Gigaversity.in • 1m
We built an e-commerce platform that worked well initially. But as the product catalog grew, users started facing issues—search results were slow and often not relevant. This led to frustration and a drop in engagement. To solve this, we upgraded the search experience using AI-powered semantic search with vector databases, making results faster and more accurate. The Problem We Faced - Search results were based on basic keyword matching, which often ignored user intent. - Users struggled to find what they sought, especially when using natural language queries. - Product data changes weren’t reflected in real-time, resulting in outdated listings in search results. - The system couldn’t scale well with growing inventory and user base. Our Solution To fix the outdated and irrelevant search experience, we built an AI-driven search system focused on speed and accuracy: - Semantic Search Integration - We used AI vector databases like Pinecone and Typesense to match search intent with product meaning. - Optimized Data Processing - Product descriptions were preprocessed with NLP and cached using Redis for faster results. - User Feedback Loop - Real-time user actions (clicks, views, carts) helped fine-tune relevance over time. - Real-Time Inventory Sync - Background workers ensured updated product data was instantly reflected in search results. Tools & Technologies Used Frontend: Next.js, Tailwind CSS Backend: Node.js, PostgreSQL AI & Search: Pinecone/Typesense (vector databases), NLP models Caching: Redis Async Processing: Background workers (Node worker threads / BullMQ)
Startups | AI | info... • 26d
Vector databases for AI memory just got disrupted… by MP4 files?! Video as Database: Store millions of text chunks in a single MP4 file Store millions of text chunks with blazing-fast semantic search — no database required. 100% open source. Zero
See MoreSoftware Engineer | ... • 7m
💡 5 Things You Need to Master for learn for integrating AI into your project 1️⃣ Retrieval-Augmented Generation (RAG): Combine search with AI for precise and context-aware outputs. 2️⃣ Vector Databases: Learn how to store and query embeddings for e
See MoreHey I am on Medial • 8h
I'm developing a smart AI-powered meal planner mobile app that helps users create personalized meal plans based on their health goals, dietary preferences, regional cuisine, and lifestyle. The app suggests meals for breakfast, lunch, snacks, and dinn
See MoreBuilding an AI eco-s... • 3m
I feel pride in announcing our Made in India, Real-Time Vector Database - SwarnDB. SwarnDB is a SarthiAI initiative towards an effort to create an end to end eco-system for the future of AI. We tested SwarnDB with 100K vector records of 1536 dime
See MoreI help businesses to... • 6m
SEO Lane Series - Lane 3 25 Common SEO Terminologies. ___________________________________ These are some of the terms you should be aware of while doing SEO, 1 - Keywords: Words or phrases people type into search engines to find information. 2 -
See MoreHey I am on Medial • 2m
there is In-house application which is developed by only java and .jsp for frontend and databases is SQL and SQL Lite and there are multiple roles which are Admin , Client Manager, Client Resource, Manager and Resource there are Management sections l
See MoreDownload the medial app to read full posts, comements and news.