📝 Blogs & Articles — Awesome Similarity Search
Loading posts…
Loading posts…
26 posts, articles, and resources from across the field.
Qdrant is enhancing its capabilities with new features and collaborations.
4 postsQdrant Academy is expanding its offerings to enhance user skills and knowledge.
3 postsVarious industries are leveraging Qdrant for innovative solutions in AI and vector search.
3 postsPartnerships are forming to drive AI innovations and infrastructure development.
3 postsWhy it matters — This post discusses the importance of multi-vector embeddings for capturing complex interactions in retrieval systems, which is crucial for enhancing the accuracy of search results in Learning To Hash applications.
Why it matters — The collaboration between LangChain and Qdrant Hybrid Cloud highlights the integration of robust frameworks for developing advanced retrieval-augmented generation (RAG) systems, essential for researchers focusing on scalable AI applications.
Why it matters — This post emphasizes the shift from passive vector storage to active configuration of vector engines, which can significantly improve the efficiency of document retrieval in Learning To Hash frameworks.
Why it matters — The launch of Qdrant Academy provides structured learning resources that are vital for researchers aiming to master vector search systems and apply them effectively in their projects.
Why it matters — Analyzing community threads on pgvector provides insights into its limitations, helping researchers make informed decisions about their choice of vector database for future projects.
Why it matters — The introduction of official certification from Qdrant Academy signifies a commitment to professional development in vector search, which is crucial for researchers seeking to validate their skills in this area.
Why it matters — This new course on multi-vector image retrieval offers advanced techniques that can enhance the performance of image search systems, which is critical for researchers working with multimodal data.
Why it matters — The concept of on-device vector search for memory building in robots presents innovative applications of Learning To Hash techniques in real-world scenarios, particularly in robotics and AI.
Why it matters — Anima Health's implementation of Qdrant showcases practical applications of vector search in clinical settings, providing insights into how AI can improve healthcare delivery.
Why it matters — This post illustrates the application of real-time multimodal similarity search in fraud detection, demonstrating the practical implications of vector search techniques in trust and safety contexts.
Why it matters — The new features in Qdrant 1.16, particularly tiered multitenancy, address scalability challenges, which are essential for researchers looking to implement efficient vector search solutions.
Why it matters — The collaboration between NVIDIA and AWS highlights the importance of optimizing infrastructure for AI workloads, which is critical for researchers focused on deploying scalable vector search systems.
Why it matters — The hackathon showcases innovative applications of vector search, providing researchers with inspiration and insights into creative uses of AI technology in various fields.
Why it matters — The upgrades in Qdrant Cloud, including GPU indexing and audit logging, are crucial for researchers needing high-performance solutions for continuous AI workloads.
Why it matters — Vector Space Day 2026 presents an opportunity for networking and sharing knowledge among researchers, which can foster collaboration and innovation in the field of vector search.
Why it matters — The announcement of significant funding for composable vector search infrastructure underscores the growing importance of retrieval systems in AI, making it relevant for researchers in the field.
Why it matters — The Sketch & Search hackathon winners highlight creative applications of AI-driven pipelines, showcasing the potential of vector search in enhancing creative processes.
Why it matters — The winners of the hackathon challenge conventional uses of vector search, prompting researchers to think innovatively about applications in various domains.
Why it matters — The partnership between Aleph Alpha and Qdrant emphasizes the importance of data sovereignty in AI applications, which is a critical consideration for researchers working with sensitive data.
Why it matters — The collaboration with Vultr enhances the scalability and performance of vector search workloads, providing researchers with insights into optimizing their deployments.
Why it matters — The introduction of Qdrant Hybrid Cloud with Scaleway offers researchers a fully managed vector database solution, facilitating easier deployment of AI applications in existing environments.
Why it matters — The release of Qdrant Hybrid Cloud for OVHcloud users allows enterprises to leverage vector search technology, which is significant for researchers focused on enterprise applications of AI.
Why it matters — The collaboration between Qdrant Hybrid Cloud and LlamaIndex highlights new horizons in RAG systems, which are essential for researchers developing advanced AI applications.
Why it matters — The partnership with Jina AI emphasizes the importance of hybrid cloud solutions for scaling AI applications, which is crucial for researchers looking to enhance their systems' capabilities.
Announcing the Vector Space Day 2025 Speaker Lineup We are just days away from Vector Space Day in Berlin, and the full speaker lineup is here! This year’s program spans keynotes, deep-dive technical sessions, and lightning talks, covering everything from benchmarking search engines to scalable AI memory and multimodal embeddings. Here’s what to expect. Opening Keynotes The day begins with perspectives from across the ecosystem: Andre Zayarni, Andrey Vasnetsov, and Neil Kanungo sharing Qdrant’s vision for the future of vector search and how devs can engage with the Qdrant Community. Robert Eichenseer (Microsoft), Kevin Cochrane (Vultr), and Inaam Syed (AWS) offering insights on how cloud, infrastructure, and developer communities are reshaping AI systems. Breakout Sessions Track A: Milky Way - Architectures, Infrastructure and Multimodal Retrieval AskNews - Building a News Sleuth for the Deep Research Paradigm: How high-performance hybrid retrieval can support investigative journalism and geopolitical risk monitoring. Delivery Hero - How to Cheat at Benchmarking Search Engines: Lessons from building reproducible benchmarking harnesses and public leaderboards. Neo4j - Hands-On GraphRAG: Practical guidance on combining knowledge graphs with RAG for more explainable retrieval. Superlinked - Beyond Text-Only: How mixture of encoders unlocks advanced retrieval using Google DeepMind’s latest embeddings. Jina AI - Vision-Language Models for Embedding: Training insights for multimodal embeddings that span text, diagrams, and UI screenshots. TwelveLabs - Practical Multimodal Embeddings: Real workflows for cross-modal video search and recommendations. Baseten - High Throughput, Low Latency Embedding Pipelines: Patterns and open-source tools for production-ready embedding inference. Google DeepMind - Vector Search with Gemini and EmbeddingGemma: Deploying cutting-edge embeddings with the right indexing strategies. Track B: Andromeda - AI Workflows, Agents and Applications Linkup - Beyond Web Search: Infrastructure for AI-native agents that need structured, real-time web intelligence. Cognee - Building Scalable AI Memory: Abstractions that sync graphs and vectors for durable, multi-backend AI memory. n8n - Evaluate Your Qdrant-RAG Agents: A live no-code session on agent evaluation using n8n’s native tools. Arize AI - Self-Improving Evaluations: Feedback loops and tracing for reliable agentic RAG in production. LlamaIndex - Vector Databases for Workflow Engineering: Using Qdrant to orchestrate context-aware AI pipelines. deepset - Agent-Powered Retrieval with Haystack and Qdrant: When retrieval agents outperform or overcomplicate pipelines. GoodData - Scaling Real-Time RAG for Analytics: Lessons from streaming BI artifacts into Qdrant for natural-language analytics. Equal - Redefining Long-Term Memory: Streaming-driven ingestion architectures that give agents enterprise-grade responsiveness. Lightning Talks The afternoon features rapid-fire sessions from innovators including:
Variety is the spice of life! Yet often, with search engines, users find that the results are too similar to get value. You search for a black jacket on your favorite shopping site, and you get 5 black full zip bomber jackets. Search for a black dress and you get 5 strapless dresses. Traditional vector search focuses on returning the most relevant items, which creates an echo chamber of similar results.