language models has made many Natural Processing (NLP) tasks appear effortless. Tools like ChatGPT sometimes generate strikingly good responses, leading even seasoned professionals to wonder if some jobs might be handed over to algorithms sooner rather than later. Yet, as impressive as these models are, they still stumble on tasks requiring precise, domain-specific extraction. ContentsMotivation: …
Image by Editor | ChatGPT/font> As large language models (LLMs) become increasingly central to applications such as chatbots, coding assistants, and content generation, the challenge of deploying them continues to grow. Traditional inference systems struggle with memory limits, long input sequences, and latency issues. This is where vLLM comes in. In this article, we’ll …
Acknowledgements We thank the International Collegiate Programming Contest (ICPC) for their support. This project was a large-scale collaboration, and its success is due to the combined efforts of many individuals and teams. Hanzhao (Maggie) Lin led the overall technical direction for Gemini competitive programming and ICPC 2025 efforts, and co-led with Heng-Tze Cheng on the …
systems, understanding user intent is fundamental especially in the customer service domain where I operate. Yet across enterprise teams, intent recognition often happens in silos, each team building bespoke pipelines for different products, from troubleshooting assistants to chatbots and issue triage tools. This redundancy slows innovation and makes scaling a challenge. ContentsSpotting a Pattern in …
Image by Ideogram Most of my days as a data scientist look like this: Stakeholder: “Can you tell us how much we made in advertising revenue in the last month and what percentage of that came from search ads?” Me: “Run an SQL query to extract the data and hand it to them.” Stakeholder: …
Here’s How I Built an MCP to Automate My Data Science Job Read More »
This post introduces the emerging field of semantic entity resolution for knowledge graphs, which uses language models to automate the most painful part of building knowledge graphs from text: deduplicating records. Knowledge graphs extracted from text power most autonomous agents, but these contain many duplicates. The work below includes original research, so this post is …
Image by Author | Ideogram Contents# Introduction# 1. itertools.groupby() for Run-Length Encoding# 2. zip() with * for Matrix Transposition# 3. bisect for Maintaining Sorted Order# 4. heapq for Finding Extremes Without Full Sorting# 5. operator.itemgetter for Multi-Level Sorting# 6. collections.defaultdict for Building Data Structures on the Fly# 7. string.Template for Safe String Formatting# Conclusion # Introduction You know the basics of Python’s standard library. …
Uncommon Uses of Common Python Standard Library Functions Read More »
ContentsWhy do we still wrestle with documents in 2025?As a data scientist or ML engineer, why should I care about Docling?Where Docling came fromWhat we’ll do Setting up a development environmentSummary Why do we still wrestle with documents in 2025? in any data-driven organisation, and you’ll encounter a host of PDFs, Word files, PowerPoints, half-scanned images, handwritten notes, and the occasional …
Docling: The Document Alchemist | Towards Data Science Read More »
Image by Author | Canva & ChatGPT Contents# Introduction# 1. Intro to AI Agents and Agent Use Cases# 2. Exploring AI Agentic Frameworks# 3. Understanding AI Agentic Design Patterns# 4. Tool Use Design Pattern# 5. Agentic RAG# 6. Building Trustworthy AI Agents# 7. Planning Design Pattern# 8. Multi-Agent Design Pattern# 9. Metacognition Design Pattern# 10. AI Agents in Production# 11. Using Agentic Protocols# 12. Context Engineering for …
Federated Learning (FL) is we train AI models. Instead of sending all your sensitive data to a central location, FL keeps the data where it is, and only shares model updates. This preserves privacy and enables AI to run closer to where the data is generated. However, with computation and data spread across many devices, …
Fighting Back Against Attacks in Federated Learning Read More »
