurate icons for various Google products.

GitHub Repo https://github.com/ChristianJesinghaus/Hybrid-Quantum-Classical-Product-Quantization-for-Vector-Databases

ChristianJesinghaus/Hybrid-Quantum-Classical-Product-Quantization-for-Vector-Databases

Hybrid quantum–classical Product Quantization (PQ‑kNN) with log‑fidelity (based on SWAP test) for vector search.