Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

Rename prebuilt indexes #2672

Draft
wants to merge 5 commits into
base: master
Choose a base branch
from
Draft

Rename prebuilt indexes #2672

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
64ba7e4
Update IndexInfo for HNSW indexes
lintool Jan 6, 2025
fe5816f
tweaked commands
lintool Jan 6, 2025
d340a23
rename
lintool Jan 8, 2025
5a5c9e4
tweaks
lintool Jan 9, 2025
f02fee1
fixed paths.
lintool Jan 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
508 changes: 508 additions & 0 deletions docs/fatjar-regressions/fatjar-regressions-v0.39.0.md
View file
Open in desktop

Large diffs are not rendered by default.

292 changes: 146 additions & 146 deletions docs/reproduce/msmarco-v1-passage.html
View file
Open in desktop

Large diffs are not rendered by default.

10 changes: 5 additions & 5 deletions src/main/java/io/anserini/encoder/dense/CosDprDistilEncoder.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,13 +31,13 @@
* CosDPRDistil
*/
public class CosDprDistilEncoder extends DenseEncoder {
static private final String MODEL_URL = "https://rgw.cs.uwaterloo.ca/pyserini/data/cos-dpr-distil-optimized.onnx";
static private final String MODEL_URL = "https://rgw.cs.uwaterloo.ca/pyserini/data/cosdpr-distil-optimized.onnx";

static private final String VOCAB_URL = "https://rgw.cs.uwaterloo.ca/pyserini/data/cos-dpr-distil-vocab.txt";
static private final String VOCAB_URL = "https://rgw.cs.uwaterloo.ca/pyserini/data/cosdpr-distil-vocab.txt";

static private final String MODEL_NAME = "cos-dpr-distil-optimized.onnx";
static private final String MODEL_NAME = "cosdpr-distil-optimized.onnx";

static private final String VOCAB_NAME = "cos-dpr-distil-vocab.txt";
static private final String VOCAB_NAME = "cosdpr-distil-vocab.txt";

public CosDprDistilEncoder() throws IOException, OrtException, URISyntaxException {
super(MODEL_NAME, MODEL_URL, VOCAB_NAME, VOCAB_URL);
Expand Down Expand Up @@ -65,4 +65,4 @@ public float[] encode(String query) throws OrtException {
return weights;
}

}
}
32 changes: 16 additions & 16 deletions src/main/java/io/anserini/index/IndexInfo.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,47 +48,47 @@ public enum IndexInfo {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-inverted.msmarco-v1-passage.splade-pp-ed.20230524.a59610.tar.gz" },
"2c008fc36131e27966a72292932358e6"),

MSMARCO_V1_PASSAGE_COS_DPR_DISTIL("msmarco-v1-passage.cos-dpr-distil",
MSMARCO_V1_PASSAGE_COS_DPR_DISTIL_HNSW("msmarco-v1-passage.cosdpr-distil.hnsw",
"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",
"",
"lucene-hnsw.msmarco-v1-passage.cosdpr-distil.20240108.825148.tar.gz",
"lucene-hnsw.msmarco-v1-passage.cosdpr-distil.20240108.825148.README.md",
"MS MARCO V1 Passage",
"cosDPR-distil w/ HNSW fp32",
new String[] {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.msmarco-v1-passage.cos-dpr-distil.20240108.825148.tar.gz" },
"d0d602c46fb8b93511f2ab1214bcb86a"),
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.msmarco-v1-passage.cosdpr-distil.20240108.825148.tar.gz" },
"df4c60fa1f3804fa409499824d12d035"),

MSMARCO_V1_PASSAGE_COS_DPR_DISTIL_QUANTIZED("msmarco-v1-passage.cos-dpr-distil.quantized",
MSMARCO_V1_PASSAGE_COS_DPR_DISTIL_HNSW_INT8("msmarco-v1-passage.cosdpr-distil.hnsw-int8",
"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",
"",
"lucene-hnsw-int8.msmarco-v1-passage.cosdpr-distil.20240108.825148.tar.gz",
"lucene-hnsw.msmarco-v1-passage.cosdpr-distil.20240108.825148.README.md",
"MS MARCO V1 Passage",
"cosDPR-distil w/ HNSW int8",
new String[] {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw-int8.msmarco-v1-passage.cos-dpr-distil.20240108.825148.tar.gz" },
"24ed94669c9caf52704e0ceccee3732b"),
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw-int8.msmarco-v1-passage.cosdpr-distil.20240108.825148.tar.gz" },
"119124ad358bb81e6a203b04d1b99a9c"),

MSMARCO_V1_PASSAGE_BGE_BASE_EN_15("msmarco-v1-passage.bge-base-en-v1.5",
MSMARCO_V1_PASSAGE_BGE_BASE_EN_15_HNSW("msmarco-v1-passage.bge-base-en-v1.5.hnsw",
"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",
"",
"lucene-hnsw.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.README.md",
"MS MARCO V1 Passage",
"bge-base-en-v1.5 w/ HNSW fp32",
new String[] {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.tar.gz" },
"00a577f689d90f95e6c5611438b0af3d"),

MSMARCO_V1_PASSAGE_BGE_BASE_EN_15_QUANTIZED("msmarco-v1-passage.bge-base-en-v1.5.quantized",
MSMARCO_V1_PASSAGE_BGE_BASE_EN_15_HNSW_INT8("msmarco-v1-passage.bge-base-en-v1.5.hnsw-int8",
"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",
"",
"lucene-hnsw.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.README.md",
"MS MARCO V1 Passage",
"bge-base-en-v1.5 w/ HNSW int8",
new String[] {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw-int8.msmarco-v1-passage.bge-base-en-v1.5.20240117.53514b.tar.gz" },
"7830712459cf124c96fd058bb0a405b7"),

MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30("msmarco-v1-passage.cohere-embed-english-v3.0",
MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30_HNSW("msmarco-v1-passage.cohere-embed-english-v3.0.hnsw",
"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",
"",
Expand All @@ -98,7 +98,7 @@ public enum IndexInfo {
"https://rgw.cs.uwaterloo.ca/pyserini/indexes/lucene/lucene-hnsw.msmarco-v1-passage.cohere-embed-english-v3.0.20240228.eacd13.tar.gz" },
"c7294ca988ae1b812d427362ffca1ee2"),

MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30_QUANTIZED("msmarco-v1-passage.cohere-embed-english-v3.0.quantized",
MSMARCO_V1_PASSAGE_COHERE_EMBED_ENGLISH_30_HNSW_INT8("msmarco-v1-passage.cohere-embed-english-v3.0.hnsw-int8",
"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",
"",
Expand Down
16 changes: 8 additions & 8 deletions src/main/java/io/anserini/search/topicreader/Topics.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ public enum Topics {
TREC2019_DL_PASSAGE_SPLADE_DISTILL_COCODENSER_MEDIUM(TsvIntTopicReader.class,"topics.dl19-passage.splade_distil_cocodenser_medium.tsv.gz"),
TREC2019_DL_PASSAGE_SPLADE_PP_ED(TsvIntTopicReader.class,"topics.dl19-passage.splade-pp-ed.tsv.gz"),
TREC2019_DL_PASSAGE_SPLADE_PP_SD(TsvIntTopicReader.class,"topics.dl19-passage.splade-pp-sd.tsv.gz"),
TREC2019_DL_PASSAGE_COS_DPR_DISTIL(JsonIntVectorTopicReader.class, "topics.dl19-passage.cos-dpr-distil.jsonl.gz"),
TREC2019_DL_PASSAGE_COSDPR_DISTIL(JsonIntVectorTopicReader.class, "topics.dl19-passage.cosdpr-distil.jsonl.gz"),
TREC2019_DL_PASSAGE_BGE_BASE_EN_15(JsonIntVectorTopicReader.class, "topics.dl19-passage.bge-base-en-v1.5.jsonl.gz"),
TREC2019_DL_PASSAGE_COHERE_EMBED_ENGLISH_30(JsonIntVectorTopicReader.class, "topics.dl19-passage.cohere-embed-english-v3.0.jsonl.gz"),
TREC2020_DL(TsvIntTopicReader.class,"topics.dl20.txt"),
Expand All @@ -72,7 +72,7 @@ public enum Topics {
TREC2020_DL_SPLADE_DISTILL_COCODENSER_MEDIUM(TsvIntTopicReader.class,"topics.dl20.splade_distil_cocodenser_medium.tsv.gz"),
TREC2020_DL_SPLADE_PP_ED(TsvIntTopicReader.class,"topics.dl20.splade-pp-ed.tsv.gz"),
TREC2020_DL_SPLADE_PP_SD(TsvIntTopicReader.class,"topics.dl20.splade-pp-sd.tsv.gz"),
TREC2020_DL_COS_DPR_DISTIL(JsonIntVectorTopicReader.class, "topics.dl20.cos-dpr-distil.jsonl.gz"),
TREC2020_DL_COSDPR_DISTIL(JsonIntVectorTopicReader.class, "topics.dl20.cosdpr-distil.jsonl.gz"),
TREC2020_DL_BGE_BASE_EN_15(JsonIntVectorTopicReader.class, "topics.dl20.bge-base-en-v1.5.jsonl.gz"),
TREC2020_DL_COHERE_EMBED_ENGLISH_30(JsonIntVectorTopicReader.class, "topics.dl20.cohere-embed-english-v3.0.jsonl.gz"),
TREC2021_DL(TsvIntTopicReader.class,"topics.dl21.txt"),
Expand Down Expand Up @@ -117,7 +117,7 @@ public enum Topics {
MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_DISTILL_COCODENSER_MEDIUM(TsvIntTopicReader.class, "topics.msmarco-passage.dev-subset.splade_distil_cocodenser_medium.tsv.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_ED(TsvIntTopicReader.class, "topics.msmarco-passage.dev-subset.splade-pp-ed.tsv.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_SD(TsvIntTopicReader.class, "topics.msmarco-passage.dev-subset.splade-pp-sd.tsv.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_COS_DPR_DISTIL(JsonIntVectorTopicReader.class, "topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_COSDPR_DISTIL(JsonIntVectorTopicReader.class, "topics.msmarco-passage.dev-subset.cosdpr-distil.jsonl.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_BGE_BASE_EN_15(JsonIntVectorTopicReader.class, "topics.msmarco-passage.dev-subset.bge-base-en-v1.5.jsonl.gz"),
MSMARCO_PASSAGE_DEV_SUBSET_COHERE_EMBED_ENGLISH_30(JsonIntVectorTopicReader.class, "topics.msmarco-passage.dev-subset.cohere-embed-english-v3.0.jsonl.gz"),
MSMARCO_PASSAGE_TEST_SUBSET(TsvIntTopicReader.class, "topics.msmarco-passage.test-subset.txt"),
Expand Down Expand Up @@ -566,33 +566,33 @@ private static Map<String, Topics> generateSymbolDictionary() {
// Additional aliases
m.put("msmarco-passage-dev", MSMARCO_PASSAGE_DEV_SUBSET);
m.put("msmarco-passage-dev-splade-pp-ed", MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_ED);
m.put("msmarco-passage-dev-cos-dpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COS_DPR_DISTIL);
m.put("msmarco-passage-dev-cosdpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COSDPR_DISTIL);
m.put("msmarco-passage-dev-bge-base-en-v1.5", MSMARCO_PASSAGE_DEV_SUBSET_BGE_BASE_EN_15);
m.put("msmarco-passage-dev-cohere-embed-english-v3.0", MSMARCO_PASSAGE_DEV_SUBSET_COHERE_EMBED_ENGLISH_30);

m.put("msmarco-passage.dev", MSMARCO_PASSAGE_DEV_SUBSET);
m.put("msmarco-passage.dev.splade-pp-ed", MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_ED);
m.put("msmarco-passage.dev.cos-dpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COS_DPR_DISTIL);
m.put("msmarco-passage.dev.cosdpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COSDPR_DISTIL);
m.put("msmarco-passage.dev.bge-base-en-v1.5", MSMARCO_PASSAGE_DEV_SUBSET_BGE_BASE_EN_15);
m.put("msmarco-passage.dev.cohere-embed-english-v3.0", MSMARCO_PASSAGE_DEV_SUBSET_COHERE_EMBED_ENGLISH_30);

m.put("msmarco-v1-passage-dev", MSMARCO_PASSAGE_DEV_SUBSET);
m.put("msmarco-v1-passage-dev-splade-pp-ed", MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_ED);
m.put("msmarco-v1-passage-dev-cos-dpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COS_DPR_DISTIL);
m.put("msmarco-v1-passage-dev-cosdpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COSDPR_DISTIL);
m.put("msmarco-v1-passage-dev-bge-base-en-v1.5", MSMARCO_PASSAGE_DEV_SUBSET_BGE_BASE_EN_15);
m.put("msmarco-v1-passage-dev-cohere-embed-english-v3.0", MSMARCO_PASSAGE_DEV_SUBSET_COHERE_EMBED_ENGLISH_30);

m.put("msmarco-v1-passage.dev", MSMARCO_PASSAGE_DEV_SUBSET);
m.put("msmarco-v1-passage.dev.splade-pp-ed", MSMARCO_PASSAGE_DEV_SUBSET_SPLADE_PP_ED);
m.put("msmarco-v1-passage.dev.cos-dpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COS_DPR_DISTIL);
m.put("msmarco-v1-passage.dev.cosdpr-distil", MSMARCO_PASSAGE_DEV_SUBSET_COSDPR_DISTIL);
m.put("msmarco-v1-passage.dev.bge-base-en-v1.5", MSMARCO_PASSAGE_DEV_SUBSET_BGE_BASE_EN_15);
m.put("msmarco-v1-passage.dev.cohere-embed-english-v3.0", MSMARCO_PASSAGE_DEV_SUBSET_COHERE_EMBED_ENGLISH_30);

m.put("dl20-passage", TREC2020_DL);
m.put("dl20-doc", TREC2020_DL);

m.put("dl20-passage.splade-pp-ed", TREC2020_DL_SPLADE_PP_ED);
m.put("dl20-passage.cos-dpr-distil", TREC2020_DL_COS_DPR_DISTIL);
m.put("dl20-passage.cosdpr-distil", TREC2020_DL_COSDPR_DISTIL);
m.put("dl20-passage.bge-base-en-v1.5", TREC2020_DL_BGE_BASE_EN_15);
m.put("dl20-passage.cohere-embed-english-v3.0", TREC2020_DL_COHERE_EMBED_ENGLISH_30);

Expand Down
Loading
Loading