Qdrant - Vector Database & Search Engine Courses

Introducing Qdrant's Official n8n Node - Hybrid Search Example

Discover how to install and use Qdrant's verified n8n node for native vector database integration with a practical hybrid search demonstration.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Beyond LLMs: Building Smarter Search with Superlinked and Qdrant

Explore how to build advanced search systems beyond LLMs using Superlinked and Qdrant vector database technologies for more intelligent information retrieval.

• YouTube
• 59 minutes
• On-Demand
• Free Video

Power Up Your Embeddings with Metadata Awareness

Discover how to enhance vector search by incorporating metadata awareness into embeddings, exploring hybrid search, metadata boosting, and re-ranking techniques for richer retrieval.

• YouTube
• 50 minutes
• On-Demand
• Free Video

Finding the Right Embedding Model for AI Applications Using Sentrev

Master embedding model selection for AI applications using Sentrev - evaluate dense and sparse models, integrate with Qdrant and FastEmbed, and optimize performance while considering environmental impact.

• YouTube
• 1 hour 14 minutes
• On-Demand
• Free Video

Building Open-Source Agentic RAG with DeepSeek

Dive into building agentic RAG systems using DeepSeek and Qdrant, learning to orchestrate AI applications with secure vector search while maintaining data privacy and control.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Building Intelligent Agentic RAG with CrewAI and Qdrant

Discover how to build AI agents that analyze your emails and knowledge base, creating contextual response suggestions using CrewAI and Qdrant vector database integration.

• YouTube
• 1 hour 5 minutes
• On-Demand
• Free Video

Rapid Prototyping RAG Agents with n8n and Qdrant

Discover how to rapidly prototype Retrieval-Augmented Generation workflows using n8n and Qdrant vector database for fast, flexible AI-powered applications without heavy infrastructure.

• YouTube
• 30 minutes
• On-Demand
• Free Video

How to Cheat at Benchmarking Search Engines

Discover how to build fair, reproducible benchmarks for search engines and avoid misleading performance comparisons that plague the industry.

• YouTube
• 20 minutes
• On-Demand
• Free Video

Self-Improving Evaluations for Agentic RAG - Tracing and Feedback Loops

Discover how to build self-improving agentic RAG systems through advanced tracing, evaluation methods, and feedback loops for better AI reasoning and accountability.

• YouTube
• 24 minutes
• On-Demand
• Free Video

Evaluate Your Qdrant-RAG Agents with No-Code n8n Evaluations

Master no-code RAG agent evaluation using n8n and Qdrant, building test workflows, measuring citation faithfulness, and setting up quality drift alerts for reliable AI systems.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Agent-Powered Retrieval with Haystack and Qdrant - Promises and Pitfalls

Explore agent-powered retrieval vs traditional pipelines using Haystack and Qdrant, comparing latency, accuracy, and robustness to determine when agents add value over simpler approaches.

• YouTube
• 20 minutes
• On-Demand
• Free Video

Redefining Long-Term Memory Ingestion for Streaming Autonomous Agents

Discover how to build asynchronous memory systems for autonomous agents using Qdrant, enabling real-time ingestion, layered retrieval, and enterprise-grade performance.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Scaling Real-Time RAG for Analytics with Qdrant

Discover how GoodData built production-grade RAG architecture using Qdrant for real-time analytics, covering ingestion patterns, retrieval optimization, and scaling strategies.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Building a News Sleuth for the Deep Research Paradigm - AskNews

Discover how to build AI-powered news research systems with expert ontology, rigorous sourcing, and hybrid retrieval for high-stakes decision-making and fact-checking.

• YouTube
• 17 minutes
• On-Demand
• Free Video

Building Scalable AI Memory for Agents Across Graphs and Vectors

Discover how to build scalable AI memory systems using cognee SDK, combining graph and vector databases for reliable LLM data integration with practical finance examples.

• YouTube
• 15 minutes
• On-Demand
• Free Video