BLOG different

Real-time personalization with bi(OS)
Introduction I am Saurabh, a Tech Lead at Pharmeasy. My team develops and maintains the ML infrastructure for serving customer recommendations. Last year, we deployed our first real-time recommendation engine for non-Rx product category recommendations on our home page. This blog will explain how Isima’s bi(OS) helped with this initiative and the solution architecture for recommendations. Real-time ML Like any eCommerce property, recommendations' relevance, freshness, and speed are critical for us. While our data science teams pioneer new models for relevance, we in ML engineering care deeply about freshness and speed. Hence, we are cautious when we onboard a new recommendation engine and its new feature store. Our app chooses to timeout instead of waiting for stale and slow recommendations. Converting eCommerce window shoppers eCommerce consumers typically window shop ...

Intel inside™. bi(OS) outside.
Authors: Mayur Kulkarni, Pradeep Madhavarapu, Isima with inputs from Ryan Metz, Rahul Unnikrishnan Nair, Intel Introduction In the early 90s, Intel ran a campaign1 about spotting the very best PCs. This decade established Intel as the undisputed leader in microprocessors. 30 ...

State of Multi-cloud Storage and Compute
Too Long, Must-read The [Live] Multi-cloud-native architecture can deliver a 10X better TCO than the other variants. Some other unique insights we found - Azure’s NVMe drives beat AWS and GCP by a significant amount w.r.to latencies. AWS delivered the most respectable IO ...

The last (and only) mile of resiliency you need. 10X cheaper.
Introduction What happens if the machine, an AZ, or a region serving your customers fails? Nothing - if you rely on cloud-native deployments, stateless microservices, and multi-master databases. That’s the promise anyway. How many IT teams have the luxury of relying on multi-AZ ...

Scaling the multi-cloud Moon
Introduction While the category leaders were busy drowning the market with deafening marketecture(s), our engineers landed on the multi-cloud ‘moon’ of Data and Analytics. TL, DR - Ingest on AWS, Analyze on GCP and Visualize on Azure - in real-time, without migrating an ...

Taming the observability maze
Introduction Last week we wrote about how bi(OS) was hit with the load equivalent to two black Fridays on Thursday by tier-1 global retailers during Black Friday. While we are proud of our achievement, we don’t take our customers’ reliability for granted. Although, we do take a ...

Black Friday 2021 – A bi(OS) Perspective
Introduction Since bi(OS) serves unicorns and tier-1 retailers across three continents, we have a unique vantage point in experiencing Black Friday (and Cyber Monday), especially as it stresses Cloud Data Platforms. This Black Friday saw bi(OS) handle 3x more peak load across all ...

Only Custom Silicon Can Beat Us
Introduction Since the birth of SQL in the mid 70’s, there has been a wall of separation between OLTP and OLAP use cases. One of the defining characteristics of this separation is the stringent need for speed and QoS (quality of service) by OLTP applications. Even today, Data ...

Taming the non-deterministic Cloud
The TL;DR summary Over a 12+ hour run, bi(OS)'s real-time OLAP engine delivered a p99 latency of 1.46ms for inserts, 2.94ms for selects at a peak throughput of 21.5K rows/sec with an 80:20 write: read split for 1KB rows when the system is 70%+ utilized. Writes followed ⅔ QUORUM ...

Who is M/F? Real World Data Quality
My blog last week talked about Schema lost in transit. Let me tell you a real story about a customer. We uploaded data from their repository into bi(OS) and the image above is a screenshot of what we saw on bi(OS) after an hour. We were not surprised as we have seen this story at ...