Posts - Engineering

Showing 1 - 12 of 12 Posts

we described how we added a vector model to our search stack, which gave us the power of hybrid search - balancing lexical and semantic matching

How Fullscript replaced K8s-heavy local- and cloud-based dev environments with local Docker Compose and never looked back.

How Fullscript engineered AI into its monolith, boosting developer velocity without rewriting the architecture.

How we fine-tuned a vector model to create a hybrid search engine that understands the intent of our users' queries.

Lessons learned from building Nitro, Fullscript's autonomous background agent.

How we developed an NER service to label user queries, dynamically generate our Elasticsearch query, and return more precise search results.

How we used Metarank to quickly build a learning to rank service to improve the NDCG of our search engine.

Using Quepid and Optuna to optimize the boost values for your Elasticsearch query and improve your NDCG

Describing search metrics that are important when building and evaluating a search engine (precision, recall, & NDCG)

An overview of how Fullscript built a modern search stack to provide more relevant results to its users.

What is the foundations team all about? Check out the impact of coming together at our most recent onsite.

Learn how Fullscript scaled project throughput by 300% using a scalable Project Lead framework that empowers developers and builds leadership