Add YAML config files for parquet for BEIR (#2599)

src/main/resources/regression/beir-v1.0.0-arguana.bge-base-en-v1.5.parquet.flat.cached.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-arguana.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/arguana.parquet
+
+index_path: indexes/parquet/arguana
+index_type: flat
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: ""
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: JsonStringVector
+topics:
+- name: "BEIR (v1.0.0): ArguAna"
+  id: test
+  path: topics.beir-v1.0.0-arguana.test.bge-base-en-v1.5.jsonl.gz
+  qrel: qrels.beir-v1.0.0-arguana.test.txt
+
+models:
+- name: bge-flat-cached
+  display: BGE-base-en-v1.5
+  type: flat
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000
+  results:
+    nDCG@10:
+    - 0.6361
+    R@100:
+    - 0.9915
+    R@1000:
+    - 0.9964

src/main/resources/regression/beir-v1.0.0-arguana.bge-base-en-v1.5.parquet.flat.onnx.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-arguana.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/arguana.parquet
+
+index_path: indexes/parquet/arguana
+index_type: flat
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: ""
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: TsvString
+topics:
+- name: "BEIR (v1.0.0): ArguAna"
+  id: test
+  path: topics.beir-v1.0.0-arguana.test.tsv.gz
+  qrel: qrels.beir-v1.0.0-arguana.test.txt
+
+models:
+- name: bge-flat-onnx
+  display: BGE-base-en-v1.5
+  type: flat
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000 -encoder BgeBaseEn15
+  results:
+    nDCG@10:
+    - 0.6361
+    R@100:
+    - 0.9915
+    R@1000:
+    - 0.9964

src/main/resources/regression/beir-v1.0.0-arguana.bge-base-en-v1.5.parquet.hnsw.cached.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-arguana.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/arguana.parquet
+
+index_path: indexes/parquet/arguana
+index_type: hnsw
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: -M 16 -efC 100
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: JsonStringVector
+topics:
+- name: "BEIR (v1.0.0): ArguAna"
+  id: test
+  path: topics.beir-v1.0.0-arguana.test.bge-base-en-v1.5.jsonl.gz
+  qrel: qrels.beir-v1.0.0-arguana.test.txt
+
+models:
+- name: bge-hnsw-cached
+  display: BGE-base-en-v1.5
+  type: hnsw
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000 -efSearch 1000
+  results:
+    nDCG@10:
+    - 0.6361
+    R@100:
+    - 0.9915
+    R@1000:
+    - 0.9964

src/main/resources/regression/beir-v1.0.0-arguana.bge-base-en-v1.5.parquet.hnsw.onnx.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-arguana.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/arguana.parquet
+
+index_path: indexes/parquet/arguana
+index_type: hnsw
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: -M 16 -efC 100 -memoryBuffer 65536 -noMerge
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: TsvString
+topics:
+- name: "BEIR (v1.0.0): ArguAna"
+  id: test
+  path: topics.beir-v1.0.0-arguana.test.tsv.gz
+  qrel: qrels.beir-v1.0.0-arguana.test.txt
+
+models:
+- name: bge-hnsw-onnx
+  display: BGE-base-en-v1.5
+  type: hnsw
+  params: -generator VectorQueryGenerator -topicField title -removeQuery -threads
+    16 -hits 1000 -efSearch 1000 -encoder BgeBaseEn15
+  results:
+    nDCG@10:
+    - 0.6361
+    R@100:
+    - 0.9915
+    R@1000:
+    - 0.9964

src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.parquet.flat.cached.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-bioasq.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/bioasq.parquet
+
+index_path: indexes/parquet/bioasq
+index_type: flat
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: ""
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: JsonStringVector
+topics:
+- name: "BEIR (v1.0.0): BioASQ"
+  id: test
+  path: topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz
+  qrel: qrels.beir-v1.0.0-bioasq.test.txt
+
+models:
+- name: bge-flat-cached
+  display: BGE-base-en-v1.5
+  type: flat
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000
+  results:
+    nDCG@10:
+    - 0.4149
+    R@100:
+    - 0.6317
+    R@1000:
+    - 0.8059

src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.parquet.flat.onnx.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-bioasq.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/bioasq.parquet
+
+index_path: indexes/parquet/bioasq
+index_type: flat
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: ""
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: TsvString
+topics:
+- name: "BEIR (v1.0.0): BioASQ"
+  id: test
+  path: topics.beir-v1.0.0-bioasq.test.tsv.gz
+  qrel: qrels.beir-v1.0.0-bioasq.test.txt
+
+models:
+- name: bge-flat-onnx
+  display: BGE-base-en-v1.5
+  type: flat
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000 -encoder BgeBaseEn15
+  results:
+    nDCG@10:
+    - 0.4149
+    R@100:
+    - 0.6317
+    R@1000:
+    - 0.8059

src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.parquet.hnsw.cached.yaml

@@ -0,0 +1,53 @@
+corpus: beir-v1.0.0-bioasq.bge-base-en-v1.5
+corpus_path: collections/beir-v1.0.0/bge-base-en-v1.5/bioasq.parquet
+
+index_path: indexes/parquet/bioasq
+index_type: hnsw
+collection_class: ParquetDenseVectorCollection
+generator_class: ParquetDenseVectorDocumentGenerator
+index_threads: 16
+index_options: -M 16 -efC 100
+
+metrics:
+- metric: nDCG@10
+  command: bin/trec_eval
+  params: -c -m ndcg_cut.10
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@100
+  command: bin/trec_eval
+  params: -c -m recall.100
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+- metric: R@1000
+  command: bin/trec_eval
+  params: -c -m recall.1000
+  separator: "\t"
+  parse_index: 2
+  metric_precision: 4
+  can_combine: false
+
+topic_reader: JsonStringVector
+topics:
+- name: "BEIR (v1.0.0): BioASQ"
+  id: test
+  path: topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz
+  qrel: qrels.beir-v1.0.0-bioasq.test.txt
+
+models:
+- name: bge-hnsw-cached
+  display: BGE-base-en-v1.5
+  type: hnsw
+  params: -generator VectorQueryGenerator -topicField vector -removeQuery -threads
+    16 -hits 1000 -efSearch 5000
+  results:
+    nDCG@10:
+    - 0.4149
+    R@100:
+    - 0.6317
+    R@1000:
+    - 0.8059