diff --git a/docs/fatjar-regressions/fatjar-regressions-v0.37.0.md b/docs/fatjar-regressions/fatjar-regressions-v0.37.0.md index e4d1057153..254cbb8135 100644 --- a/docs/fatjar-regressions/fatjar-regressions-v0.37.0.md +++ b/docs/fatjar-regressions/fatjar-regressions-v0.37.0.md @@ -36,19 +36,20 @@ curl -X GET "http://localhost:8081/api/v1.0/indexes/msmarco-v2.1-doc/search?quer The json results are the same as the output of the `-outputRerankerRequests` option in `SearchCollection`, described below for TREC 2024 RAG. Use the `hits` parameter to specify the number of hits to return, e.g., `hits=1000` to return the top 1000 hits. +Switch to `msmarco-v2.1-doc-segmented` in the route to query the segmented docs instead. Details of the built-in webapp and REST API can be found [here](../rest-api.md). ## TREC 2024 RAG -For the TREC 2024 RAG Track, we have thus far only implemented BM25 baselines on the MS MARCO V2.1 document corpus (both the doc and doc segmented variants). +For the [TREC 2024 RAG Track](https://trec-rag.github.io/), we have thus far only implemented BM25 baselines on the MS MARCO V2.1 document corpus (both the doc and doc segmented variants). ❗ Beware, you need lots of space to run these experiments. The `msmarco-v2.1-doc` prebuilt index is 63 GB uncompressed. The `msmarco-v2.1-doc-segmented` prebuilt index is 84 GB uncompressed. Both indexes will be downloaded automatically. -This release of Anserini comes with the test topic for the TREC 2024 RAG track (`-topics rag24.test`). +This release of Anserini comes with bindings for the test topics for the TREC 2024 RAG track (`-topics rag24.test`). To generate jsonl output containing the raw documents that can be reranked and further processed, use the `-outputRerankerRequests` option to specify an output file. For example: @@ -61,7 +62,7 @@ java -cp $ANSERINI_JAR io.anserini.search.SearchCollection \ -outputRerankerRequests $OUTPUT_DIR/results.msmarco-v2.1-doc.bm25.rag24.test.jsonl ``` -And the output looks something like: +And the output looks something like (pipe through `jq` to pretty-print): ```bash $ head -n 1 $OUTPUT_DIR/results.msmarco-v2.1-doc.bm25.rag24.test.jsonl | jq diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.md index 1717d3d172..f192011d78 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.md @@ -58,7 +58,7 @@ bin/run.sh io.anserini.search.SearchHnswDenseVectors \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ -output runs/run.beir-v1.0.0-bioasq.bge-base-en-v1.5.bge-hnsw-int8-cached.topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.txt \ - -hits 1000 -efSearch 1000 -removeQuery -threads 16 & + -hits 1000 -efSearch 2000 -removeQuery -threads 16 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.md index 17dde96416..6d89e4ce77 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.md @@ -58,7 +58,7 @@ bin/run.sh io.anserini.search.SearchHnswDenseVectors \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq.bge-base-en-v1.5.bge-hnsw-int8-onnx.topics.beir-v1.0.0-bioasq.test.txt \ - -encoder BgeBaseEn15 -hits 1000 -efSearch 1000 -removeQuery -threads 16 & + -encoder BgeBaseEn15 -hits 1000 -efSearch 2000 -removeQuery -threads 16 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.md index b4fbef49ff..0c1e906aab 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.md @@ -58,7 +58,7 @@ bin/run.sh io.anserini.search.SearchHnswDenseVectors \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.gz \ -topicReader JsonStringVector \ -output runs/run.beir-v1.0.0-bioasq.bge-base-en-v1.5.bge-hnsw-cached.topics.beir-v1.0.0-bioasq.test.bge-base-en-v1.5.jsonl.txt \ - -hits 1000 -efSearch 1000 -removeQuery -threads 16 & + -hits 1000 -efSearch 2000 -removeQuery -threads 16 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.md b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.md index 1bdcdd0b99..a6d559fd0a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.md @@ -58,7 +58,7 @@ bin/run.sh io.anserini.search.SearchHnswDenseVectors \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq.bge-base-en-v1.5.bge-hnsw-onnx.topics.beir-v1.0.0-bioasq.test.txt \ - -encoder BgeBaseEn15 -hits 1000 -efSearch 1000 -removeQuery -threads 16 & + -encoder BgeBaseEn15 -hits 1000 -efSearch 2000 -removeQuery -threads 16 & ``` Evaluation can be performed using `trec_eval`: diff --git a/src/main/java/io/anserini/index/IndexInfo.java b/src/main/java/io/anserini/index/IndexInfo.java index ccd1c96474..69ab09c7e6 100644 --- a/src/main/java/io/anserini/index/IndexInfo.java +++ b/src/main/java/io/anserini/index/IndexInfo.java @@ -20,6 +20,7 @@ public enum IndexInfo { CACM("cacm", "Lucene index of the CACM corpus.", "lucene-index.cacm.20221005.252b5e.tar.gz", + "", "CACM", "BM25", new String[] { @@ -30,6 +31,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE("msmarco-v1-passage", "Lucene index of the MS MARCO V1 passage corpus.", "lucene-inverted.msmarco-v1-passage.20221004.252b5e.tar.gz", + "", "MS MARCO V1 Passage", "BM25", new String[] { @@ -39,6 +41,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_SPLADE_PP_ED("msmarco-v1-passage.splade-pp-ed", "Lucene impact index of the MS MARCO V1 passage corpus encoded by SPLADE++ CoCondenser-EnsembleDistil.", "lucene-inverted.msmarco-v1-passage.splade-pp-ed.20230524.a59610.tar.gz", + "", "MS MARCO V1 Passage", "SPLADE++ EnsembleDistil", new String[] { @@ -48,6 +51,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_COS_DPR_DISTIL("msmarco-v1-passage.cos-dpr-distil", "Lucene HNSW index of the MS MARCO V1 passage corpus encoded by cos-DPR Distil.", "lucene-hnsw.msmarco-v1-passage.cos-dpr-distil.20240108.825148.tar.gz", + "", "MS MARCO V1 Passage", "cosDPR-distil w/ HNSW fp32", new String[] { @@ -57,6 +61,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_COS_DPR_DISTIL_QUANTIZED("msmarco-v1-passage.cos-dpr-distil.quantized", "Lucene quantized HNSW index of the MS MARCO V1 passage corpus encoded by cos-DPR Distil.", "lucene-hnsw-int8.msmarco-v1-passage.cos-dpr-distil.20240108.825148.tar.gz", + "", "MS MARCO V1 Passage", "cosDPR-distil w/ HNSW int8", new String[] { @@ -66,6 +71,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_BGE_BASE_EN_15("msmarco-v1-passage.bge-base-en-v1.5", "Lucene HNSW index of the MS MARCO V1 passage corpus encoded by BGE-base-en-v1.5.", "lucene-hnsw.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.tar.gz", + "", "MS MARCO V1 Passage", "bge-base-en-v1.5 w/ HNSW fp32", new String[] { @@ -75,6 +81,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_BGE_BASE_EN_15_QUANTIZED("msmarco-v1-passage.bge-base-en-v1.5.quantized", "Lucene quantized HNSW index of the MS MARCO V1 passage corpus encoded by BGE-base-en-v1.5.", "lucene-hnsw-int8.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.tar.gz", + "", "MS MARCO V1 Passage", "bge-base-en-v1.5 w/ HNSW int8", new String[] { @@ -84,6 +91,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30("msmarco-v1-passage.cohere-embed-english-v3.0", "Lucene HNSW index of the MS MARCO V1 passage corpus encoded by Cohere embed-english-v3.0.", "lucene-hnsw.msmarco-v1-passage.cohere-embed-english-v3.0.20240228.eacd13.tar.gz", + "", "MS MARCO V1 Passage", "cohere-embed-english-v3.0 w/ HNSW fp32", new String[] { @@ -93,6 +101,7 @@ public enum IndexInfo { MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30_QUANTIZED("msmarco-v1-passage.cohere-embed-english-v3.0.quantized", "Lucene quantized HNSW index of the MS MARCO V1 passage corpus encoded by Cohere embed-english-v3.0.", "lucene-hnsw-int8.msmarco-v1-passage.cohere-embed-english-v3.0.20240228.eacd13.tar.gz", + "", "MS MARCO V1 Passage", "cohere-embed-english-v3.0 w/ HNSW fp32", new String[] { @@ -103,6 +112,7 @@ public enum IndexInfo { MSMARCO_V2_PASSAGE("msmarco-v2-passage", "Lucene index of the MS MARCO V2 passage corpus.", "lucene-index.msmarco-v2-passage.20220808.4d6d2a.tar.gz", + "", "MS MARCO V2 Passage", "BM25", new String[] { @@ -112,6 +122,7 @@ public enum IndexInfo { MSMARCO_V2_DOC("msmarco-v2-doc", "Lucene index of the MS MARCO V2 document corpus.", "lucene-index.msmarco-v2-doc.20220808.4d6d2a.tar.gz", + "", "MS MARCO V2 Doc", "BM25", new String[] { @@ -121,6 +132,7 @@ public enum IndexInfo { MSMARCO_V2_DOC_SEGMENTED("msmarco-v2-doc-segmented", "Lucene index of the MS MARCO V2 segmented document corpus.", "lucene-index.msmarco-v2-doc-segmented.20220808.4d6d2a.tar.gz", + "", "MS MARCO V2 Segmented Doc", "BM25", new String[] { @@ -130,6 +142,7 @@ public enum IndexInfo { MSMARCO_V21_DOC("msmarco-v2.1-doc", "Lucene index of the MS MARCO V2.1 document corpus.", "lucene-inverted.msmarco-v2.1-doc.20240418.4f9675.tar.gz", + "", "MS MARCO V2.1 Doc", "BM25", new String[] { @@ -139,6 +152,7 @@ public enum IndexInfo { MSMARCO_V21_DOC_SEGMENTED("msmarco-v2.1-doc-segmented", "Lucene index of the MS MARCO V2.1 segmented document corpus.", "lucene-inverted.msmarco-v2.1-doc-segmented.20240418.4f9675.tar.gz", + "", "MS MARCO V2.1 Segmented Doc", "BM25", new String[] { @@ -149,6 +163,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_COVID_FLAT("beir-v1.0.0-trec-covid.flat", "Lucene inverted 'flat' index of BEIR collection 'trec-covid'.", "lucene-inverted.beir-v1.0.0-trec-covid.flat.20221116.505594.tar.gz", + "", "BEIR: trec-covid", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-covid.flat.20221116.505594.tar.gz" }, @@ -157,6 +172,7 @@ public enum IndexInfo { BEIR_V1_0_0_BIOASQ_FLAT("beir-v1.0.0-bioasq.flat", "Lucene inverted 'flat' index of BEIR collection 'bioasq'.", "lucene-inverted.beir-v1.0.0-bioasq.flat.20221116.505594.tar.gz", + "", "BEIR: bioasq", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-bioasq.flat.20221116.505594.tar.gz" }, @@ -165,6 +181,7 @@ public enum IndexInfo { BEIR_V1_0_0_NFCORPUS_FLAT("beir-v1.0.0-nfcorpus.flat", "Lucene inverted 'flat' index of BEIR collection 'nfcorpus'.", "lucene-inverted.beir-v1.0.0-nfcorpus.flat.20221116.505594.tar.gz", + "", "BEIR: nfcorpus", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nfcorpus.flat.20221116.505594.tar.gz" }, @@ -173,6 +190,7 @@ public enum IndexInfo { BEIR_V1_0_0_NQ_FLAT("beir-v1.0.0-nq.flat", "Lucene inverted 'flat' index of BEIR collection 'nq'.", "lucene-inverted.beir-v1.0.0-nq.flat.20221116.505594.tar.gz", + "", "BEIR: nq", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nq.flat.20221116.505594.tar.gz" }, @@ -181,6 +199,7 @@ public enum IndexInfo { BEIR_V1_0_0_HOTPOTQA_FLAT("beir-v1.0.0-hotpotqa.flat", "Lucene inverted 'flat' index of BEIR collection 'hotpotqa'.", "lucene-inverted.beir-v1.0.0-hotpotqa.flat.20221116.505594.tar.gz", + "", "BEIR: hotpotqa", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-hotpotqa.flat.20221116.505594.tar.gz" }, @@ -189,6 +208,7 @@ public enum IndexInfo { BEIR_V1_0_0_FIQA_FLAT("beir-v1.0.0-fiqa.flat", "Lucene inverted 'flat' index of BEIR collection 'fiqa'.", "lucene-inverted.beir-v1.0.0-fiqa.flat.20221116.505594.tar.gz", + "", "BEIR: fiqa", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fiqa.flat.20221116.505594.tar.gz" }, @@ -197,6 +217,7 @@ public enum IndexInfo { BEIR_V1_0_0_SIGNAL1M_FLAT("beir-v1.0.0-signal1m.flat", "Lucene inverted 'flat' index of BEIR collection 'signal1m'.", "lucene-inverted.beir-v1.0.0-signal1m.flat.20221116.505594.tar.gz", + "", "BEIR: signal1m", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-signal1m.flat.20221116.505594.tar.gz" }, @@ -205,6 +226,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_NEWS_FLAT("beir-v1.0.0-trec-news.flat", "Lucene inverted 'flat' index of BEIR collection 'trec-news'.", "lucene-inverted.beir-v1.0.0-trec-news.flat.20221116.505594.tar.gz", + "", "BEIR: trec-news", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-news.flat.20221116.505594.tar.gz" }, @@ -213,6 +235,7 @@ public enum IndexInfo { BEIR_V1_0_0_ROBUST04_FLAT("beir-v1.0.0-robust04.flat", "Lucene inverted 'flat' index of BEIR collection 'robust04'.", "lucene-inverted.beir-v1.0.0-robust04.flat.20221116.505594.tar.gz", + "", "BEIR: robust04", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-robust04.flat.20221116.505594.tar.gz" }, @@ -221,6 +244,7 @@ public enum IndexInfo { BEIR_V1_0_0_ARGUANA_FLAT("beir-v1.0.0-arguana.flat", "Lucene inverted 'flat' index of BEIR collection 'arguana'.", "lucene-inverted.beir-v1.0.0-arguana.flat.20221116.505594.tar.gz", + "", "BEIR: arguana", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-arguana.flat.20221116.505594.tar.gz" }, @@ -229,6 +253,7 @@ public enum IndexInfo { BEIR_V1_0_0_WEBIS_TOUCHE2020_FLAT("beir-v1.0.0-webis-touche2020.flat", "Lucene inverted 'flat' index of BEIR collection 'webis-touche2020'.", "lucene-inverted.beir-v1.0.0-webis-touche2020.flat.20221116.505594.tar.gz", + "", "BEIR: webis-touche2020", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-webis-touche2020.flat.20221116.505594.tar.gz" }, @@ -237,6 +262,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ANDROID_FLAT("beir-v1.0.0-cqadupstack-android.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-android'.", "lucene-inverted.beir-v1.0.0-cqadupstack-android.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-android", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-android.flat.20221116.505594.tar.gz" }, @@ -245,6 +271,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ENGLISH_FLAT("beir-v1.0.0-cqadupstack-english.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-english'.", "lucene-inverted.beir-v1.0.0-cqadupstack-english.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-english", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-english.flat.20221116.505594.tar.gz" }, @@ -253,6 +280,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GAMING_FLAT("beir-v1.0.0-cqadupstack-gaming.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-gaming'.", "lucene-inverted.beir-v1.0.0-cqadupstack-gaming.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-gaming", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gaming.flat.20221116.505594.tar.gz" }, @@ -261,6 +289,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GIS_FLAT("beir-v1.0.0-cqadupstack-gis.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-gis'.", "lucene-inverted.beir-v1.0.0-cqadupstack-gis.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-gis", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gis.flat.20221116.505594.tar.gz" }, @@ -269,6 +298,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_MATHEMATICA_FLAT("beir-v1.0.0-cqadupstack-mathematica.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-mathematica'.", "lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-mathematica", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.flat.20221116.505594.tar.gz" }, @@ -277,6 +307,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PHYSICS_FLAT("beir-v1.0.0-cqadupstack-physics.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-physics'.", "lucene-inverted.beir-v1.0.0-cqadupstack-physics.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-physics", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-physics.flat.20221116.505594.tar.gz" }, @@ -285,6 +316,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PROGRAMMERS_FLAT("beir-v1.0.0-cqadupstack-programmers.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-programmers'.", "lucene-inverted.beir-v1.0.0-cqadupstack-programmers.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-programmers", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-programmers.flat.20221116.505594.tar.gz" }, @@ -293,6 +325,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_STATS_FLAT("beir-v1.0.0-cqadupstack-stats.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-stats'.", "lucene-inverted.beir-v1.0.0-cqadupstack-stats.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-stats", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-stats.flat.20221116.505594.tar.gz" }, @@ -301,6 +334,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_TEX_FLAT("beir-v1.0.0-cqadupstack-tex.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-tex'.", "lucene-inverted.beir-v1.0.0-cqadupstack-tex.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-tex", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-tex.flat.20221116.505594.tar.gz" }, @@ -309,6 +343,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_UNIX_FLAT("beir-v1.0.0-cqadupstack-unix.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-unix'.", "lucene-inverted.beir-v1.0.0-cqadupstack-unix.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-unix", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-unix.flat.20221116.505594.tar.gz" }, @@ -317,6 +352,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WEBMASTERS_FLAT("beir-v1.0.0-cqadupstack-webmasters.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-webmasters'.", "lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-webmasters", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.flat.20221116.505594.tar.gz" }, @@ -325,6 +361,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WORDPRESS_FLAT("beir-v1.0.0-cqadupstack-wordpress.flat", "Lucene inverted 'flat' index of BEIR collection 'cqadupstack-wordpress'.", "lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.flat.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-wordpress", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.flat.20221116.505594.tar.gz" }, @@ -333,6 +370,7 @@ public enum IndexInfo { BEIR_V1_0_0_QUORA_FLAT("beir-v1.0.0-quora.flat", "Lucene inverted 'flat' index of BEIR collection 'quora'.", "lucene-inverted.beir-v1.0.0-quora.flat.20221116.505594.tar.gz", + "", "BEIR: quora", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-quora.flat.20221116.505594.tar.gz" }, @@ -341,6 +379,7 @@ public enum IndexInfo { BEIR_V1_0_0_DBPEDIA_ENTITY_FLAT("beir-v1.0.0-dbpedia-entity.flat", "Lucene inverted 'flat' index of BEIR collection 'dbpedia-entity'.", "lucene-inverted.beir-v1.0.0-dbpedia-entity.flat.20221116.505594.tar.gz", + "", "BEIR: dbpedia-entity", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-dbpedia-entity.flat.20221116.505594.tar.gz" }, @@ -349,6 +388,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIDOCS_FLAT("beir-v1.0.0-scidocs.flat", "Lucene inverted 'flat' index of BEIR collection 'scidocs'.", "lucene-inverted.beir-v1.0.0-scidocs.flat.20221116.505594.tar.gz", + "", "BEIR: scidocs", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scidocs.flat.20221116.505594.tar.gz" }, @@ -357,6 +397,7 @@ public enum IndexInfo { BEIR_V1_0_0_FEVER_FLAT("beir-v1.0.0-fever.flat", "Lucene inverted 'flat' index of BEIR collection 'fever'.", "lucene-inverted.beir-v1.0.0-fever.flat.20221116.505594.tar.gz", + "", "BEIR: fever", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fever.flat.20221116.505594.tar.gz" }, @@ -365,6 +406,7 @@ public enum IndexInfo { BEIR_V1_0_0_CLIMATE_FEVER_FLAT("beir-v1.0.0-climate-fever.flat", "Lucene inverted 'flat' index of BEIR collection 'climate-fever'.", "lucene-inverted.beir-v1.0.0-climate-fever.flat.20221116.505594.tar.gz", + "", "BEIR: climate-fever", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-climate-fever.flat.20221116.505594.tar.gz" }, @@ -373,6 +415,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIFACT_FLAT("beir-v1.0.0-scifact.flat", "Lucene inverted 'flat' index of BEIR collection 'scifact'.", "lucene-inverted.beir-v1.0.0-scifact.flat.20221116.505594.tar.gz", + "", "BEIR: scifact", "BM25 'flat'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scifact.flat.20221116.505594.tar.gz" }, @@ -382,6 +425,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_COVID_MULTIFIELD("beir-v1.0.0-trec-covid.multifield", "Lucene inverted 'multifield' index of BEIR collection 'trec-covid'.", "lucene-inverted.beir-v1.0.0-trec-covid.multifield.20221116.505594.tar.gz", + "", "BEIR: trec-covid", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-covid.multifield.20221116.505594.tar.gz" }, @@ -390,6 +434,7 @@ public enum IndexInfo { BEIR_V1_0_0_BIOASQ_MULTIFIELD("beir-v1.0.0-bioasq.multifield", "Lucene inverted 'multifield' index of BEIR collection 'bioasq'.", "lucene-inverted.beir-v1.0.0-bioasq.multifield.20221116.505594.tar.gz", + "", "BEIR: bioasq", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-bioasq.multifield.20221116.505594.tar.gz" }, @@ -398,6 +443,7 @@ public enum IndexInfo { BEIR_V1_0_0_NFCORPUS_MULTIFIELD("beir-v1.0.0-nfcorpus.multifield", "Lucene inverted 'multifield' index of BEIR collection 'nfcorpus'.", "lucene-inverted.beir-v1.0.0-nfcorpus.multifield.20221116.505594.tar.gz", + "", "BEIR: nfcorpus", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nfcorpus.multifield.20221116.505594.tar.gz" }, @@ -406,6 +452,7 @@ public enum IndexInfo { BEIR_V1_0_0_NQ_MULTIFIELD("beir-v1.0.0-nq.multifield", "Lucene inverted 'multifield' index of BEIR collection 'nq'.", "lucene-inverted.beir-v1.0.0-nq.multifield.20221116.505594.tar.gz", + "", "BEIR: nq", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nq.multifield.20221116.505594.tar.gz" }, @@ -414,6 +461,7 @@ public enum IndexInfo { BEIR_V1_0_0_HOTPOTQA_MULTIFIELD("beir-v1.0.0-hotpotqa.multifield", "Lucene inverted 'multifield' index of BEIR collection 'hotpotqa'.", "lucene-inverted.beir-v1.0.0-hotpotqa.multifield.20221116.505594.tar.gz", + "", "BEIR: hotpotqa", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-hotpotqa.multifield.20221116.505594.tar.gz" }, @@ -422,6 +470,7 @@ public enum IndexInfo { BEIR_V1_0_0_FIQA_MULTIFIELD("beir-v1.0.0-fiqa.multifield", "Lucene inverted 'multifield' index of BEIR collection 'fiqa'.", "lucene-inverted.beir-v1.0.0-fiqa.multifield.20221116.505594.tar.gz", + "", "BEIR: fiqa", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fiqa.multifield.20221116.505594.tar.gz" }, @@ -430,6 +479,7 @@ public enum IndexInfo { BEIR_V1_0_0_SIGNAL1M_MULTIFIELD("beir-v1.0.0-signal1m.multifield", "Lucene inverted 'multifield' index of BEIR collection 'signal1m'.", "lucene-inverted.beir-v1.0.0-signal1m.multifield.20221116.505594.tar.gz", + "", "BEIR: signal1m", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-signal1m.multifield.20221116.505594.tar.gz" }, @@ -438,6 +488,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_NEWS_MULTIFIELD("beir-v1.0.0-trec-news.multifield", "Lucene inverted 'multifield' index of BEIR collection 'trec-news'.", "lucene-inverted.beir-v1.0.0-trec-news.multifield.20221116.505594.tar.gz", + "", "BEIR: trec-news", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-news.multifield.20221116.505594.tar.gz" }, @@ -446,6 +497,7 @@ public enum IndexInfo { BEIR_V1_0_0_ROBUST04_MULTIFIELD("beir-v1.0.0-robust04.multifield", "Lucene inverted 'multifield' index of BEIR collection 'robust04'.", "lucene-inverted.beir-v1.0.0-robust04.multifield.20221116.505594.tar.gz", + "", "BEIR: robust04", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-robust04.multifield.20221116.505594.tar.gz" }, @@ -454,6 +506,7 @@ public enum IndexInfo { BEIR_V1_0_0_ARGUANA_MULTIFIELD("beir-v1.0.0-arguana.multifield", "Lucene inverted 'multifield' index of BEIR collection 'arguana'.", "lucene-inverted.beir-v1.0.0-arguana.multifield.20221116.505594.tar.gz", + "", "BEIR: arguana", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-arguana.multifield.20221116.505594.tar.gz" }, @@ -462,6 +515,7 @@ public enum IndexInfo { BEIR_V1_0_0_WEBIS_TOUCHE2020_MULTIFIELD("beir-v1.0.0-webis-touche2020.multifield", "Lucene inverted 'multifield' index of BEIR collection 'webis-touche2020'.", "lucene-inverted.beir-v1.0.0-webis-touche2020.multifield.20221116.505594.tar.gz", + "", "BEIR: webis-touche2020", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-webis-touche2020.multifield.20221116.505594.tar.gz" }, @@ -470,6 +524,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ANDROID_MULTIFIELD("beir-v1.0.0-cqadupstack-android.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-android'.", "lucene-inverted.beir-v1.0.0-cqadupstack-android.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-android", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-android.multifield.20221116.505594.tar.gz" }, @@ -478,6 +533,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ENGLISH_MULTIFIELD("beir-v1.0.0-cqadupstack-english.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-english'.", "lucene-inverted.beir-v1.0.0-cqadupstack-english.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-english", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-english.multifield.20221116.505594.tar.gz" }, @@ -486,6 +542,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GAMING_MULTIFIELD("beir-v1.0.0-cqadupstack-gaming.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-gaming'.", "lucene-inverted.beir-v1.0.0-cqadupstack-gaming.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-gaming", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gaming.multifield.20221116.505594.tar.gz" }, @@ -494,6 +551,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GIS_MULTIFIELD("beir-v1.0.0-cqadupstack-gis.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-gis'.", "lucene-inverted.beir-v1.0.0-cqadupstack-gis.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-gis", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gis.multifield.20221116.505594.tar.gz" }, @@ -502,6 +560,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_MATHEMATICA_MULTIFIELD("beir-v1.0.0-cqadupstack-mathematica.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-mathematica'.", "lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-mathematica", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.multifield.20221116.505594.tar.gz" }, @@ -510,6 +569,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PHYSICS_MULTIFIELD("beir-v1.0.0-cqadupstack-physics.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-physics'.", "lucene-inverted.beir-v1.0.0-cqadupstack-physics.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-physics", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-physics.multifield.20221116.505594.tar.gz" }, @@ -518,6 +578,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PROGRAMMERS_MULTIFIELD("beir-v1.0.0-cqadupstack-programmers.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-programmers'.", "lucene-inverted.beir-v1.0.0-cqadupstack-programmers.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-programmers", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-programmers.multifield.20221116.505594.tar.gz" }, @@ -526,6 +587,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_STATS_MULTIFIELD("beir-v1.0.0-cqadupstack-stats.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-stats'.", "lucene-inverted.beir-v1.0.0-cqadupstack-stats.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-stats", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-stats.multifield.20221116.505594.tar.gz" }, @@ -534,6 +596,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_TEX_MULTIFIELD("beir-v1.0.0-cqadupstack-tex.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-tex'.", "lucene-inverted.beir-v1.0.0-cqadupstack-tex.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-tex", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-tex.multifield.20221116.505594.tar.gz" }, @@ -542,6 +605,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_UNIX_MULTIFIELD("beir-v1.0.0-cqadupstack-unix.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-unix'.", "lucene-inverted.beir-v1.0.0-cqadupstack-unix.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-unix", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-unix.multifield.20221116.505594.tar.gz" }, @@ -550,6 +614,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WEBMASTERS_MULTIFIELD("beir-v1.0.0-cqadupstack-webmasters.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-webmasters'.", "lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-webmasters", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.multifield.20221116.505594.tar.gz" }, @@ -558,6 +623,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WORDPRESS_MULTIFIELD("beir-v1.0.0-cqadupstack-wordpress.multifield", "Lucene inverted 'multifield' index of BEIR collection 'cqadupstack-wordpress'.", "lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.multifield.20221116.505594.tar.gz", + "", "BEIR: cqadupstack-wordpress", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.multifield.20221116.505594.tar.gz" }, @@ -566,6 +632,7 @@ public enum IndexInfo { BEIR_V1_0_0_QUORA_MULTIFIELD("beir-v1.0.0-quora.multifield", "Lucene inverted 'multifield' index of BEIR collection 'quora'.", "lucene-inverted.beir-v1.0.0-quora.multifield.20221116.505594.tar.gz", + "", "BEIR: quora", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-quora.multifield.20221116.505594.tar.gz" }, @@ -574,6 +641,7 @@ public enum IndexInfo { BEIR_V1_0_0_DBPEDIA_ENTITY_MULTIFIELD("beir-v1.0.0-dbpedia-entity.multifield", "Lucene inverted 'multifield' index of BEIR collection 'dbpedia-entity'.", "lucene-inverted.beir-v1.0.0-dbpedia-entity.multifield.20221116.505594.tar.gz", + "", "BEIR: dbpedia-entity", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-dbpedia-entity.multifield.20221116.505594.tar.gz" }, @@ -582,6 +650,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIDOCS_MULTIFIELD("beir-v1.0.0-scidocs.multifield", "Lucene inverted 'multifield' index of BEIR collection 'scidocs'.", "lucene-inverted.beir-v1.0.0-scidocs.multifield.20221116.505594.tar.gz", + "", "BEIR: scidocs", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scidocs.multifield.20221116.505594.tar.gz" }, @@ -590,6 +659,7 @@ public enum IndexInfo { BEIR_V1_0_0_FEVER_MULTIFIELD("beir-v1.0.0-fever.multifield", "Lucene inverted 'multifield' index of BEIR collection 'fever'.", "lucene-inverted.beir-v1.0.0-fever.multifield.20221116.505594.tar.gz", + "", "BEIR: fever", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fever.multifield.20221116.505594.tar.gz" }, @@ -598,6 +668,7 @@ public enum IndexInfo { BEIR_V1_0_0_CLIMATE_FEVER_MULTIFIELD("beir-v1.0.0-climate-fever.multifield", "Lucene inverted 'multifield' index of BEIR collection 'climate-fever'.", "lucene-inverted.beir-v1.0.0-climate-fever.multifield.20221116.505594.tar.gz", + "", "BEIR: climate-fever", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-climate-fever.multifield.20221116.505594.tar.gz" }, @@ -606,6 +677,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIFACT_MULTIFIELD("beir-v1.0.0-scifact.multifield", "Lucene inverted 'multifield' index of BEIR collection 'scifact'.", "lucene-inverted.beir-v1.0.0-scifact.multifield.20221116.505594.tar.gz", + "", "BEIR: scifact", "BM25 'multifield'", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scifact.multifield.20221116.505594.tar.gz" }, @@ -615,6 +687,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_COVID_SPLADE_PP_ED("beir-v1.0.0-trec-covid.splade-pp-ed", "Lucene impact index of BEIR collection 'trec-covid' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-trec-covid.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: trec-covid", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-covid.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -623,6 +696,7 @@ public enum IndexInfo { BEIR_V1_0_0_BIOASQ_SPLADE_PP_ED("beir-v1.0.0-bioasq.splade-pp-ed", "Lucene impact index of BEIR collection 'bioasq' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-bioasq.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: bioasq", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-bioasq.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -631,6 +705,7 @@ public enum IndexInfo { BEIR_V1_0_0_NFCORPUS_SPLADE_PP_ED("beir-v1.0.0-nfcorpus.splade-pp-ed", "Lucene impact index of BEIR collection 'nfcorpus' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-nfcorpus.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: nfcorpus", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nfcorpus.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -639,6 +714,7 @@ public enum IndexInfo { BEIR_V1_0_0_NQ_SPLADE_PP_ED("beir-v1.0.0-nq.splade-pp-ed", "Lucene impact index of BEIR collection 'nq' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-nq.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: nq", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-nq.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -647,6 +723,7 @@ public enum IndexInfo { BEIR_V1_0_0_HOTPOTQA_SPLADE_PP_ED("beir-v1.0.0-hotpotqa.splade-pp-ed", "Lucene impact index of BEIR collection 'hotpotqa' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-hotpotqa.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: hotpotqa", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-hotpotqa.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -655,6 +732,7 @@ public enum IndexInfo { BEIR_V1_0_0_FIQA_SPLADE_PP_ED("beir-v1.0.0-fiqa.splade-pp-ed", "Lucene impact index of BEIR collection 'fiqa' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-fiqa.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: fiqa", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fiqa.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -663,6 +741,7 @@ public enum IndexInfo { BEIR_V1_0_0_SIGNAL1M_SPLADE_PP_ED("beir-v1.0.0-signal1m.splade-pp-ed", "Lucene impact index of BEIR collection 'signal1m' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-signal1m.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: signal1m", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-signal1m.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -671,6 +750,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_NEWS_SPLADE_PP_ED("beir-v1.0.0-trec-news.splade-pp-ed", "Lucene impact index of BEIR collection 'trec-news' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-trec-news.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: trec-news", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-trec-news.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -679,6 +759,7 @@ public enum IndexInfo { BEIR_V1_0_0_ROBUST04_SPLADE_PP_ED("beir-v1.0.0-robust04.splade-pp-ed", "Lucene impact index of BEIR collection 'robust04' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-robust04.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: robust04", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-robust04.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -687,6 +768,7 @@ public enum IndexInfo { BEIR_V1_0_0_ARGUANA_SPLADE_PP_ED("beir-v1.0.0-arguana.splade-pp-ed", "Lucene impact index of BEIR collection 'arguana' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-arguana.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: arguana", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-arguana.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -695,6 +777,7 @@ public enum IndexInfo { BEIR_V1_0_0_WEBIS_TOUCHE2020_SPLADE_PP_ED("beir-v1.0.0-webis-touche2020.splade-pp-ed", "Lucene impact index of BEIR collection 'webis-touche2020' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-webis-touche2020.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: webis-touche2020", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-webis-touche2020.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -703,6 +786,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ANDROID_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-android.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-android' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-android.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-android", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-android.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -711,6 +795,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ENGLISH_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-english.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-english' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-english.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-english", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-english.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -719,6 +804,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GAMING_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-gaming.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-gaming' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-gaming.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-gaming", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gaming.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -727,6 +813,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GIS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-gis.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-gis' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-gis.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-gis", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-gis.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -735,6 +822,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_MATHEMATICA_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-mathematica.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-mathematica' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-mathematica", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-mathematica.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -743,6 +831,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PHYSICS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-physics.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-physics' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-physics.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-physics", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-physics.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -751,6 +840,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PROGRAMMERS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-programmers.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-programmers' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-programmers.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-programmers", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-programmers.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -759,6 +849,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_STATS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-stats.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-stats' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-stats.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-stats", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-stats.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -767,6 +858,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_TEX_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-tex.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-tex' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-tex.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-tex", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-tex.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -775,6 +867,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_UNIX_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-unix.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-unix' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-unix.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-unix", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-unix.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -783,6 +876,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WEBMASTERS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-webmasters.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-webmasters' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-webmasters", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-webmasters.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -791,6 +885,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WORDPRESS_SPLADE_PP_ED("beir-v1.0.0-cqadupstack-wordpress.splade-pp-ed", "Lucene impact index of BEIR collection 'cqadupstack-wordpress' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: cqadupstack-wordpress", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-cqadupstack-wordpress.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -799,6 +894,7 @@ public enum IndexInfo { BEIR_V1_0_0_QUORA_SPLADE_PP_ED("beir-v1.0.0-quora.splade-pp-ed", "Lucene impact index of BEIR collection 'quora' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-quora.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: quora", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-quora.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -807,6 +903,7 @@ public enum IndexInfo { BEIR_V1_0_0_DBPEDIA_ENTITY_SPLADE_PP_ED("beir-v1.0.0-dbpedia-entity.splade-pp-ed", "Lucene impact index of BEIR collection 'dbpedia-entity' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-dbpedia-entity.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: dbpedia-entity", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-dbpedia-entity.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -815,6 +912,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIDOCS_SPLADE_PP_ED("beir-v1.0.0-scidocs.splade-pp-ed", "Lucene impact index of BEIR collection 'scidocs' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-scidocs.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: scidocs", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scidocs.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -823,6 +921,7 @@ public enum IndexInfo { BEIR_V1_0_0_FEVER_SPLADE_PP_ED("beir-v1.0.0-fever.splade-pp-ed", "Lucene impact index of BEIR collection 'fever' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-fever.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: fever", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-fever.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -831,6 +930,7 @@ public enum IndexInfo { BEIR_V1_0_0_CLIMATE_FEVER_SPLADE_PP_ED("beir-v1.0.0-climate-fever.splade-pp-ed", "Lucene impact index of BEIR collection 'climate-fever' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-climate-fever.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: climate-fever", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-climate-fever.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -839,6 +939,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIFACT_SPLADE_PP_ED("beir-v1.0.0-scifact.splade-pp-ed", "Lucene impact index of BEIR collection 'scifact' encoded by SPLADE++ EnsembleDistil", "lucene-inverted.beir-v1.0.0-scifact.splade-pp-ed.20231124.a66f86f.tar.gz", + "", "BEIR: scifact", "SPLADE++ EnsembleDistil", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.beir-v1.0.0-scifact.splade-pp-ed.20231124.a66f86f.tar.gz" }, @@ -848,6 +949,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_COVID_BGE_BASE_EN_15_HNSW("beir-v1.0.0-trec-covid.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'trec-covid' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-trec-covid.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: trec-covid", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-trec-covid.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -856,6 +958,7 @@ public enum IndexInfo { BEIR_V1_0_0_BIOASQ_BGE_BASE_EN_15_HNSW("beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'bioasq' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-bioasq.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: bioasq", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-bioasq.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -864,6 +967,7 @@ public enum IndexInfo { BEIR_V1_0_0_NFCORPUS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-nfcorpus.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'nfcorpus' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-nfcorpus.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: nfcorpus", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-nfcorpus.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -872,6 +976,7 @@ public enum IndexInfo { BEIR_V1_0_0_NQ_BGE_BASE_EN_15_HNSW("beir-v1.0.0-nq.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'nq' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-nq.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: nq", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-nq.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -880,6 +985,7 @@ public enum IndexInfo { BEIR_V1_0_0_HOTPOTQA_BGE_BASE_EN_15_HNSW("beir-v1.0.0-hotpotqa.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'hotpotqa' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-hotpotqa.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: hotpotqa", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-hotpotqa.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -888,6 +994,7 @@ public enum IndexInfo { BEIR_V1_0_0_FIQA_BGE_BASE_EN_15_HNSW("beir-v1.0.0-fiqa.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'fiqa' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-fiqa.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: fiqa", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-fiqa.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -896,6 +1003,7 @@ public enum IndexInfo { BEIR_V1_0_0_SIGNAL1M_BGE_BASE_EN_15_HNSW("beir-v1.0.0-signal1m.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'signal1m' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-signal1m.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: signal1m", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-signal1m.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -904,6 +1012,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_NEWS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-trec-news.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'trec-news' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-trec-news.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: trec-news", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-trec-news.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -912,6 +1021,7 @@ public enum IndexInfo { BEIR_V1_0_0_ROBUST04_BGE_BASE_EN_15_HNSW("beir-v1.0.0-robust04.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'robust04' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-robust04.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: robust04", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-robust04.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -920,6 +1030,7 @@ public enum IndexInfo { BEIR_V1_0_0_ARGUANA_BGE_BASE_EN_15_HNSW("beir-v1.0.0-arguana.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'arguana' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-arguana.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: arguana", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-arguana.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -928,6 +1039,7 @@ public enum IndexInfo { BEIR_V1_0_0_WEBIS_TOUCHE2020_BGE_BASE_EN_15_HNSW("beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'webis-touche2020' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: webis-touche2020", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -936,6 +1048,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ANDROID_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-android' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-android", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -944,6 +1057,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ENGLISH_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-english' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-english", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -952,6 +1066,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GAMING_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-gaming' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-gaming", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -960,6 +1075,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GIS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-gis' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-gis", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -968,6 +1084,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_MATHEMATICA_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-mathematica' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-mathematica", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -976,6 +1093,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PHYSICS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-physics' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-physics", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -984,6 +1102,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PROGRAMMERS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-programmers' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-programmers", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -992,6 +1111,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_STATS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-stats' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-stats", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1000,6 +1120,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_TEX_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-tex' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-tex", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1008,6 +1129,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_UNIX_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-unix' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-unix", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1016,6 +1138,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WEBMASTERS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-webmasters' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-webmasters", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1024,6 +1147,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WORDPRESS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'cqadupstack-wordpress' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: cqadupstack-wordpress", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1032,6 +1156,7 @@ public enum IndexInfo { BEIR_V1_0_0_QUORA_BGE_BASE_EN_15_HNSW("beir-v1.0.0-quora.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'quora' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-quora.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: quora", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-quora.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1040,6 +1165,7 @@ public enum IndexInfo { BEIR_V1_0_0_DBPEDIA_ENTITY_BGE_BASE_EN_15_HNSW("beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'dbpedia-entity' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: dbpedia-entity", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1048,6 +1174,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIDOCS_BGE_BASE_EN_15_HNSW("beir-v1.0.0-scidocs.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'scidocs' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-scidocs.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: scidocs", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-scidocs.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1056,6 +1183,7 @@ public enum IndexInfo { BEIR_V1_0_0_FEVER_BGE_BASE_EN_15_HNSW("beir-v1.0.0-fever.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'fever' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-fever.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: fever", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-fever.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1064,6 +1192,7 @@ public enum IndexInfo { BEIR_V1_0_0_CLIMATE_FEVER_BGE_BASE_EN_15_HNSW("beir-v1.0.0-climate-fever.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'climate-fever' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-climate-fever.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: climate-fever", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-climate-fever.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1072,6 +1201,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIFACT_BGE_BASE_EN_15_HNSW("beir-v1.0.0-scifact.bge-base-en-v1.5.hnsw", "Lucene HNSW index of BEIR collection 'scifact' encoded by BGE-base-en-v1.5.", "lucene-hnsw.beir-v1.0.0-scifact.bge-base-en-v1.5.20240223.43c9ec.tar.gz", + "lucene-hnsw.beir-v1.0.0.bge-base-en-v1.5.20240223.43c9ec.README.md", "BEIR: scifact", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.beir-v1.0.0-scifact.bge-base-en-v1.5.20240223.43c9ec.tar.gz" }, @@ -1081,6 +1211,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_COVID_BGE_BASE_EN_15_FLAT("beir-v1.0.0-trec-covid.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'trec-covid' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-trec-covid.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: trec-covid", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-trec-covid.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1089,6 +1220,7 @@ public enum IndexInfo { BEIR_V1_0_0_BIOASQ_BGE_BASE_EN_15_FLAT("beir-v1.0.0-bioasq.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'bioasq' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-bioasq.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: bioasq", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-bioasq.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1097,6 +1229,7 @@ public enum IndexInfo { BEIR_V1_0_0_NFCORPUS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-nfcorpus.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'nfcorpus' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-nfcorpus.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: nfcorpus", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-nfcorpus.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1105,6 +1238,7 @@ public enum IndexInfo { BEIR_V1_0_0_NQ_BGE_BASE_EN_15_FLAT("beir-v1.0.0-nq.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'nq' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-nq.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: nq", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-nq.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1113,6 +1247,7 @@ public enum IndexInfo { BEIR_V1_0_0_HOTPOTQA_BGE_BASE_EN_15_FLAT("beir-v1.0.0-hotpotqa.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'hotpotqa' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-hotpotqa.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: hotpotqa", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-hotpotqa.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1121,6 +1256,7 @@ public enum IndexInfo { BEIR_V1_0_0_FIQA_BGE_BASE_EN_15_FLAT("beir-v1.0.0-fiqa.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'fiqa' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-fiqa.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: fiqa", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-fiqa.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1129,6 +1265,7 @@ public enum IndexInfo { BEIR_V1_0_0_SIGNAL1M_BGE_BASE_EN_15_FLAT("beir-v1.0.0-signal1m.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'signal1m' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-signal1m.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: signal1m", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-signal1m.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1137,6 +1274,7 @@ public enum IndexInfo { BEIR_V1_0_0_TREC_NEWS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-trec-news.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'trec-news' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-trec-news.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: trec-news", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-trec-news.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1145,6 +1283,7 @@ public enum IndexInfo { BEIR_V1_0_0_ROBUST04_BGE_BASE_EN_15_FLAT("beir-v1.0.0-robust04.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'robust04' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-robust04.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: robust04", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-robust04.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1153,6 +1292,7 @@ public enum IndexInfo { BEIR_V1_0_0_ARGUANA_BGE_BASE_EN_15_FLAT("beir-v1.0.0-arguana.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'arguana' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-arguana.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: arguana", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-arguana.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1161,6 +1301,7 @@ public enum IndexInfo { BEIR_V1_0_0_WEBIS_TOUCHE2020_BGE_BASE_EN_15_FLAT("beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'webis-touche2020' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: webis-touche2020", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-webis-touche2020.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1169,6 +1310,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ANDROID_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-android' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-android", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-android.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1177,6 +1319,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_ENGLISH_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-english' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-english", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-english.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1185,6 +1328,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GAMING_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-gaming' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-gaming", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-gaming.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1193,6 +1337,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_GIS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-gis' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-gis", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-gis.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1201,6 +1346,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_MATHEMATICA_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-mathematica' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-mathematica", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-mathematica.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1209,6 +1355,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PHYSICS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-physics' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-physics", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-physics.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1217,6 +1364,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_PROGRAMMERS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-programmers' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-programmers", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-programmers.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1225,6 +1373,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_STATS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-stats' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-stats", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-stats.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1233,6 +1382,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_TEX_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-tex' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-tex", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-tex.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1241,6 +1391,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_UNIX_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-unix' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-unix", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-unix.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1249,6 +1400,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WEBMASTERS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-webmasters' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-webmasters", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-webmasters.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1257,6 +1409,7 @@ public enum IndexInfo { BEIR_V1_0_0_CQADUPSTACK_WORDPRESS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'cqadupstack-wordpress' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: cqadupstack-wordpress", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-cqadupstack-wordpress.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1265,6 +1418,7 @@ public enum IndexInfo { BEIR_V1_0_0_QUORA_BGE_BASE_EN_15_FLAT("beir-v1.0.0-quora.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'quora' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-quora.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: quora", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-quora.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1273,6 +1427,7 @@ public enum IndexInfo { BEIR_V1_0_0_DBPEDIA_ENTITY_BGE_BASE_EN_15_FLAT("beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'dbpedia-entity' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: dbpedia-entity", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-dbpedia-entity.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1281,6 +1436,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIDOCS_BGE_BASE_EN_15_FLAT("beir-v1.0.0-scidocs.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'scidocs' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-scidocs.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: scidocs", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-scidocs.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1289,6 +1445,7 @@ public enum IndexInfo { BEIR_V1_0_0_FEVER_BGE_BASE_EN_15_FLAT("beir-v1.0.0-fever.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'fever' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-fever.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: fever", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-fever.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1297,6 +1454,7 @@ public enum IndexInfo { BEIR_V1_0_0_CLIMATE_FEVER_BGE_BASE_EN_15_FLAT("beir-v1.0.0-climate-fever.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'climate-fever' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-climate-fever.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: climate-fever", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-climate-fever.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1305,6 +1463,7 @@ public enum IndexInfo { BEIR_V1_0_0_SCIFACT_BGE_BASE_EN_15_FLAT("beir-v1.0.0-scifact.bge-base-en-v1.5.flat", "Lucene flat index of BEIR collection 'scifact' encoded by BGE-base-en-v1.5.", "lucene-flat.beir-v1.0.0-scifact.bge-base-en-v1.5.20240618.6cf601.tar.gz", + "lucene-flat.beir-v1.0.0.bge-base-en-v1.5.20240618.6cf601.README.md", "BEIR: scifact", "bge-base-en-v1.5", new String[] { "https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-flat.beir-v1.0.0-scifact.bge-base-en-v1.5.20240618.6cf601.tar.gz" }, @@ -1313,15 +1472,18 @@ public enum IndexInfo { public final String indexName; public final String description; public final String filename; + public final String readme; public final String corpus; public final String model; public final String[] urls; public final String md5; - IndexInfo(String indexName, String description, String filename, String corpus, String model, String[] urls, String md5) { + IndexInfo(String indexName, String description, String filename, String readme, String corpus, String model, + String[] urls, String md5) { this.indexName = indexName; this.description = description; this.filename = filename; + this.readme = readme; this.corpus = corpus; this.model = model; this.urls = urls; diff --git a/src/main/java/io/anserini/search/BaseSearchArgs.java b/src/main/java/io/anserini/search/BaseSearchArgs.java index ec888ebc9a..176d83c3d8 100644 --- a/src/main/java/io/anserini/search/BaseSearchArgs.java +++ b/src/main/java/io/anserini/search/BaseSearchArgs.java @@ -21,7 +21,7 @@ /** * This is the base class that holds common arguments for configuring searchers. Note that, explicitly, there are no * arguments that are specific to the retrieval implementation (e.g., for HNSW searchers), and that there are no - * arguments that define queries and outputs (which are to be defined by sub-classes that may call the searcher in + * arguments that define queries and outputs (which are to be defined by subclasses that may call the searcher in * different ways). */ public class BaseSearchArgs { diff --git a/src/main/java/io/anserini/search/FlatDenseSearcher.java b/src/main/java/io/anserini/search/FlatDenseSearcher.java index b9d2b923e4..634dc595be 100644 --- a/src/main/java/io/anserini/search/FlatDenseSearcher.java +++ b/src/main/java/io/anserini/search/FlatDenseSearcher.java @@ -129,78 +129,122 @@ public FlatDenseSearcher(Args args) { } } - public SortedMap batch_search(List qids, List queries, int hits) { + /** + * Searches the collection in batch using multiple threads. + * + * @param queries list of queries + * @param qids list of unique query ids + * @param k number of hits + * @param threads number of threads + * @return a map of query id to search results + */ + public SortedMap batch_search(List queries, List qids, int k, int threads) { final SortedMap results = new ConcurrentSkipListMap<>(); - final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(args.threads); final AtomicInteger cnt = new AtomicInteger(); - final long start = System.nanoTime(); - assert qids.size() == queries.size(); - for (int i=0; i { - try { - results.put(qid, search(qid, queryString, hits)); - } catch (IOException e) { - throw new CompletionException(e); - } - - int n = cnt.incrementAndGet(); - if (n % 100 == 0) { - LOG.info(String.format("%d queries processed", n)); - } - }); - } - executor.shutdown(); + try(ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(threads)) { + assert qids.size() == queries.size(); + for (int i = 0; i < qids.size(); i++) { + K qid = qids.get(i); + String queryString = queries.get(i); - try { - // Wait for existing tasks to terminate. - while (!executor.awaitTermination(1, TimeUnit.MINUTES)); - } catch (InterruptedException ie) { - // (Re-)Cancel if current thread also interrupted. - executor.shutdownNow(); - // Preserve interrupt status. - Thread.currentThread().interrupt(); + // This is the per-query execution, in parallel. + executor.execute(() -> { + try { + results.put(qid, search(qid, queryString, k)); + } catch (IOException e) { + throw new CompletionException(e); + } + + int n = cnt.incrementAndGet(); + if (n % 100 == 0) { + LOG.info(String.format("%d queries processed", n)); + } + }); + } + + executor.shutdown(); + + try { + // Wait for existing tasks to terminate. + while (!executor.awaitTermination(1, TimeUnit.MINUTES)); + } catch (InterruptedException ie) { + // (Re-)Cancel if current thread also interrupted. + executor.shutdownNow(); + // Preserve interrupt status. + Thread.currentThread().interrupt(); + } } final long durationMillis = TimeUnit.MILLISECONDS.convert(System.nanoTime() - start, TimeUnit.NANOSECONDS); - LOG.info(queries.size() + " queries processed in " + - DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss") + + LOG.info("{} queries processed in {}{}", queries.size(), + DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss"), String.format(" = ~%.2f q/s", queries.size() / (durationMillis / 1000.0))); return results; } - public ScoredDoc[] search(float[] queryFloat, int hits) throws IOException { - return search(null, queryFloat, hits); + /** + * Searches the collection with a query vector. + * + * @param query query vector + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(float[] query, int k) throws IOException { + return search(null, query, k); } - public ScoredDoc[] search(@Nullable K qid, float[] queryFloat, int hits) throws IOException { - KnnFloatVectorQuery query = new KnnFloatVectorQuery(Constants.VECTOR, queryFloat, DUMMY_EF_SEARCH); - TopDocs topDocs = getIndexSearcher().search(query, hits, BREAK_SCORE_TIES_BY_DOCID, true); + /** + * Searches the collection with a query vector. + * + * @param qid query id + * @param query query vector + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(@Nullable K qid, float[] query, int k) throws IOException { + KnnFloatVectorQuery vectorQuery = new KnnFloatVectorQuery(Constants.VECTOR, query, DUMMY_EF_SEARCH); + TopDocs topDocs = getIndexSearcher().search(vectorQuery, k, BREAK_SCORE_TIES_BY_DOCID, true); return super.processLuceneTopDocs(qid, topDocs); } - public ScoredDoc[] search(String queryString, int hits) throws IOException { - return search(null, queryString, hits); + /** + * Searches the collection with a string query that will be encoded by the underlying encoder. + * + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(String query, int k) throws IOException { + return search(null, query, k); } - public ScoredDoc[] search(@Nullable K qid, String queryString, int hits) throws IOException { + /** + * Searches the collection with a string query that will be encoded by the underlying encoder. + * + * @param qid query id + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(@Nullable K qid, String query, int k) throws IOException { if (encoder != null) { try { - return search(qid, encoder.encode(queryString), hits); + return search(qid, encoder.encode(query), k); } catch (OrtException e) { throw new RuntimeException("Error encoding query."); } } - KnnFloatVectorQuery query = generator.buildQuery(Constants.VECTOR, queryString, DUMMY_EF_SEARCH); - TopDocs topDocs = getIndexSearcher().search(query, hits, BREAK_SCORE_TIES_BY_DOCID, true); + KnnFloatVectorQuery vectorQuery = generator.buildQuery(Constants.VECTOR, query, DUMMY_EF_SEARCH); + TopDocs topDocs = getIndexSearcher().search(vectorQuery, k, BREAK_SCORE_TIES_BY_DOCID, true); return super.processLuceneTopDocs(qid, topDocs); } diff --git a/src/main/java/io/anserini/search/HnswDenseSearcher.java b/src/main/java/io/anserini/search/HnswDenseSearcher.java index 822a8724a4..a64b1a4e83 100644 --- a/src/main/java/io/anserini/search/HnswDenseSearcher.java +++ b/src/main/java/io/anserini/search/HnswDenseSearcher.java @@ -130,78 +130,122 @@ public HnswDenseSearcher(Args args) { } } - public SortedMap batch_search(List qids, List queries, int hits) { + /** + * Searches the collection in batch using multiple threads. + * + * @param queries list of queries + * @param qids list of unique query ids + * @param k number of hits + * @param threads number of threads + * @return a map of query id to search results + */ + public SortedMap batch_search(List queries, List qids, int k, int threads) { final SortedMap results = new ConcurrentSkipListMap<>(); - final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(args.threads); final AtomicInteger cnt = new AtomicInteger(); - final long start = System.nanoTime(); - assert qids.size() == queries.size(); - for (int i=0; i { - try { - results.put(qid, search(qid, queryString, hits)); - } catch (IOException e) { - throw new CompletionException(e); - } - - int n = cnt.incrementAndGet(); - if (n % 100 == 0) { - LOG.info(String.format("%d queries processed", n)); - } - }); - } - executor.shutdown(); + try(ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(threads)) { + assert qids.size() == queries.size(); + for (int i = 0; i < qids.size(); i++) { + K qid = qids.get(i); + String queryString = queries.get(i); + + // This is the per-query execution, in parallel. + executor.execute(() -> { + try { + results.put(qid, search(qid, queryString, k)); + } catch (IOException e) { + throw new CompletionException(e); + } + + int n = cnt.incrementAndGet(); + if (n % 100 == 0) { + LOG.info("{} queries processed", n); + } + }); + } - try { - // Wait for existing tasks to terminate. - while (!executor.awaitTermination(1, TimeUnit.MINUTES)); - } catch (InterruptedException ie) { - // (Re-)Cancel if current thread also interrupted. - executor.shutdownNow(); - // Preserve interrupt status. - Thread.currentThread().interrupt(); + executor.shutdown(); + + try { + // Wait for existing tasks to terminate. + while (!executor.awaitTermination(1, TimeUnit.MINUTES)); + } catch (InterruptedException ie) { + // (Re-)Cancel if current thread also interrupted. + executor.shutdownNow(); + // Preserve interrupt status. + Thread.currentThread().interrupt(); + } } final long durationMillis = TimeUnit.MILLISECONDS.convert(System.nanoTime() - start, TimeUnit.NANOSECONDS); - LOG.info(queries.size() + " queries processed in " + - DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss") + + LOG.info("{} queries processed in {}{}", queries.size(), + DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss"), String.format(" = ~%.2f q/s", queries.size() / (durationMillis / 1000.0))); return results; } - public ScoredDoc[] search(float[] queryFloat, int hits) throws IOException { - return search(null, queryFloat, hits); + /** + * Searches the collection with a query vector. + * + * @param query query vector + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(float[] query, int k) throws IOException { + return search(null, query, k); } - public ScoredDoc[] search(@Nullable K qid, float[] queryFloat, int hits) throws IOException { - KnnFloatVectorQuery query = new KnnFloatVectorQuery(Constants.VECTOR, queryFloat, ((Args) args).efSearch); - TopDocs topDocs = getIndexSearcher().search(query, hits, BREAK_SCORE_TIES_BY_DOCID, true); + /** + * Searches the collection with a query vector. + * + * @param qid query id + * @param query query vector + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(@Nullable K qid, float[] query, int k) throws IOException { + KnnFloatVectorQuery vectorQuery = new KnnFloatVectorQuery(Constants.VECTOR, query, ((Args) args).efSearch); + TopDocs topDocs = getIndexSearcher().search(vectorQuery, k, BREAK_SCORE_TIES_BY_DOCID, true); return super.processLuceneTopDocs(qid, topDocs); } - public ScoredDoc[] search(String queryString, int hits) throws IOException { - return search(null, queryString, hits); + /** + * Searches the collection with a string query that will be encoded by the underlying encoder. + * + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(String query, int k) throws IOException { + return search(null, query, k); } - public ScoredDoc[] search(@Nullable K qid, String queryString, int hits) throws IOException { + /** + * Searches the collection with a string query that will be encoded by the underlying encoder. + * + * @param qid query id + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(@Nullable K qid, String query, int k) throws IOException { if (encoder != null) { try { - return search(qid, encoder.encode(queryString), hits); + return search(qid, encoder.encode(query), k); } catch (OrtException e) { throw new RuntimeException("Error encoding query."); } } - KnnFloatVectorQuery query = generator.buildQuery(Constants.VECTOR, queryString, ((Args) args).efSearch); - TopDocs topDocs = getIndexSearcher().search(query, hits, BREAK_SCORE_TIES_BY_DOCID, true); + KnnFloatVectorQuery vectorQuery = generator.buildQuery(Constants.VECTOR, query, ((Args) args).efSearch); + TopDocs topDocs = getIndexSearcher().search(vectorQuery, k, BREAK_SCORE_TIES_BY_DOCID, true); return super.processLuceneTopDocs(qid, topDocs); } diff --git a/src/main/java/io/anserini/search/InvertedDenseSearcher.java b/src/main/java/io/anserini/search/InvertedDenseSearcher.java index d3e826d687..262aaa6f08 100644 --- a/src/main/java/io/anserini/search/InvertedDenseSearcher.java +++ b/src/main/java/io/anserini/search/InvertedDenseSearcher.java @@ -33,6 +33,7 @@ import org.apache.lucene.store.FSDirectory; import org.kohsuke.args4j.Option; +import javax.annotation.Nullable; import java.io.Closeable; import java.io.IOException; import java.nio.file.Paths; @@ -105,59 +106,85 @@ public InvertedDenseSearcher(Args args) { this.generator = new InvertedDenseVectorQueryGenerator(args, true); } - public SortedMap batch_search(List qids, List queries, int hits) { + /** + * Searches the collection in batch using multiple threads. + * + * @param queries list of queries + * @param qids list of unique query ids + * @param k number of hits + * @param threads number of threads + * @return a map of query id to search results + */ + public SortedMap batch_search(List queries, List qids, int k, int threads) { final SortedMap results = new ConcurrentSkipListMap<>(); - final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(args.threads); final AtomicInteger cnt = new AtomicInteger(); - final long start = System.nanoTime(); - assert qids.size() == queries.size(); - for (int i=0; i { - try { - results.put(qid, search(qid, queryString, hits)); - } catch (IOException e) { - throw new CompletionException(e); - } - - int n = cnt.incrementAndGet(); - if (n % 100 == 0) { - LOG.info(String.format("%d queries processed", n)); - } - }); - } - - executor.shutdown(); - try { - // Wait for existing tasks to terminate. - while (!executor.awaitTermination(1, TimeUnit.MINUTES)); - } catch (InterruptedException ie) { - // (Re-)Cancel if current thread also interrupted. - executor.shutdownNow(); - // Preserve interrupt status. - Thread.currentThread().interrupt(); + try(ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(threads)) { + assert qids.size() == queries.size(); + for (int i = 0; i < qids.size(); i++) { + K qid = qids.get(i); + String queryString = queries.get(i); + + // This is the per-query execution, in parallel. + executor.execute(() -> { + try { + results.put(qid, search(qid, queryString, k)); + } catch (IOException e) { + throw new CompletionException(e); + } + + int n = cnt.incrementAndGet(); + if (n % 100 == 0) { + LOG.info(String.format("%d queries processed", n)); + } + }); + } + + executor.shutdown(); + + try { + // Wait for existing tasks to terminate. + while (!executor.awaitTermination(1, TimeUnit.MINUTES)); + } catch (InterruptedException ie) { + // (Re-)Cancel if current thread also interrupted. + executor.shutdownNow(); + // Preserve interrupt status. + Thread.currentThread().interrupt(); + } } final long durationMillis = TimeUnit.MILLISECONDS.convert(System.nanoTime() - start, TimeUnit.NANOSECONDS); - LOG.info(queries.size() + " queries processed in " + - DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss") + + LOG.info("{} queries processed in {}{}", queries.size(), + DurationFormatUtils.formatDuration(durationMillis, "HH:mm:ss"), String.format(" = ~%.2f q/s", queries.size() / (durationMillis / 1000.0))); return results; } - public ScoredDoc[] search(String queryString, int hits) throws IOException { - return search(null, queryString, hits); + /** + * Searches the collection with a query. + * + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(String query, int k) throws IOException { + return search(null, query, k); } - public ScoredDoc[] search(K qid, String queryString, int hits) throws IOException { - Query query = generator.buildQuery(queryString); - TopDocs topDocs = getIndexSearcher().search(query, hits, BREAK_SCORE_TIES_BY_DOCID, true); + /** + * Searches the collection with a query. + * + * @param qid query id + * @param query query + * @param k number of hits + * @return array of search results + * @throws IOException if error encountered during search + */ + public ScoredDoc[] search(@Nullable K qid, String query, int k) throws IOException { + TopDocs topDocs = getIndexSearcher().search(generator.buildQuery(query), k, BREAK_SCORE_TIES_BY_DOCID, true); return super.processLuceneTopDocs(qid, topDocs); } diff --git a/src/main/java/io/anserini/search/SearchFlatDenseVectors.java b/src/main/java/io/anserini/search/SearchFlatDenseVectors.java index 4096254e44..6f614c1ec5 100644 --- a/src/main/java/io/anserini/search/SearchFlatDenseVectors.java +++ b/src/main/java/io/anserini/search/SearchFlatDenseVectors.java @@ -81,12 +81,12 @@ public SearchFlatDenseVectors(Args args) throws IOException { this.args = args; this.searcher = new FlatDenseSearcher<>(args); - LOG.info(String.format("============ Initializing %s ============", this.getClass().getSimpleName())); - LOG.info("Index: " + args.index); - LOG.info("Topics: " + Arrays.toString(args.topics)); - LOG.info("Query generator: " + args.queryGenerator); - LOG.info("Encoder: " + args.encoder); - LOG.info("Threads: " + args.threads); + LOG.info("============ Initializing {} ============", this.getClass().getSimpleName()); + LOG.info("Index: {}", args.index); + LOG.info("Topics: {}", Arrays.toString(args.topics)); + LOG.info("Query generator: {}", args.queryGenerator); + LOG.info("Encoder: {}", args.encoder); + LOG.info("Threads: {}", args.threads); // We might not be able to successfully read topics for a variety of reasons. Gather all possible // exceptions together as an unchecked exception to make initialization and error reporting clearer. @@ -140,7 +140,7 @@ public void close() throws IOException { @Override public void run() { LOG.info("============ Launching Search Threads ============"); - SortedMap results = searcher.batch_search(qids, queries, args.hits); + SortedMap results = searcher.batch_search(queries, qids, args.hits, args.threads); try(RunOutputWriter out = new RunOutputWriter<>(args.output, args.format, args.runtag, null)) { // zip query to results @@ -148,12 +148,13 @@ public void run() { try { out.writeTopic(qid, queries.get(qids.indexOf(qid)), results.get(qid)); } catch (JsonProcessingException e) { - // Handle the exception or rethrow as unchecked + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. throw new RuntimeException(e); } }); } catch (IOException e) { - e.printStackTrace(); + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. + throw new RuntimeException(e); } } diff --git a/src/main/java/io/anserini/search/SearchHnswDenseVectors.java b/src/main/java/io/anserini/search/SearchHnswDenseVectors.java index cad335a37c..a801338396 100644 --- a/src/main/java/io/anserini/search/SearchHnswDenseVectors.java +++ b/src/main/java/io/anserini/search/SearchHnswDenseVectors.java @@ -81,12 +81,12 @@ public SearchHnswDenseVectors(Args args) throws IOException { this.args = args; this.searcher = new HnswDenseSearcher<>(args); - LOG.info(String.format("============ Initializing %s ============", this.getClass().getSimpleName())); - LOG.info("Index: " + args.index); - LOG.info("Topics: " + Arrays.toString(args.topics)); - LOG.info("Query generator: " + args.queryGenerator); - LOG.info("Encoder: " + args.encoder); - LOG.info("Threads: " + args.threads); + LOG.info("============ Initializing {} ============", this.getClass().getSimpleName()); + LOG.info("Index: {}", args.index); + LOG.info("Topics: {}", Arrays.toString(args.topics)); + LOG.info("Query generator: {}", args.queryGenerator); + LOG.info("Encoder: {}", args.encoder); + LOG.info("Threads: {}", args.threads); // We might not be able to successfully read topics for a variety of reasons. Gather all possible // exceptions together as an unchecked exception to make initialization and error reporting clearer. @@ -140,7 +140,7 @@ public void close() throws IOException { @Override public void run() { LOG.info("============ Launching Search Threads ============"); - SortedMap results = searcher.batch_search(qids, queries, args.hits); + SortedMap results = searcher.batch_search(queries, qids, args.hits, args.threads); try(RunOutputWriter out = new RunOutputWriter<>(args.output, args.format, args.runtag, null)) { // zip query to results @@ -148,12 +148,13 @@ public void run() { try { out.writeTopic(qid, queries.get(qids.indexOf(qid)), results.get(qid)); } catch (JsonProcessingException e) { - // Handle the exception or rethrow as unchecked + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. throw new RuntimeException(e); } }); } catch (IOException e) { - e.printStackTrace(); + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. + throw new RuntimeException(e); } } diff --git a/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java b/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java index b42c138fe2..a1dc00ff0b 100644 --- a/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java +++ b/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java @@ -127,19 +127,20 @@ public void close() throws IOException { @Override public void run() { LOG.info("============ Launching Search Threads ============"); - SortedMap results = searcher.batch_search(qids, queries, args.hits); + SortedMap results = searcher.batch_search(queries, qids, args.hits, args.threads); try(RunOutputWriter out = new RunOutputWriter<>(args.output, args.format, args.runtag, null)) { results.forEach((qid, hits) -> { try { out.writeTopic(qid, queries.get(qids.indexOf(qid)), results.get(qid)); } catch (JsonProcessingException e) { - // Handle the exception or rethrow as unchecked + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. throw new RuntimeException(e); } }); } catch (IOException e) { - e.printStackTrace(); + // Rethrow as unchecked; if we encounter an exception here, the caller should really look into it. + throw new RuntimeException(e); } } diff --git a/src/main/python/run_regression.py b/src/main/python/run_regression.py index f7164eb3e1..ec66fe657c 100644 --- a/src/main/python/run_regression.py +++ b/src/main/python/run_regression.py @@ -234,7 +234,7 @@ def construct_convert_commands(yaml_data): beir_hnsw_onnx = defaultdict(lambda: 0.003) beir_hnsw_onnx['ArguAna'] = 0.02 -beir_hnsw_onnx['BioASQ'] = 0.005 +beir_hnsw_onnx['BioASQ'] = 0.01 beir_hnsw_onnx['CQADupStack-wordpress'] = 0.004 beir_hnsw_onnx['DBPedia'] = 0.006 beir_hnsw_onnx['FEVER'] = 0.007 @@ -245,7 +245,7 @@ def construct_convert_commands(yaml_data): beir_hnsw_onnx['TREC-NEWS'] = 0.02 beir_hnsw_cached = defaultdict(lambda: 0.003) -beir_hnsw_cached['BioASQ'] = 0.005 +beir_hnsw_cached['BioASQ'] = 0.01 beir_hnsw_cached['DBPedia'] = 0.006 beir_hnsw_cached['FEVER'] = 0.008 beir_hnsw_cached['FiQA-2018'] = 0.008 diff --git a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.yaml b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.yaml index f0d2af58ed..5b35238a80 100644 --- a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.yaml +++ b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.cached.yaml @@ -43,7 +43,7 @@ models: - name: bge-hnsw-int8-cached display: BGE-base-en-v1.5 type: hnsw - params: -hits 1000 -efSearch 1000 -removeQuery -threads 16 + params: -hits 1000 -efSearch 2000 -removeQuery -threads 16 results: nDCG@10: - 0.4149 diff --git a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.yaml b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.yaml index 9a832587ae..2546de4fdd 100644 --- a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.yaml +++ b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw-int8.onnx.yaml @@ -43,7 +43,7 @@ models: - name: bge-hnsw-int8-onnx display: BGE-base-en-v1.5 type: hnsw - params: -encoder BgeBaseEn15 -hits 1000 -efSearch 1000 -removeQuery -threads 16 + params: -encoder BgeBaseEn15 -hits 1000 -efSearch 2000 -removeQuery -threads 16 results: nDCG@10: - 0.4149 diff --git a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.yaml b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.yaml index 29d6662787..8191dd7edc 100644 --- a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.yaml +++ b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.cached.yaml @@ -43,7 +43,7 @@ models: - name: bge-hnsw-cached display: BGE-base-en-v1.5 type: hnsw - params: -hits 1000 -efSearch 1000 -removeQuery -threads 16 + params: -hits 1000 -efSearch 2000 -removeQuery -threads 16 results: nDCG@10: - 0.4149 diff --git a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.yaml b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.yaml index 53712a8908..417021a64f 100644 --- a/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.yaml +++ b/src/main/resources/regression/beir-v1.0.0-bioasq.bge-base-en-v1.5.hnsw.onnx.yaml @@ -43,7 +43,7 @@ models: - name: bge-hnsw-onnx display: BGE-base-en-v1.5 type: hnsw - params: -encoder BgeBaseEn15 -hits 1000 -efSearch 1000 -removeQuery -threads 16 + params: -encoder BgeBaseEn15 -hits 1000 -efSearch 2000 -removeQuery -threads 16 results: nDCG@10: - 0.4149 diff --git a/src/test/java/io/anserini/search/FlatDenseSearcherTest.java b/src/test/java/io/anserini/search/FlatDenseSearcherTest.java index 5d23b8eff8..b299d33d9b 100644 --- a/src/test/java/io/anserini/search/FlatDenseSearcherTest.java +++ b/src/test/java/io/anserini/search/FlatDenseSearcherTest.java @@ -162,7 +162,7 @@ public void testAda2Batch() throws Exception { }); try(FlatDenseSearcher searcher = new FlatDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(160885); assertEquals(5, results.length); @@ -406,7 +406,7 @@ public void testCosDprBatchWithOnnx() throws Exception { }); try(FlatDenseSearcher searcher = new FlatDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(2); assertEquals(5, results.length); diff --git a/src/test/java/io/anserini/search/HnswDenseSearcherTest.java b/src/test/java/io/anserini/search/HnswDenseSearcherTest.java index 1bc85de3fd..7860323016 100644 --- a/src/test/java/io/anserini/search/HnswDenseSearcherTest.java +++ b/src/test/java/io/anserini/search/HnswDenseSearcherTest.java @@ -164,7 +164,7 @@ public void testAda2Batch() throws Exception { }); try(HnswDenseSearcher searcher = new HnswDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(160885); assertEquals(5, results.length); @@ -411,7 +411,7 @@ public void testCosDprBatchWithOnnx() throws Exception { }); try(HnswDenseSearcher searcher = new HnswDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(2); assertEquals(5, results.length); diff --git a/src/test/java/io/anserini/search/InvertedDenseSearcherTest.java b/src/test/java/io/anserini/search/InvertedDenseSearcherTest.java index 599a7a8e62..a92f8a43f3 100644 --- a/src/test/java/io/anserini/search/InvertedDenseSearcherTest.java +++ b/src/test/java/io/anserini/search/InvertedDenseSearcherTest.java @@ -160,7 +160,7 @@ public void searchAda2FWBatchTest() throws Exception { }); try(InvertedDenseSearcher searcher = new InvertedDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(160885); assertEquals(5, results.length); @@ -312,7 +312,7 @@ public void searchAda2LLBatchTest() throws Exception { }); try(InvertedDenseSearcher searcher = new InvertedDenseSearcher<>(args)) { - SortedMap allResults = searcher.batch_search(qids, queries, 5); + SortedMap allResults = searcher.batch_search(queries, qids, 5, 2); ScoredDoc[] results = allResults.get(160885); assertEquals(5, results.length);