Qdrant Blog

Metadata automation and optimization - Reece Griffiths | Vector Space Talks

Metadata plays a critical role in vector search accuracy, yet it’s often overlooked. In this episode of Vector Space Talks, Reece Griffiths, CEO of Deasy Labs, explains why metadata automation is essential for scalable AI systems. He walks us through how Deasy Labs orchestrates metadata extraction, classification, and enrichment to boost retrieval efficiency.

How to Build Intelligent Agentic RAG with CrewAI and Qdrant

Learn how to build an agentic RAG system to semi-automate email communication with CrewAI, Qdrant, and Obsidian.

Qdrant 1.13 - GPU Indexing, Strict Mode & New Storage Engine

Voiceflow & Qdrant: Powering No-Code AI Agent Creation with Scalable Vector Search

Learn how Voiceflow builds scalable, customizable, no-code AI agent solutions for enterprises.

Building a Facial Recognition System with Qdrant

Build an AI app that uses facial recognition embeddings & vector search to match users with their celebrity look-alikes.

Optimizing ColPali for Retrieval at Scale, 13x Faster Results

ColPali combines text and visual contexts for precise document retrieval, but scaling posed challenges. We achieved 13x faster retrieval using pooling and reranking, reducing vector counts by ~30x while retaining near-original accuracy. Explore the open-source demo to optimize your retrieval workflows!

Best Practices in RAG Evaluation: A Comprehensive Guide

Explore best practices for evaluating Retrieval-Augmented Generation (RAG) systems.

Empowering QA.tech’s Testing Agents with Real-Time Precision and Scale

QA.tech uses Qdrant to power AI agents, enabling scalable, real-time web testing with custom embeddings and batch efficiency.

Advanced Retrieval with ColPali & Qdrant Vector Database

ColPali leverages vision language models and multivector embeddings to streamline complex document retrieval.