sqlite-vec/benchmarks-ann/datasets/cohere10m/Makefile

BASE_URL = https://assets.zilliz.com/benchmark/cohere_large_10m

TRAIN_PARQUETS = $(shell printf 'train-%02d-of-10.parquet ' 0 1 2 3 4 5 6 7 8 9)
OTHER_PARQUETS = test.parquet neighbors.parquet
PARQUETS = $(TRAIN_PARQUETS) $(OTHER_PARQUETS)

.PHONY: all download clean

all: base.db

# Use: make -j12 download
download: $(PARQUETS)

train-%-of-10.parquet:
	curl -L -o $@ $(BASE_URL)/$@

test.parquet:
	curl -L -o $@ $(BASE_URL)/test.parquet

neighbors.parquet:
	curl -L -o $@ $(BASE_URL)/neighbors.parquet

base.db: $(PARQUETS) build_base_db.py
	uv run --with pandas --with pyarrow python build_base_db.py

clean:
	rm -f base.db
Add comprehensive ANN benchmarking suite (#279) Extend benchmarks-ann/ with results database (SQLite with per-query detail and continuous writes), dataset subfolder organization, --subset-size and --warmup options. Supports systematic comparison across flat, rescore, IVF, and DiskANN index types. 2026-03-31 01:29:49 -07:00			`BASE_URL = https://assets.zilliz.com/benchmark/cohere_large_10m`

			`TRAIN_PARQUETS = $(shell printf 'train-%02d-of-10.parquet ' 0 1 2 3 4 5 6 7 8 9)`
			`OTHER_PARQUETS = test.parquet neighbors.parquet`
			`PARQUETS = $(TRAIN_PARQUETS) $(OTHER_PARQUETS)`

			`.PHONY: all download clean`

			`all: base.db`

			`# Use: make -j12 download`
			`download: $(PARQUETS)`

			`train-%-of-10.parquet:`
			`curl -L -o $@ $(BASE_URL)/$@`

			`test.parquet:`
			`curl -L -o $@ $(BASE_URL)/test.parquet`

			`neighbors.parquet:`
			`curl -L -o $@ $(BASE_URL)/neighbors.parquet`

			`base.db: $(PARQUETS) build_base_db.py`
			`uv run --with pandas --with pyarrow python build_base_db.py`

			`clean:`
			`rm -f base.db`