#thecompaniesapi sunday PoC ; add `/ask` endpoint that allows to ask any question about a company and get structured output from all our datasources combined
#thecompaniesapi lots of improvements on our robot, now track per-job metrics, also track input/output tokens for all our AI queries, started collecting dataset on sample domains for our fine-tuning
#thecompaniesapi send prompt to segmentation PR to review ; start working on performances improvement PR ; also try to address some stability issues on our GPU worker
#thecompaniesapi put new robot version & julien work on 🇪🇸 language in production! now working on "prompt to segmentation" feature and gosh the early results are cool!
#thecompaniesapi add storage pipeline for our new extraction feature; add endpoints to our storage server to automatically build fine tuning datasets from our production extraction
#thecompaniesapi finish a month long branch and prepare next steps for ai fine tuning ; replaced old textareas on the bot UI with monaco and improved UX in many spots
#thecompaniesapi working on llama3.1 with large context window, trying to improve some parts of our AI flow before merging it; now properly respects industries & naics constraints for current sample
#thecompaniesapi run my phi3-128k flow using llama3.1 and the results are mind blowing, it's insane how good llama is at conserving context and original purpose even when supplied with thousands of tokens; also shipped multiple hotfixes in robot UI; about to merge a month of work and then hop on fine tuning
#thecompaniesapi get my branch up to date with latest work from @LeCoupa and switch back to llama on critical parts ; also launch extraction of an exhaustive list of all our industries for a customer