Developed a qbash Task to match company names from call transcripts to a database, utilizing phonetic encoding to refine options. Achieved an estimated model cost reduction of approximately 84% with a minor accuracy tradeoff.
added by @qbashdev
We built a qbash Task to match company names from call transcripts to our database.
Compared Jev and OpenAI's Decisions API.
Full catalog first. Then phonetic encoding to narrow the options.
Simulation of 100 generations for binary intent classification showed 3600 LLM calls with inconsistent quality. Using Jev, unusable results were eliminated, achieving 100% parseable quality for the next pipeline.
The author shares insights on integrating a tool for spotting problematic database migrations in their CI/CD pipeline and experimenting with another tool to filter unnecessary jobs based on git diffs.
TypeSafe AI's Jev model has been integrated into a system layer, providing clean, typed decisions from unstructured state in under 500ms. This integration enhances backend processes by scoring and filtering context efficiently.
This process involves handpicked RSS feeds and an automated curator that evaluates date-bound feeds. A custom set of heuristics is used to score and rank posts, with top selections identified through a classifier.
A light gadget was modified with an ESP32 and USB-C, now integrated with HomeAssistant. It changes its light show based on doorbell rings, parcel arrivals, or motion detection.