Elise Tanaka

Elise Tanaka

Aug 7

Lessons from Scaling Data Deduplication for Trillion-Token LLMs

3 min read

Elise Tanaka

Aug 4

Building Production-Grade Vector Search: Performance Insights from Zilliz Cloud on AWS

#ai #programming

3 min read

Elise Tanaka

Jul 28

Shifting Vector Database Workloads to Arm Neoverse: Performance and Cost Observations

3 min read

Elise Tanaka

Jul 25

Filtered Vector Search: Five Techniques for Balancing Recall and Latency

3 min read

Elise Tanaka

Jul 21

The Engineering Reality Behind 10x Vector Search Improvements: A First-Hand Analysis

2 min read

Elise Tanaka

Jul 14

Re-architecting Payment Systems: What Vector Databases Revealed About Our AI Infrastructure

2 min read

Elise Tanaka

Jul 10

The Hidden Scalability Challenges in Real-Time AI Document Processing

2 min read

Elise Tanaka

Jul 7

The Nuts and Bolts of HNSW: What Works, What Doesn’t, and Why I Care

3 min read

Elise Tanaka

Jul 3

Unpacking DiskANN: My Technical Journey Through Billion-Scale Vector Search

3 min read

Elise Tanaka

Jun 30

What Building a Legal AI System Taught Me About Vector Search Tradeoffs

3 min read

Elise Tanaka

Jun 26

Why I Stopped Using SQL Queries for AI Workloads (and What Happened Next)

1

3 min read

Elise Tanaka

Jun 23

Cross-Language Model Inference Without Python: An Engineering Perspective

3 min read

Elise Tanaka

Jun 18

What Working with Vector Databases Taught Me About Semantic Search Architectures

3 min read

Elise Tanaka

Jun 16

What Zero-Downtime Vector Database Migrations Taught Me About Consistency Tradeoffs

3 min read

Elise Tanaka

Jun 12

Milvus and Late Chunking: What I Learned About Context-Aware Embedding in RAG

3 min read

Elise Tanaka

Jun 10

What I Learned Comparing Apache Cassandra and Zilliz Cloud for Vector Search Workloads

1

4 min read

Elise Tanaka

May 26

Comparing Vector Search Approaches: What I Learned Testing pgvector vs. Milvus

3 min read

Elise Tanaka

May 20

Qdrant Cloud vs. Zilliz Cloud: A Technical Audit of Vector Database Solutions

2 min read

DEV Community

Badges

Writing Debut

Lessons from Scaling Data Deduplication for Trillion-Token LLMs

Building Production-Grade Vector Search: Performance Insights from Zilliz Cloud on AWS

Shifting Vector Database Workloads to Arm Neoverse: Performance and Cost Observations

Filtered Vector Search: Five Techniques for Balancing Recall and Latency

The Engineering Reality Behind 10x Vector Search Improvements: A First-Hand Analysis

Re-architecting Payment Systems: What Vector Databases Revealed About Our AI Infrastructure

The Hidden Scalability Challenges in Real-Time AI Document Processing

The Nuts and Bolts of HNSW: What Works, What Doesn’t, and Why I Care

Unpacking DiskANN: My Technical Journey Through Billion-Scale Vector Search

What Building a Legal AI System Taught Me About Vector Search Tradeoffs

Why I Stopped Using SQL Queries for AI Workloads (and What Happened Next)

Cross-Language Model Inference Without Python: An Engineering Perspective

What Working with Vector Databases Taught Me About Semantic Search Architectures

What Zero-Downtime Vector Database Migrations Taught Me About Consistency Tradeoffs

Milvus and Late Chunking: What I Learned About Context-Aware Embedding in RAG

What I Learned Comparing Apache Cassandra and Zilliz Cloud for Vector Search Workloads

Comparing Vector Search Approaches: What I Learned Testing pgvector vs. Milvus

Qdrant Cloud vs. Zilliz Cloud: A Technical Audit of Vector Database Solutions