Commit Graph

6 Commits

Author SHA1 Message Date
arcticfly
b98eb9b729 Trigger llm output retrieval on server (#39)
* Rename tables, add graphile workers, update types

* Add dev:worker command

* Update pnpm-lock.yaml

* Remove sentry config import from worker.ts

* Stop generating new cells in cell router get query

* Generate new cells for new scenarios, variants, and experiments

* Remove most error throwing from queryLLM.task.ts

* Remove promptVariantId and testScenarioId from ModelOutput

* Remove duplicate index from ModelOutput

* Move inputHash from cell to output

* Add TODO

* Add todo

* Show cost and time for each cell

* Always show output stats if there is output

* Trigger LLM outputs when scenario variables are updated

* Add newlines to ends of files

* Add another newline

* Cascade ModelOutput deletion

* Fix linting and prettier

* Return instead of throwing for non-pending cell

* Remove pnpm dev:worker from pnpm:dev

* Update pnpm-lock.yaml
2023-07-14 16:38:46 -06:00
Kyle Corbitt
4770ea34a8 Use javascript functions for prompt completions instead of templated json 2023-07-13 18:01:07 -07:00
Kyle Corbitt
f728027ef6 add evaluations 2023-07-06 13:44:03 -07:00
arcticfly
1ae5612d55 Add promptTokens and completionTokens to model output (#11)
* Default to streaming in config

* Add tokens to database

* Add NEXT_PUBLIC_SOCKET_URL to .env.example

* Disable streaming for functions

* Add newline to types
2023-07-06 13:12:59 -07:00
arcticfly
6389bd54de Save and display timeToComplete on model outputs (#6)
* Calculate and save timeToComplete on model outputs

* Add output stats to function call as well

* Record timeToComplete before parsing response json

* Add default value for timeToComplete
2023-06-30 21:29:28 -07:00
Kyle Corbitt
625d34a9e0 start using migrations 2023-06-30 19:00:32 -07:00