Available now in public preview on Zilliz Cloud, Vector Lakebase keeps production vector search at its core and adds shared lake-native storage and on-demand compute — bringing real-time serving, interactive discovery, and batch analytics onto one data foundation.
REDWOOD CITY, Calif., June 10, 2026 /PRNewswire/ -- Zilliz, the company behind Milvus, the world's most widely adopted open-source vector database, today announced the public preview of Zilliz Vector Lakebase, a major Zilliz Cloud release that pairs the production vector database with a shared, lake-native data foundation.
Vector Lakebase keeps Zilliz Cloud's real-time vector search at the core — the engine Zillow, OpenEvidence, Exa, Filevine, MiniMax, and more than 10,000 enterprises and AI teams already rely on — and extends it with three new ways to operate on the same data: interactive discovery, large-scale batch analytics, and search directly on external data lakes. The result is a single data foundation in which every workload runs against a single logical copy of the data, with on-demand and batch jobs billed only when compute is active.
"Production vector search is and will remain at the heart of what Zilliz does — it's why thousands of teams choose Milvus and Zilliz Cloud, and it's getting faster and more cost-efficient every release," said Charles Xie, Founder and CEO of Zilliz. "Vector Lakebase is what we believe comes next: one data foundation where the same vectors can serve a production query, anchor a discovery session, and power a multi-petabyte training-data pipeline — without copies, migration, or a parallel stack."
Why a Single Data Foundation Matters
AI systems are no longer a single-query retrieval problem. They run as a continuous loop — serve, learn from feedback, mine and prepare better data, then serve again — and each turn typically requires separate systems for serving, exploration, and large-scale processing. Moving billions of vectors between those systems can take days. The cost and complexity are so high that many teams skip the loop altogether, leaving valuable data retrievable but never improved.
Vector Lakebase closes that gap with a zero-copy semantic data plane on shared lake-native storage: real-time serving, interactive discovery, and batch analytics all run against one logical copy of the data, scaling from gigabytes to petabytes.
"Teams asked for a way to keep their data in one place and run very different workloads against it — from real-time agent memory to overnight semantic deduplication," said Robert Guo, VP of Product at Zilliz and one of the architects behind Milvus. "Vector Lakebase delivers that through a unified storage layer on Vortex, tiered serving for the production path, and on-demand compute for everything else."
Five Capabilities on One Foundation
- Tiered Real-Time Serving. Three production tiers tuned for different workloads: Performance-Optimized (1,000+ QPS, single-digit-millisecond latency, in-memory); Capacity-Optimized (100–500 QPS, sub-100ms latency, memory + NVMe); and Tiered-Storage (10–50 QPS, ~100ms latency, spanning memory, NVMe, and object storage at significantly lower cost). All tiers default to 95–98% recall, tunable to 99%+, backed by Zilliz Cloud's 99.99% uptime SLA and Global Cluster cross-region high availability.
- On-Demand Search. Pay-as-you-go compute for workloads where infrastructure sits idle most of the time, billed directly for object storage and compute rather than serverless markups. In Zilliz's internal benchmark on one billion 768-dimension vectors with 10 hours of monthly active compute, On-Demand Search totaled $318 versus $4,937 for a comparable serverless path — roughly 1/15 the cost.
- External Data Lake Search. A zero-copy External Collection mode that adds state-of-the-art indexing and full-spectrum search directly to existing Lance, Iceberg, Parquet, and Vortex tables, with incremental sync on refresh. Source data stays where it lives.
- Full-Spectrum AI Search. Search across vectors (dense and sparse), text, JSON, and geospatial data, with hybrid retrieval, BM25, regex, multi-vector and iterative search, and multi-path retrieval. Results can be reranked with Cohere, Voyage AI, RRF, and weighted/boost/decay strategies.
- Unified Lake-Native Storage. Shared storage for serving and analytics built on Vortex, an open columnar format designed for faster, cheaper random reads than Lance and Parquet, paired with object-storage-aware indexes (vector, BM25, JSON) that cut read amplification by over 90%. A 100-million-row schema backfill typically completes in single-digit minutes — without disrupting active query traffic.
Together, these capabilities let AI teams consolidate what previously required parallel always-on serving clusters and separate batch systems onto one platform — with consistent indexes, versioned data, and compute that scales to zero between jobs.
Availability
Zilliz Vector Lakebase is available now in public preview on Zilliz Cloud, alongside Serverless, Dedicated, and BYOC deployment options across more than 30 regions on AWS, Google Cloud, and Microsoft Azure. New work email signups receive $100 in free credits at zilliz.com. Teams running serving, discovery, and analytics on separate stacks can contact the Zilliz team for a tailored walkthrough.
About Zilliz
Zilliz is a leading AI data infrastructure company and the creator of Milvus, the world's most widely adopted open-source vector database, with 44,000+ GitHub stars and over 100 million Docker pulls. Zilliz helps enterprises and AI startups make their unstructured data searchable, analyzable, and governable — turning text, images, audio, video, and more into a strategic asset for production AI.
Zilliz's technology centers on Milvus and Zilliz Cloud. Milvus is an open-source vector database purpose-built for 100-billion-scale vector search. Zilliz Cloud extends that foundation into a fully managed Vector Lakebase platform, combining the high-throughput, low-latency serving capabilities of vector databases with the openness, scalability, and economics of multimodal data lakes. Zilliz powers more than 10,000 enterprises and AI-native startups worldwide, including MiniMax, OpenEvidence, Filevine, Exa, Salesforce, and Read AI.
Headquartered in Redwood Shores, California, Zilliz is backed by leading investors, including Aramco's Prosperity 7 Ventures, Temasek's Pavilion Capital, Hillhouse Capital, 5Y Capital, Yunqi Partners, and Trustbridge Partners. Learn more at Zilliz.com.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
Zilliz Launches Vector Lakebase, Extending the World's Most Adopted Vector Database into a Unified Data Platform for AI
How to Choose Your First Birdwatching Thermal Camera? A Full Review of Thermal Master DV2, T2MAX and X2
LOS ANGELES, Aug. 1, 2026 /PRNewswire/ -- Birders are constantly seeking faster ways to spot hidden wildlife, and thermal imaging cameras have rapidly grown in popularity among birdwatchers and wildlife enthusiasts. Unlike standard optical binoculars, thermal optics deliver faster target detection: users can track avian activity long after sunset, and easily pick out birds concealed within dense foliage in broad daylight.
Thermal Master's debut dedicated birding thermal DV earned runaway success across Southeast Asia, winning broad acclaim from local birding communities. The all-new DV2 now launches officially for European and North American birders, alongside the T2MAX smartphone thermal imager, to cover every mainstream birdwatching use case.
1. Million Units Sold: Thermal Master Birding Cameras Launch Across Europe & North America
As the world's first consumer-grade dedicated thermal DV, the DV2 comes equipped with a 5-inch HD rotating touchscreen. Merging professional thermal detection performance with crisp high-definition imagery, it excels for birding, wildlife monitoring, backcountry camping and after-dark outdoor scouting.
A trailblazer and category leader in birding thermal technology, Thermal Master commands a 50% market share across core Asian birdwatching regions, powered by its exclusive bird-focused imaging tech and trusted by tens of thousands of avian enthusiasts.
The X2 serves as Thermal Master's all-round entry-level smartphone thermal imager, built for long-range field birding and routine household thermal checks. Boasting ultra-light compact construction and sharp thermal output, the model has hit nearly 1 million unit sales throughout Asia, setting a landmark sales record in the mobile thermal imaging segment.
Built as the enhanced successor to the X2, the T2MAX offers full cross-compatibility with iOS and Android smartphones. It delivers drastically boosted sensor sensitivity and 50% extended detection range, reaching a maximum of 910 yards, and ranks among the world's most compact portable thermal monoculars.
2. Five Core Technologies Behind Professional Birdwatching Thermal Imaging
2.1 High-Performance Outdoor Thermal Detector with NETD ≤15mK
Both the DV2 and T2MAX integrate VOx 256×192 @12μm microbolometer detectors, delivering industry-leading thermal sensitivity rated at NETD ≤15mK. This ultra-fine temperature resolution reliably picks up tiny species like winter wrens concealed under thick leaf cover.
2.2 Super Bird Finder 4.0 Achieving Zero Sky Effect
Conventional thermal cameras frequently suffer from the "sky effect" during birding sessions. When scanning tree canopies, frigid sky backgrounds force standard thermal devices to render treetops as hot zones, blending bird heat signatures into surrounding thermal clutter and making targets nearly impossible to isolate. Thermal Master's proprietary Super Bird Finder 4.0 eliminates sky effect interference entirely, sharply separating avian heat signatures from background noise for instant identification of hidden birds.
2.3 Razor-Sharp X³ Super-Resolution Technology
The DV2 and T2MAX utilize identical 256×192 VOx microbolometers. Driven by the proprietary Razor-Sharp X³ super-resolution algorithm, native resolution scales up to 512×384, quadrupling total pixel volume. Beyond a standard FPGA imaging processor, both devices carry custom-built ASIC chips. Combined amplified processing power and optimized algorithms deliver crisper thermal outlines while retaining intricate environmental texture details.
2.4 F/0.8 HD Telephoto Large-Aperture Lens
Fitted with professional F/0.8 long telephoto large-aperture lenses, the DV2 and T2MAX maximize infrared light transmittance to boost thermal radiation capture efficiency. This guarantees crisp, detailed imaging of small distant avian targets amid complex outdoor terrain.
2.5 Insight+ 4.0 AI All-Season Adaptive Algorithm
Thermal Master's award-winning P3, recipient of the 2026 Tom's Guide AI Award, demonstrates the full potential of its exclusive Insight+ 4.0 AI imaging algorithm. The system dynamically calibrates imaging parameters in real time to accommodate shifting seasons and variable field conditions. It sustains consistent thermal clarity across extreme thermal ranges, from frigid -20°C landscapes to humid 40°C tropical rainforests, suited for birding across every global climate zone.
3. Specifications & Performance Comparison
| Specifications | DV2 | T2 MAX |
| Device Type | Thermal Imaging DV | Smartphone Thermal Camera |
| X³IR™ Resolution | 512×384 | 512×384 |
| NETD | 15mK | 15mK |
| Deer Detection Distance | 610 Yards | 910 Yards |
| Cardinal Detection Distance | 100 Yards | 150 Yards |
| Super Bird Finder 4.0 | √ | √ |
| HD & Highlight Mode | √ | √ |
| AI All-Season Adaptive Algorithm | √ | √ |
| Lens Spec | 10mm F0.8 Lens | 15mm F0.8 Lens |
| Retail Price | $499 | $399 |
Specifications
DV2
T2 MAX
Device Type
Thermal Imaging DV
Smartphone Thermal Camera
X³IR™ Resolution
512×384
512×384
NETD
15mK
15mK
Deer Detection Distance
610 Yards
910 Yards
Cardinal Detection Distance
100 Yards
150 Yards
Super Bird Finder 4.0
√
√
HD & Highlight Mode
√
√
AI All-Season Adaptive Algorithm
√
√
Lens Spec
10mm F0.8 Lens
15mm F0.8 Lens
Retail Price
$499
$399
Note: Detection distances are calculated based on Johnson criteria at 3 pixels on target. Recognition requires 6 pixels on target.
4. Product Overview & Target User Scenarios
4.1 Thermal Master DV2: The World's First Consumer-Grade Thermal DV
As the world's first purpose-built birding thermal DV, the DV2 houses a 5-inch HD touchscreen with full 360° rotational adjustment and smooth 1–8x digital zoom. Its expansive high-definition panel enables low-fatigue viewing during multi-hour birding trips, outperforming rigid fixed-screen legacy thermal units.
Tested Detection Distance:
- Northern Cardinal: 100 yards
- Mallard: 150 yards
- Deer: 610 yards
Key Advantages: Professional-grade thermal imaging, 360° adjustable viewing angles, ultra-portable foldable design.
Expandability: Equipped with a rail, compatible with Thermal Master rangefinder accessories and flashlights.
Ideal Users: Birdwatching enthusiasts, users seeking a more comfortable viewing experience, outdoor campers, and wildlife observers.
4.2 Thermal Master T2MAX: 900-Yard Detection Range, The Smallest Thermal Monocular
At just 41.7 grams, the T2MAX smartphone thermal imager integrates a 15mm long-range objective lens, granting it the farthest detection reach of the three lineup models. Drawing on the robust processing power of paired smartphones, it delivers detection performance and image parity matching high-cost standalone professional thermal monoculars. This newly revised dual-platform variant offers seamless plug-and-play compatibility with iOS and Android hardware.
Tested Detection Distance:
- Northern Cardinal: 150 yards
- Mallard: 230 yards
- Deer: 910 yards
Key Advantages:
- Ideal for open environments such as plains, wetlands, and farmland
- Dual-system compatibility, plug-and-play for iOS and Android
- Extensive accessory compatibility for more versatile applications
5. Which Thermal Camera Is Best for You?
DV2: The fully dedicated pick for core birding enthusiasts.
T2MAX: Ideal for users prioritizing extended detection range, or those seeking a compact high-performance backup to replace bulky standalone thermal optics.
With its high-definition thermal imaging quality and practical features designed for complex outdoor environments, the Thermal Master birdwatching thermal cameras has sold nearly one million units across the Asian market. Thermal Master is poised to bring this proven technology to birdwatchers across Europe and North America.
Silas, Chief Technology Officer of Thermal Master, stated confidently: "We've come out as users' top pick in countless side-by-side comparison trials. Once you experience our thermal imaging technology, there's no going back."
Event: Discover Thermal Master's latest product lineup with exclusive promotions—visit thermalmaster.com for special offers.
Business Inquiries: Contact us at Sales@thermalmaster.com for partnerships.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
Thermal Master Officially Launches All-new DV2 and T2MAX Across Europe and North America
