This tool provides a fast and efficient way to convert text into vector embeddings and store them in the Qdrant search engine. Built with Rust, this tool is designed to handle large datasets and deliver lightning-fast search results.

RAG with Apache Airflow, LlamaIndex, and Qdrant

NLS Search is a flexible Natural Language Search API offering vector-based semantic search with support for multiple LLM providers, ideal for integration with e-commerce platforms and SaaS.

User-friendly interface for creating effective Retrieval Augmented Generation (RAGs)

Retrieval-Augmented Generation (RAG) pipeline using FastAPI, Sentence Transformers, and Qdrant for semantic document retrieval.

DocQ is a fast, open-source Q&A bot that finds answers from your PDFs in seconds. Just upload your documents and ask questions, no more scrolling!

Terraform definitions to set up VPCs, Cross-Region VPC Peering, and Qdrant Multiregion Distributed Deployment

How Qdrant's Score Boosting feature can personalize e-commerce search results without training data, complex pipelines, or Learning-to-Rank models.

RAG system for value-based healthcare contracts. Upload PDFs → auto-classify, extract metadata, and index into Qdrant. Ask natural language questions via a streaming chat interface. Stack: FastAPI · LangChain LCEL · OpenAI · Qdrant · Celery · React.

Enterprise compliance RAG assistant with LangGraph workflow, human-in-the-loop approval, multi-tenant RBAC, output policy guards, SSE streaming, pluggable LLM/embedding providers, and full audit trail — built for regulated industries

The RAG system supports service technicians in diagnosing faults by automatically processing PDF documentation and saving it in the Qdrant vector database. This fragment is a larger project combined with React and Bootpress.

Full-featured document search system with semantic/keyword hybrid search, PII detection, multi-collection management, and interactive UMAP clustering. Qdrant + Ollama + Vue.js.

🧠 DAML-RAG: Domain-Adaptive Multi-source Learning RAG Framework | GraphRAG混合检索 + 推理时学习 + 教师-学生双模型协作 | Production-ready vertical domain AI solution

Self-Correcting RAG Agent for code synthesis, featuring an observable Agentic Loop, local LLM (Ollama), and Qdrant retrieval.

Semantic news search & classification using Hugging Face transformers | 90.25% accuracy | Dual deployment (Qdrant + in-memory) | Streamlit UI

An out of the box n8n bare development environment with both a DB (Postgres) and a vector DB (qDrant)

A voice-powered AI customer support agent using OpenAI, Qdrant, and Firecrawl.

Convector is a tiny, practical toolkit to turn .csv datasets into newline‑delimited JSON (output.jsonl) with 384‑dim sentence embeddings and the original row as payload. It pairs with a simple importer to load the file into a local Qdrant vector DB (Docker).

Bootstrap a Qdrant vector database cluster on Fly.io

ML course aggregator with Spark vectorization and scalable vector search, built on a modular, containerized architecture.