Tag
PipesHub 的创始团队分享了他们优化 PDF 解析的工程实践：用基于 pdfplumber 的轻量解析路径替代部分 Docling 流程，将解析中位时间从 0.98 降至 0.48 秒/页，峰值内存从 2.91GB 降至 1.97GB，同时减少文本丢失。
The author discusses the architecture for scaling AI memory ingestion from thousands to millions of documents, emphasizing orchestration and parallelism over raw compute power, and using Prefect for workflow management.