My Courses
A Hands on Guide to Compact Vision Language Models using SmolDocling
SmolDocling, a 256M VLM, enables efficient document conversion using DocTags to preserve structure while reducing computation.
A Deep Dive into Chain of Draft Prompting
Chain of Draft (CoD) optimizes LLM efficiency by reducing verbosity while maintaining accuracy. It cuts token usage, lowers costs, and speeds up inference for real-world AI applications.
Mastering Multi-Head Latent Attention
DeepSeek’s MLA reduces KV cache memory via low-rank compression and decoupled positional encoding, enabling efficient long-context processing.
Building Agentic AI Applications using OpenAI Agents SDK
OpenAI’s Agents SDK enables efficient multi-agent workflows with context, tools, handoffs, and monitoring.
Observing and Tracing Multi-Modal Multi-Agent Systems through Portkey
Portkey enables observability and tracing in multi-modal, multi-agent systems for enhanced understanding and development.
A Practioner’s Guide to PydanticAI Agents
PydanticAI Agents leverage Pydantic’s validation to build reliable, type-safe AI decision-making systems.
A Practitioner’s Guide to Nexus – A Scalable Multi-Agent Framework
Nexus is a lightweight Python framework for building scalable, reusable LLM-based multi-agent systems.
The DRAMA Framework Explained – From Large LLMs to Efficient Small Dense Retrievers
DRAMA enhances dense retrieval by leveraging LLM-based data augmentation and pruning to create efficient, high-performance retrievers with multilingual and long-context capabilities.
AI Co-Scientist Systems – A Multi Agent System for Research
AI co-scientists powered by Gemini 2.0 accelerate scientific discovery by generating and ranking hypotheses using a multi-agent system.
Benchmarking AI on Software Tasks with OpenAI SWE-Lancer
SWE-Lancer benchmarks AI models on 1,400+ real freelance software engineering tasks worth $1M, evaluating their coding and management capabilities in full-stack development.
