
What Actually Happens When LangChain Runs In a Celery Task
Vector search using Celery and LangChain where OpenAI embedding clients live inside Celery workers. Startup signals and lazy resource loading.

Vector search using Celery and LangChain where OpenAI embedding clients live inside Celery workers. Startup signals and lazy resource loading.

A look at adding vector search to a Django service with pgVector and OpenAI embeddings, how Celery keeps embedding workloads scalable.

Moreover, we set it up as a relay using AWS SES for outgoing messages. Without SES, most servers like gmail.com will reject our messages by default.

It was impossible to find a guide that explains how to set up Dovecot for a multi-domain email server, so I made one to remind myself.

I wanted to manage my email accounts without paying for Google Workspace. Here is how I set up OpenLDAP for multi-domain email.

Keeping your Apache configuration up to date with the latest AWS CloudFront IP ranges can be surprisingly important. If you’re using CloudFront as a CDN or reverse proxy in front of your Apache server, you need to tell Apache which proxies are trusted.

Learn how to modify Django Admin to return Django Admin 401 responses on failed login attempts, enabling precise Fail2ban detection and stronger EC2 security.

Learn how to integrate Django and Fail2ban on an EC2 instance using Apache2 to automatically block repeated login attempts and secure your admin panel.

My enhanced release of wodsuz/EasyApplyJobsBot with overhauled application tracking and a novel dashboard suite to monitor your Linkedin job applications. Explore the integration of real-time Grafana dashboards with your job search, offering unparalleled insights into the market.

At the heart of our project lies the Restricted Boltzmann Machine, a type of neural network particularly adept at uncovering hidden patterns in data. In

Vector search using Celery and LangChain where OpenAI embedding clients live inside Celery workers. Startup signals and lazy resource loading.

A look at adding vector search to a Django service with pgVector and OpenAI embeddings, how Celery keeps embedding workloads scalable.