什么是 Qdrant？

Current in-car media systems still rely on keyword-based search, but drivers naturally express needs through emotions, vibes, and intent—not terms. Sarvesh Talele’s project, built with Qdrant Edge, delivers a fully local, AI-powered media discovery system supporting voice, text, and mood-based semantic queries—no cloud needed, ensuring privacy-first, real-time experience.

Qdrant 1.18 is released, introducing TurboQuant, a new quantization method developed by Google Research, offering higher memory efficiency and better recall.

Qdrant 1.17 introduces the first vector index-native relevance feedback mechanism, embedding relevance judgment directly into retrieval for improved efficiency and accuracy.

A semantic memory engine based on Qdrant Edge allows developers to search codebases using natural language instead of traditional grep keyword search.

Qdrant will present at Vector Space Day on building a smart, reliable, and enterprise-ready AI agent, focusing on scalable systems, context-aware reasoning, real-time decision-making, and stability in high-risk environments.

Qdrant 宣布了 Vector Space Day 的几位演讲者，包括 Taranjeet Singh、Paige Bailey 和 HubSpot，他们将分别讨论持续学习、技能文档对代理的影响以及扩展到大规模向量搜索。活动将于 6 月 11 日在 The Midway 举行。

AI recruiting systems using Qdrant Cloud's hybrid search and multivector representations boost candidate matching accuracy from 30% to 99.993%, enabling efficient large-scale talent acquisition.

Qdrant's Brian O'Grady discussed the application scenarios and differences between semantic search and exact-match in the Stack Overflow podcast.

Qdrant announces a partnership with Aman to help Israeli businesses build production AI on search infrastructure not designed for it.

Video is the most information-dense modality we have, but most retrieval pipelines treat it like text with pictures; James Le will demonstrate how proper multimodal retrieval enables advanced functions like semantic search, object tracking, and highlight generation at Vector Space Day.

Qdrant announces an event in Berlin focused on AI retrieval, agents, and modern search systems, discussing the evolution of retrieval in the age of agents, production RAG, memory systems, and vector search. Event link: https://t.co/zTuvAQ5UrM

Qdrant announces Laurie Voss will discuss retrieval metrics and golden datasets at Vector Space Day 2026, emphasizing the importance of evaluation strategies.

Join the multimodal search workshop and experiment with Gemini Embedding 2 and Qdrant.

TurboQuant is now integrated into Qdrant vector database, offering recall comparable to Scalar Quantization at ~2× compression and better recall than Binary Quantization at the same storage budget, providing a superior quantization option for SQ/BQ users.

Qdrant applies vector search technology to the field of cybersecurity, improving CyberOps efficiency through similarity search, threat modeling, and vulnerability analysis.

Qdrant introduces Agent Skills, expanding the use of vector search.

The article briefly contrasts semantic search with traditional text search, but lacks technical depth, primarily serving as a product promotion for Qdrant without actionable engineering insights.

Qdrant 宣布今日将举行办公室时间活动，主题为“使用 Qdrant 进行威胁情报”，由 Kevin 主持，讨论向量搜索在网络安全运营中的应用，包括威胁建模、攻击面分析和大规模安全数据关联。活动时间为 CEST 时间下午 6 点，地点在 Qdrant Discord，提供链接供参与。

Qdrant hosts Vector Space Meetup in Berlin on June 11, exploring the shift from simple vector matching to dynamic decision-making (when/what/how to search) for AI Agents.

This tweet is merely a promo for Vector Space Day, lacking technical depth on the embodied AI framework. An AWS engineer will demo an open-source agentic framework exposing hardware as programmable tools via hybrid search, but no architecture or code is provided.

Qdrant announces it will present a session combining OCR and semantic search for messy documents at MistralAI’s summit, though the post is merely an event announcement without technical depth.

This tweet highlights how health insurance is difficult to understand, making it hard for patients to find care; SunnyHealthAI is building a healthcare assistant to address this issue.

This is a promotional tweet for an upcoming Qdrant webinar on TurboQuant technology, lacking substantive technical details.

This is a marketing tweet from Qdrant's official Twitter account promoting its deep query filtering feature. It merely lists four components of vector search (semantic search, metadata filtering, structured constraints, fast query execution) without elaborating technical details or production experience, resulting in extremely low information density.

Qdrant announces an upcoming live session on using vector search for threat intelligence in cybersecurity, covering threat modeling and vulnerability analysis — but offers no technical depth, only event promotion.

Qdrant 将于明天举办 TurboQuant 网络研讨会，展示 TurboQuant 在压缩性能上的优势，同时不牺牲召回率，并进行技术演示。

Qdrant宣布作为黄金合作伙伴参加#bbuzz26，并邀请参会者与团队成员会面，讨论向量搜索、生产检索系统和实际AI工作负载。他们还将展示Qdrant Edge的现场演示和提供大量周边商品。

这是一条关于 Vector Space Day 2026 提案截止（5月6日）的推广推文，呼吁在检索、智能体、记忆或边缘AI领域有实践的工程师提交演讲提案。

This is a promotional message about a technical conference, announcing that Qdrant will host technical talks on vector search, AI memory, context engineering, and more.

Early bird pricing for Vector Space Day 2026 ends soon, focusing on retrieval, agents, and edge AI in San Francisco.