Skip to content

feat(model-eval-ingest): [WIP] cloud-side worker for bench → kiloBench ingest #3028

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
lambertjosh wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

feat(model-eval-ingest): [WIP] cloud-side worker for bench → kiloBench ingest #3028

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 26 additions & 0 deletions packages/db/src/migrations/0109_watery_freak.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
CREATE TABLE "model_eval_ingest" (
"id" uuid PRIMARY KEY DEFAULT gen_random_uuid() NOT NULL,
"bench_job_name" text NOT NULL,
"bench_job_url" text NOT NULL,
"provider" text NOT NULL,
"model" text NOT NULL,
"model_stats_id" uuid,
"variant" text,
"task_source" text NOT NULL,
"task_source_display_name" text,
"n_trials" integer NOT NULL,
"success_rate" numeric(5, 4) NOT NULL,
"avg_cost_usd" numeric(10, 6),
"avg_input_tokens" integer,
"avg_output_tokens" integer,
"avg_cache_read_tokens" integer,
"avg_execution_ms" integer,
"review_note" text,
"promoted_by_email" text NOT NULL,
"promoted_at" timestamp with time zone DEFAULT now() NOT NULL
);
--> statement-breakpoint
ALTER TABLE "model_eval_ingest" ADD CONSTRAINT "model_eval_ingest_model_stats_id_model_stats_id_fk" FOREIGN KEY ("model_stats_id") REFERENCES "public"."model_stats"("id") ON DELETE no action ON UPDATE no action;--> statement-breakpoint
CREATE INDEX "IDX_model_eval_ingest_model" ON "model_eval_ingest" USING btree ("model");--> statement-breakpoint
CREATE INDEX "IDX_model_eval_ingest_model_stats" ON "model_eval_ingest" USING btree ("model_stats_id");--> statement-breakpoint
CREATE INDEX "IDX_model_eval_ingest_lookup" ON "model_eval_ingest" USING btree ("provider","model","variant","task_source","promoted_at");
Loading
Loading