How to create Question-Answering system combining Langchain and OpenAI
The rag pipeline for optimizing dynamic data editing.
Doppalf is a RAG powered AI chat bot application
🤖 AI-Powered PDF Chat App | Dual AI Engine (Alchemyst + Gemini) | RAG Pipeline | Vector Search | MERN + TypeScript
Feature extraction + chatbot
A powerful knowledge management system that forges wisdom from experiences, insights, and best practices. Built with Qdrant vector database for efficient knowledge storage and retrieval.
The AI-Powered assistant for jargons.dev ecosystem
Implementation of the GraphRAG system based on QDrantDB + Neo4j DB on a clean Bun + TypeScript architecture
Kết nối tri thức y học cổ truyền với công nghệ hiện đại https://yitam.org
AI Assistant (Agent ) with Llamaindex, Qdrant and OpenAI
Orion is a lightweight chat interface built using LLM APIs, enabling basic AI tasks like chatting, PDF summarization, image generation, and retrieval-augmented generation (RAG).
Rag Web app
Analysis Agent on Llamaindex Typescript with a simple caching mechanism
Archive and search Product Hunt data locally with Qdrant + MCP (GraphQL, embeddings, vector search).
Developed an AI-powered chat app that lets users upload their own files and have natural conversations with an assistant that understands and answers questions directly from those documents.
Backend service that evaluates candidate CVs and project reports against job requirements using vector similarity search and Large Language Model (LLM) chaining.
Qdrant ile RAG teknolojisinin nasıl uygulanacağını gösteren bir örnektir.
Talk with PDF is a web application that allows users to ask questions and get instant answers from the contents of large PDF files without the need to scroll through them.
An AI-powered document chat application that lets you upload files and websites to have intelligent conversations with your content using RAG technology.
A complete web data Retrieval-Augmented Generation (RAG) pipeline built with TypeScript and Bun that scrapes news articles using Selenium, embeds them with Jina's cloud embeddings API, and stores semantic vectors in Qdrant vector database for fast similarity search and AI-powered applications.
Add a description, image, and links to the qdrant-vector-database topic page so that developers can more easily learn about it.
To associate your repository with the qdrant-vector-database topic, visit your repo's landing page and select "manage topics."