Loading / 加载中
Thinkgap feed
Curated items are read from the processed items table and served as a bilingual feed.
9 items
This brief post mentions aligning with Claude Code to boost productivity with LLMs, but the content provides no specific techniques, data, or concrete guidance. It merely introduces the topic without detailed elaboration.
This tutorial from the Enterprise Document Intelligence series shows how Azure Document Intelligence’s layout model extracts relational tables from PDFs where PyMuPDF falls short. The Azure approach preserves native table cells and works on scanned pages via integrated OCR. It also retrieves captions and headings without relying on regular expressions. The method is presented as a superior parsing step for Retrieval Augmented Generation (RAG) pipelines.
The author attempted to make an ETL pipeline production-ready. Three things broke during the process. Each failure taught insights that scripting alone could not provide. The experience highlighted the additional complexities of production data engineering.
The post argues that the true bottleneck in business intelligence was never the analysis itself. It appears on Towards Data Science but contains no further explanation or supporting details beyond that single claim.
This article explores how Large Language Models can enhance the precision of recommendation systems. It provides a Python-based tutorial on integrating LLMs into recommendation pipelines. The author demonstrates practical techniques for leveraging LLM capabilities to better understand user preferences and item features. The approach aims to improve recommendation accuracy beyond traditional methods.
This tutorial introduces four new techniques to maximize the use of Claude Code, an AI-powered coding assistant. The techniques aim to improve productivity and efficiency in software development. Readers can learn practical tips to get the most out of Claude Code's features.