A modern desktop application for exploring, managing, and analyzing vector databases
-
Updated
Jan 30, 2026 - HTML
A modern desktop application for exploring, managing, and analyzing vector databases
Open multilingual construction cost database for AI Agents - 55K+ work items, 27K+ resources, 9 languages. Semantic search via Qdrant vector DB
Medical RAG QA App using Meditron 7B LLM, Qdrant Vector Database, and PubMedBERT Embedding Model.
This is a RAG implementation using Open Source stack. BioMistral 7B has been used to build this app along with PubMedBert as an embedding model, Qdrant as a self hosted Vector DB, and Langchain & Llama CPP as an orchestration frameworks.
A production framework for DSPy implementing the Teacher-Student pattern. Distill the reasoning of expensive models (Teacher) into optimized prompts for cheap, fast models (Student) to reduce inference costs by up to 50x.
FlutterGPT - AI chatbot powered by OpenAI API, Qdrant, LangChain and AWS Lambda
The objective of this project is to create a chatbot that can be used to communicate with users to provide answers to their health issues. This is a RAG implementation using open source stack.
AI-Powered Visual Evidence Matching for Indian Law Enforcement using Qdrant Vector Search - Convolve 4.0 Hackathon Submission
Store and search string data using embeddings + Qdrant vector database via Flask. Fully containerized with Docker.
IRC bot with AI-powered knowledge retrieval and dynamic learning. Real-time conversation via GPT-4o-mini, vector search (Qdrant), and community-driven corrections. Includes Python web scraper toolchain for content ingestion. Built on n8n + PostgreSQL. Respectful of robots.txt and site policies.
Arabic RAG chatbot (Bosala AI) transforms documents into a searchable knowledge base using Gemini and Qdrant. Includes a web UI, admin analytics, and easy ingestion tools for high-quality Arabic Q&A
This is a comprehensive stock management system that integrates AI-powered tools for stock analysis, trade requests, and client activity tracking. It includes a backend built with Python, a frontend with HTML, and services for PDF processing, stock queries, and real-time communication.
Add a description, image, and links to the qdrant topic page so that developers can more easily learn about it.
To associate your repository with the qdrant topic, visit your repo's landing page and select "manage topics."