Daily Dose of Data Science | Avi Chawla | Substack·1yAI Agent Crash Course—Part 1
In this crash course, learn about AI agents and their implementation. It covers the fundamentals, memory for agents, agentic flows, guardrails, implementing agentic design patterns, and optimizing agents for production. The aim is to build autonomous systems that can reason, plan, take actions, and correct themselves, going beyond the capabilities of standalone generative models.
Daily Dose of Data Science | Avi Chawla | Substack·1y16 Techniques to Build Real-world RAG Systems
Scaling a prototype RAG system for real-world use presents significant challenges, such as performance bottlenecks and inefficient retrieval. This guide offers 16 practical techniques to help developers overcome these issues across five key pillars. It also highlights five agentic AI design patterns, including reflection, tool use, ReAct, planning, and multi-agent patterns, which enable LLMs to refine outputs, gather information, and subdivide tasks more effectively.
Daily Dose of Data Science | Avi Chawla | Substack·1yOpen-source Python Development Landscape
Explore the essential tools for various stages of Python development, including dependency and package managers, monitoring and profiling, virtual environments, linters and style checkers, type checkers, logging, testing, debugging, code refactoring, and code security. These tools are crucial for improving development workflow and code quality.
Daily Dose of Data Science | Avi Chawla | Substack·1y4 Ways to Test ML Models in Production
Testing machine learning models in production is crucial for reliability. Four key strategies are A/B testing, canary testing, interleaved testing, and shadow testing. These methods allow models to be tested on real-world data while minimizing risk and user impact. Tools like Maxim can aid in simulating, evaluating, and observing AI agents for better performance before deployment.
Daily Dose of Data Science | Avi Chawla | Substack·1y[Hands-on] Agentic RAG Using DeepSeek-R1
Learn how to build an intelligent RAG application using DeepSeek-R1 that offers vision-based indexing and supports over 100 file formats without requiring OCR or text extraction. The tutorial walks through the setup of a local DeepSeek model, integrating tools like Qdrant and FireCrawl, and defining agents for retrieving context and generating responses using CrewAI.