balaji balLook Mom! I reinvented the application server! Exploring Dynamically Configurable APIsI’ve been toying with the idea of writing this piece of code for ages — something to explore dynamically generated API endpoints that are…2d ago2d ago
balaji balAI in Architecture: Notes from 3 years of ExplorationsThe following is an interview with myself on my explorations of the past 3 years with AI and Computational Design in Architecture. My…Aug 19Aug 19
balaji balPrompt Architectures: An Overview of structured prompting strategiesStructuring prompts effectively for AI is essential for getting the desired outcomes. Different prompt frameworks can help you craft…Aug 10Aug 10
balaji balinSTREAM-ZEROThe True Cost of a FeatureRecently, I was on a call with a major Email API vendor regarding the integration with the StreamZero platform. Given that StreamZero has…Jul 18Jul 18
balaji balinSTREAM-ZERORequirements Documentation AI ToolsMost of the attention is on writing code despite the fact that poor requirements documentation and the effort required to maintain them are…Jul 16Jul 16
balaji balinSTREAM-ZEROOpenAI API implementation for 3rd party LLMOpenAI’s API is fast becoming the de-facto standard for interacting with LLMs. From a ‘pragmatic engineering’ perspective it means not…Jul 11Jul 11
balaji balinSTREAM-ZEROStreamZero Model Store : An OverviewA high level technical overview of the StreamZero Model Store and Runtime Environment. Host and execute-on-demand 1000s of AI…Jul 11Jul 11
balaji balinSTREAM-ZEROApache APISIX: Overview and AdvantagesApache APISIX is a dynamic, cloud-native, distributed API gateway, offering a robust platform for managing microservices, service mesh, and…Jul 1Jul 1
balaji balinSTREAM-ZEROUnderstanding the Essentials of Model Distillation in AI“RAG” (Retrieval-Augmented Generation) and Model Distillation are both advanced techniques used in the field of artificial intelligence…Jun 8Jun 8
balaji balinSTREAM-ZEROChunking Strategies and Retrieval-Augmented GenerationRetrieval-Augmented Generation (RAG) is essential for equipping your Large Language Models (LLMs) with the most relevant enterprise data…May 31May 31