1d ago · 13 min read · Why Most RAG Demos Fail in Production You've seen the 50-line RAG demo. Load a PDF, embed it, ask a question, get an answer. It works in a notebook. It falls apart the moment you add real users, large
Join discussionJun 1 · 9 min read · Celery is one of the most widely deployed task queue systems in Python. It is also, by default, a system that silently loses approximately 8% of your tasks the moment a worker crashes. This is not a b
Join discussionApr 30 · 7 min read · Building docling-server: a one-command document API for our AI pipeline This is another one in the series where I walk through my open-source projects. Earlier ones covered backupctl, mcp-pool, and a few smaller tools. Today it is docling-server — t...
Join discussion
Apr 22 · 7 min read · Building docling-server: a one-command document API for our AI pipeline This is another one in the series where I walk through my open-source projects. Earlier ones covered backupctl, mcp-pool, and a few smaller tools. Today it is docling-server — t...
Join discussionApr 14 · 10 min read · 📌 Executive Summary In a real-world setup using RabbitMQ + Celery + Docker, I encountered multiple production-level issues: SMTP credential mismatch (username & domain swapped) Environment variable
Join discussion
Mar 25 · 15 min read · Your Celery workers are slowly eating all your RAM. You've checked your tasks, your results backend, your broker — everything looks fine. But every few hours, the workers get OOM-killed. Here's how I
Join discussion
Mar 5 · 5 min read · A practical walkthrough of Redis buffering, Celery Beat flushing, and multilingual Django — for any counter, queue, or rate-sensitive write pattern. There's a specific class of problem in web develo
Join discussion
Mar 3 · 11 min read · Background Job and Workflow Tools: BullMQ, Temporal, and Celery Every non-trivial application eventually needs to do work outside the request-response cycle. Send an email after signup. Generate a PDF invoice. Process a video upload. Sync data with a...
Join discussionFeb 10 · 3 min read · Introduction In most Django apps, tasks are handled synchronously: a user makes a request, Django processes it, and the response is returned. But what about tasks that take a long time—like sending emails, generating reports, or cleaning up old data?...
Join discussion
