Memory Tiers in Qdrant: What to Use and When
Which Qdrant memory tier layout to use and when, and why, backed by benchmarks.
Clelia Bertelli
August 28, 2026
Latest Articles
The most recent publications from the Qdrant team.
Configure Qdrant's Optimizer for Predictable Search Latency
Configuration guidance for Qdrant's indexing, merge, and vacuum optimizers, backed by search latency measurements across 13 configurations on a 1.76 million point collection.
Clelia Bertelli
August 25, 2026
Hybrid Search in Qdrant
Decide whether to add hybrid search in Qdrant: the queries dense and sparse retrieval each get wrong, and how to measure the gain.
Dylan Couzon
August 24, 2026
Core Concepts
Start here to understand the building blocks of vector search. Learn what vector databases, embeddings, quantization, and retrieval-augmented generation are and how they fit together.
Is RAG Dead? Why Long Context Windows Don't Replace RAG
Uncover the necessity of vector search for RAG and learn how Qdrant empowers enterprise AI with unmatched accuracy and cost-effectiveness.
David Myriel & Chadha Sridi
August 04, 2026
How to Choose an Embedding Model: Evaluation & Tradeoffs
Building proper search requires selecting the right embedding model for your specific use case. This guide helps you navigate the selection process based on performance, cost, and other practical considerations.
Kacper Łukawski
July 15, 2025
Why Vector Search Needs a Dedicated Database
Why add-on vector search looks good — until you actually use it.
Evgeniya Sukhodolskaya & Andrey Vasnetsov
February 17, 2025
Mastering Search
Go beyond the basics and master vector search with Qdrant. Learn how to combine filtering, hybrid retrieval, multivectors, and reranking to build high-quality search.
Fine-Tuning Sparse Embeddings for E-Commerce Search | Part 5: From Research to Product
Part 5 of a 5-part series on fine-tuning SPLADE sparse embeddings for e-commerce search. We packaged the entire training pipeline from Parts 1-4 into an open-source CLI and web dashboard that fine-tunes SPLADE models for any product catalog in minutes.
Thierry Damiba
March 09, 2026
Fine-Tuning Sparse Embeddings for E-Commerce Search | Part 4: Specialization vs Generalization
Part 4 of a 5-part series on fine-tuning SPLADE sparse embeddings for e-commerce search. Test cross-domain generalization, train a multi-domain model, and decide when to specialize vs generalize.
Thierry Damiba
March 09, 2026
Fine-Tuning Sparse Embeddings for E-Commerce Search | Part 3: Evaluation and Hard Negatives
Part 3 of a 5-part series on fine-tuning SPLADE sparse embeddings for e-commerce search. Index products in Qdrant, run retrieval benchmarks, and implement ANCE-inspired hard negative mining for a 28% improvement over BM25.
Thierry Damiba
March 09, 2026
Search Quality
Learn how to evaluate and improve the quality of your vector search. Explore relevance feedback, evaluation methodologies, and benchmarking techniques.
Hybrid Search in Qdrant
Decide whether to add hybrid search in Qdrant: the queries dense and sparse retrieval each get wrong, and how to measure the gain.
Dylan Couzon
August 24, 2026
When Your Collection Outgrows RAM
Set quantization and memory placement in Qdrant once a collection outgrows RAM: what the rescoring disk read costs and what quality it recovers.
Dylan Couzon
August 24, 2026
When Is a Reranker Worth It?
Test whether a cross-encoder reranker beats your tuned first stage in Qdrant, then choose the model and candidate count from measured results.
Dylan Couzon
August 23, 2026
Production Ops
Operate Qdrant at scale. Learn how to optimize memory and resources, apply quantization, manage multitenancy and sharding, and secure access in production.
Memory Tiers in Qdrant: What to Use and When
Which Qdrant memory tier layout to use and when, and why, backed by benchmarks.
Clelia Bertelli
August 28, 2026
Configure Qdrant's Optimizer for Predictable Search Latency
Configuration guidance for Qdrant's indexing, merge, and vacuum optimizers, backed by search latency measurements across 13 configurations on a 1.76 million point collection.
Clelia Bertelli
August 25, 2026
Bulk Uploading Data to Qdrant
Plan bulk uploads in Qdrant: batching, parallelization, sharding, payload indexes, quantization, and on-disk storage.
John Kupchanko
July 14, 2026
Qdrant Internals
Take a look under the hood of Qdrant’s high-performance vector search engine. Explore the architecture, components, and design principles the Qdrant Vector Search Engine is built on.
Filtered Vector Search: What ACORN Fixes, and What Fixes ACORN
Benchmark filtered vector search in Qdrant: how ACORN, filterable HNSW, and query planning trade recall for latency on one million points.
Dylan Couzon & Meina Ghafouri
August 07, 2026
Introducing Gridstore: Qdrant's Custom Key-Value Store
Why and how we built our own key-value store. A short technical report on our procedure and results.
Luis Cossio, Arnaud Gourlay & David Myriel
February 05, 2025
Immutable Data Structures in Qdrant
Learn how immutable data structures improve vector search performance in Qdrant.
Andrey Vasnetsov
August 20, 2024
Embedding Research
Explore the research behind modern embeddings and neural retrieval. Dive into sparse neural models, late interaction, metric learning, and new baselines for hybrid search.
miniCOIL: on the Road to Usable Sparse Neural Retrieval
Introducing miniCOIL, a lightweight sparse neural retriever capable of generalization.
Evgeniya Sukhodolskaya
May 13, 2025
Modern Sparse Neural Retrieval: From Theory to Practice
A comprehensive guide to modern sparse neural retrievers: COIL, TILDEv2, SPLADE, and more. Find out how they work and learn how to use them effectively.
Evgeniya Sukhodolskaya
October 23, 2024
Late Interaction Retrieval with Dense Token Embeddings
We recently discovered that embedding models can become late interaction models & can perform surprisingly well in some scenarios. See what we learned here.
Kacper Łukawski
August 14, 2024
RAG & Agents
Build retrieval-augmented generation and agentic applications with Qdrant. Learn agentic RAG patterns, agent memory, semantic caching, and how agents access your data.
Building Performant, Scaled Agentic Vector Search with Qdrant
Learn how to build performant, scalable AI agents with efficient vector retrieval, hybrid dense-sparse search, real-time memory, multimodal context integration, and optimized architectures for low-latency, high-accuracy execution in production environments.
Thierry Damiba
October 26, 2025
What is Agentic RAG? Building Agents with Qdrant
Agents are a new paradigm in AI, and they are changing how we build RAG systems. Learn how to build agents with Qdrant and which framework to choose.
Kacper Łukawski
November 22, 2024
Semantic Caching for RAG: Cut LLM Cost and Latency
Semantic cache is reshaping AI applications by enabling rapid data retrieval. Discover how its implementation benefits your RAG setup.
Daniel Romero, David Myriel
May 07, 2024
Data Exploration
Learn how you can leverage vector similarity beyond just search. Reveal hidden patterns and insights in your data, provide recommendations, and navigate data space.
Data Exploration with Qdrant's Distance Matrix API
Explore your data under a new angle with Qdrant's tools for dimensionality reduction, clusterization, and visualization.
Andrey Vasnetsov
March 11, 2025
Discovery Search in Qdrant
Discovery Search, an innovative way to constrain the vector space in which a search is performed, relying only on vectors.
Luis Cossío
January 31, 2024
Multimodal Food Search Demo
Feeling hungry? Find the perfect meal with Qdrant's multimodal semantic search.
Kacper Łukawski
September 05, 2023
Demos & Tutorials
Learn by building. Follow hands-on tutorials and demos covering neural search, serverless deployments, search-as-you-type, and integrations with popular frameworks.
Question Answering with LangChain and Qdrant
We combined LangChain, a modern chat model like Claude or GPT, FastEmbed & Qdrant to create a question answering system with just a few lines of code. Learn more!
Kacper Łukawski and Manas Chopra
July 30, 2026
FastEmbed: Qdrant's Efficient Python Library for Embedding Generation
Learn how to accurately and efficiently create text embeddings with FastEmbed.
Nirant Kasliwal and Manas Chopra
July 30, 2026
Semantic Search As You Type
To show off Qdrant's performance, we show how to do a quick search-as-you-type that will come back within a few milliseconds.
Andre Bogus
August 14, 2023