| Real-time vector retrieval for Edge AI in resource-constrained environments |
| id |
image |
title |
description |
| 0 |
| src |
alt |
| /img/edge-beta-features/native-vector.svg |
Native Vector Search |
|
Native Vector Search for Embedded & Edge AI |
Runs as a lightweight, in-process library. No background threads, no services - ideal for mobile, robotic, and embedded environments. |
|
| id |
image |
title |
description |
| 1 |
| src |
alt |
| /img/edge-beta-features/optimized-for-low-memory.svg |
Low-Memory |
|
Optimized for Low-Memory, Low-Compute Devices |
Dramatically Designed for resource-constrained hardware. No idle overhead, no runtime daemons. Fits into tightly scoped edge deployments. memory usage with built-in compression options and offload data to disk. |
|
| id |
image |
title |
description |
| 2 |
| src |
alt |
| /img/edge-beta-features/local-by-default.svg |
Local by Default |
|
Local by Default, Cloud-Connected When Needed |
Retrieval runs fully offline. Sync with Qdrant Cloud only when required - for data transfer, tenant promotion, or coordination at scale. |
|
| id |
image |
title |
description |
| 3 |
| src |
alt |
| /img/edge-beta-features/hybrid-and-multimodal-search.svg |
Hybrid & Multimodal Search |
|
Hybrid & Multimodal Search On-Device |
Supports dense and multimodal vectors with structured filtering. Enables real-time retrieval from text, image, audio, or sensor-derived embeddings. |
|
| id |
image |
title |
description |
| 4 |
| src |
alt |
| /img/edge-beta-features/multitenancy-built.svg |
Multitenancy Built |
|
Edge-Scale Multitenancy with Native SDKs |
Supports payload- and shard-based tenant isolation. Routes queries across uneven edge workloads. Native SDKs in Java (Android), Swift (Apple), and more. |
|
|
true |
