IntenseFinance/nosqlbench
3
0
Fork 0
mirror of https://github.com/nosqlbench/nosqlbench.git synced 2024-12-23 15:40:44 -06:00
Code Issues Packages Projects Releases Wiki Activity

adding ann_benchmarks.yaml

Browse Source
This commit is contained in:
Mark Wolters 2024-02-08 19:23:04 -04:00
parent fa4ff13a89
commit 8f4aa5cec5
1 changed files with 82 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

82
adapter-aws-opensearch/src/main/resources/activities/ann_benchmarks.yaml Normal file
View File

@ -0,0 +1,82 @@
description: |
basic test for vectors in open search
https://www.elastic.co/guide/en/elasticsearch/reference/current/rest-apis.html
template vars:
TEMPLATE(indexname,vectors_index)
TEMPLATE(dimensions,25)
params:
driver: opensearch
instrument: true
scenarios:
vectors:
drop: run tags='block:drop' labels='target:opensearch' threads===1 cycles===UNDEF
schema: run tags='block:schema' labels='target:opensearch' threads===1 cycles===UNDEF
rampup: run tags='block:rampup' labels='target:opensearch' threads=TEMPLATE(rampup_threads,10) cycles=TEMPLATE(trainsize)
search: run tags='block:search' labels='target:opensearch' threads=TEMPLATE(search_threads,10) cycles=TEMPLATE(testsize)
# errors=counter,warn,log
bindings:
id: ToString()
test_floatlist: HdfFileToFloatList("testdata/TEMPLATE(dataset).hdf5", "/test");
relevant_indices: HdfFileToIntArray("testdata/TEMPLATE(dataset).hdf5", "/neighbors")
distance_floatlist: HdfFileToFloatList("testdata/TEMPLATE(dataset).hdf5", "/distance")
train_floatlist: HdfFileToFloatList("testdata/TEMPLATE(dataset).hdf5", "/train");
blocks:
drop:
ops:
drop_index:
delete_index: TEMPLATE(indexname,vectors_index)
schema:
ops:
create_index:
create_index: TEMPLATE(indexname)
mappings:
m1: v1
search:
ops:
search:
knn_search: TEMPLATE(indexname,vectors_index)
k: 100
vector: "{test_floatlist}"
field: value
search_and_verify:
ops:
select_ann_limit_TEMPLATE(k,100):
knn_search: TEMPLATE(indexname,vectors_index)
k: 100
vector: "{test_floatlist}"
field: value
verifier-init: |
relevancy=new io.nosqlbench.nb.api.engine.metrics.wrappers.RelevancyMeasures(_parsed_op)
for (int k in List.of(100)) {
relevancy.addFunction(io.nosqlbench.engine.extensions.computefunctions.RelevancyFunctions.recall("recall",k));
relevancy.addFunction(io.nosqlbench.engine.extensions.computefunctions.RelevancyFunctions.precision("precision",k));
relevancy.addFunction(io.nosqlbench.engine.extensions.computefunctions.RelevancyFunctions.F1("F1",k));
relevancy.addFunction(io.nosqlbench.engine.extensions.computefunctions.RelevancyFunctions.reciprocal_rank("RR",k));
relevancy.addFunction(io.nosqlbench.engine.extensions.computefunctions.RelevancyFunctions.average_precision("AP",k));
}
verifier: |
// driver-specific function
actual_indices=pinecone_utils.responseIdsToIntArray(result)
// driver-agnostic function
relevancy.accept({relevant_indices},actual_indices);
return true;
bulkrampup:
ops:
bulk_index:
bulk_index:
- '{"key":"{id}","value":"{train_floatlist}"'
-
rampup:
ops:
index:
index: TEMPLATE(indexname)
document:
key: "{id}"
value: "{train_floatlist}"