prior attempt outputs and problems given to any .check callback #promptgun

all attempted LLM results (parsed and typed, if structured) are available on error object thrown when a .check reaches its max attempt count #promptgun

fixed: when a .check reaching max attempt count interrupts LLM conversation by throwing an error, that error does not trigger the retry mechanism for individual OpenAI calls #promptgun

Added more data sources #happenlist

added several more data sources and improved data import #happenlist

pre-made constants for every day of the week from #globol

slight in-place correction: throwing in .check clause now stops prompt, escapes answer iteration #promptgun

Made a list of possible revenue streams, fueled motivation #happenlist

Fixed outdated json configs of data sources. Last week saw many updates to the data collection module and this is still an afterbug #happenlist

Flying to Rome and finishing a day job day

Pure dayjob today

Improved the docs of Promptgun a lot. Added many missing pieces of information. If you use OpenAI API from a Typescript or Javascript project, you’d do me a big favor if you want to go take a look at #promptgun to see if you can get it set up in 1 minute or if something is unclear

Made tools even simpler to add to your prompts in #promptgun. Go take a look if you use the OpenAI API in a NodeJS project!

Adding more data sources today #happenlist

expanded crawl reach #happenlist

#monoflux was not running all flatMap callbacks as soon as source Flux emitted a value, but sometimes waiting until entire source Flux completed – now solved

Added more data sources #happenlist

Automated data collection #happenlist

day job today

tenfolded scraping efficiency again #happenlist