Vinayak ShanawadinDataDrivenInvestorHow to handle a Million Vector Embeddings in the RAG ApplicationsExplore the use of PGVector in managing a large dataset for RAG applications and the challenges we faced along the wayMar 25Mar 25
Vinayak ShanawadinDataDrivenInvestorSlashing Python Docker build times in half with uvuv: Python packaging in RustFeb 161Feb 161
Vinayak ShanawadinDataDrivenInvestorBeyond Relational Databases: Taming LLM and Transformer Embeddings with PGVectorFrom Text to Insights: An End-to-End Guide to PGVectorFeb 131Feb 131
Vinayak ShanawadBuild an ML Pipeline (Part 2) — Model Registration and Serving with MLflow and KServeSeamless Model Deployment: MLflow and KServe CollaborationDec 4, 2023Dec 4, 2023
Vinayak ShanawadBuild an ML Pipeline (Part 1) — Getting Started with Kubeflow V2 PipelinesDiscovering Kubeflow: Launching into ML PipelinesDec 4, 20234Dec 4, 20234
Vinayak ShanawadServing Hugging Face Transformers: Optimizing Custom Model Deployment with Seldon CoreTransforming Deployment: Seldon Core Meets Hugging FaceSep 14, 20231Sep 14, 20231
Vinayak ShanawadFrom Dev to Production: Deploying HuggingFace BERT with KServeThe Future of NLP Deployment: BERT Models and KServe in ActionSep 11, 20234Sep 11, 20234
Vinayak ShanawadData Analysis at Warp Speed: Explore the World of PolarsEmpowering Data Scientists and Engineers with Lightning-Fast Data Analysis and Transformation CapabilitiesJul 1, 2023Jul 1, 2023
Vinayak ShanawadSay Goodbye to Costly BERT Inference: Turbocharge with AWS Inferentia2 and Hugging Face…Achieve 2–3ms inference speed and high throughput for text classification tasksJun 1, 2023Jun 1, 2023
Vinayak ShanawadMonitoring and Saving AWS SageMaker Inference ExpensesTips and Tools for Effective Monitoring and SavingsApr 30, 2023Apr 30, 2023