From 4e4669361530bab035bde4e43ca00861727776ed Mon Sep 17 00:00:00 2001 From: Sean MacAvaney Date: Sun, 4 Feb 2024 15:59:27 +0000 Subject: [PATCH] fix location of msmarco source files and bump version (#257) --- ir_datasets/__init__.py | 2 +- ir_datasets/etc/downloads.json | 138 ++++++++++++++++----------------- setup.py | 2 +- 3 files changed, 71 insertions(+), 71 deletions(-) diff --git a/ir_datasets/__init__.py b/ir_datasets/__init__.py index 85abe2c2..6bb5f194 100644 --- a/ir_datasets/__init__.py +++ b/ir_datasets/__init__.py @@ -101,4 +101,4 @@ def main_cli(): import sys main(sys.argv[1:]) -__version__ = "0.5.5" # NOTE: keep this in sync with setup.py +__version__ = "0.5.6" # NOTE: keep this in sync with setup.py diff --git a/ir_datasets/etc/downloads.json b/ir_datasets/etc/downloads.json index 5994c0e0..f70e951f 100644 --- a/ir_datasets/etc/downloads.json +++ b/ir_datasets/etc/downloads.json @@ -4422,62 +4422,62 @@ "msmarco-document": { "docs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-docs.trec.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-docs.trec.gz", "size_hint": 8501799926, "expected_md5": "d4863e4f342982b51b9a8fc668b2d0c0", "cache_path": "collection.tsv.gz", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-doctrain-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-doctrain-queries.tsv.gz", "size_hint": 6457962, "expected_md5": "4086d31a9cf2d7b69c4932609058111d", "cache_path": "train/queries.tsv.gz" }, "train/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-doctrain-qrels.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-doctrain-qrels.tsv.gz", "size_hint": 2385717, "expected_md5": "9d1609e240113b0504fd2e61cb36d924", "cache_path": "train/qrels.gz" }, "train/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-doctrain-top100.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-doctrain-top100.gz", "size_hint": 403564127, "expected_md5": "be32fa12eb71e93014c84775d7465976", "cache_path": "train/ms.run.gz" }, "dev/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-docdev-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-docdev-queries.tsv.gz", "size_hint": 91837, "expected_md5": "ac20593d71b9c32ab2633230f9cdf10d", "cache_path": "dev/queries.tsv.gz" }, "dev/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-docdev-qrels.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-docdev-qrels.tsv.gz", "size_hint": 38553, "expected_md5": "5eeafaeb4960979a62e7fed93273254e", "cache_path": "dev/qrels.gz" }, "dev/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-docdev-top100.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-docdev-top100.gz", "size_hint": 5701839, "expected_md5": "ac10255edf321821b0ccd0f123037780", "cache_path": "dev/ms.run.gz" }, "eval/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docleaderboard-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docleaderboard-queries.tsv.gz", "size_hint": 102131, "expected_md5": "50fe4285d64444c9ffc933b66a79f775", "cache_path": "eval/queries.tsv.gz" }, "eval/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docleaderboard-top100.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docleaderboard-top100.tsv.gz", "size_hint": 6362021, "expected_md5": "a039a00356c09606962f3c07c68d02ef", "cache_path": "eval/ms.run.gz" }, "trec-dl-2019/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", "size_hint": 4276, "expected_md5": "eda71eccbe4d251af83150abe065368c", "cache_path": "trec-dl-2019/queries.tsv.gz" @@ -4490,19 +4490,19 @@ "cache_path": "trec-dl-2019/qrels" }, "trec-dl-2019/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-doctest2019-top100.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-doctest2019-top100.gz", "size_hint": 220457, "expected_md5": "91071b89dd52124057a87d53cd22028d", "cache_path": "trec-dl-2019/ms.run.gz" }, "trec-dl-2020/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", "size_hint": 4131, "expected_md5": "00a406fb0d14ed3752d70d1e4eb98600", "cache_path": "trec-dl-2020/queries.tsv.gz" }, "trec-dl-2020/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-doctest2020-top100.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-doctest2020-top100.gz", "size_hint": 208679, "expected_md5": "96f39dae3443736bd6393bd09a5a0a20", "cache_path": "trec-dl-2020/ms.run.gz" @@ -4515,19 +4515,19 @@ "cache_path": "trec-dl-2020/qrels" }, "orcas/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/orcas-doctrain-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/orcas-doctrain-queries.tsv.gz", "size_hint": 104209356, "expected_md5": "519c5f522294406e3b0574d7d53cf233", "cache_path": "orcas/queries.tsv.gz" }, "orcas/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/orcas-doctrain-qrels.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/orcas-doctrain-qrels.tsv.gz", "size_hint": 109824304, "expected_md5": "3f94db106374be649782022c3018acd0", "cache_path": "orcas/qrels.gz" }, "orcas/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/orcas-doctrain-top100.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/orcas-doctrain-top100.gz", "size_hint": 10724320629, "expected_md5": "118d0884638fd405e111157a124ef0b2", "cache_path": "orcas/ms.run.gz", @@ -4549,98 +4549,98 @@ "msmarco-document-v2": { "docs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco_v2_doc.tar", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco_v2_doc.tar", "size_hint": 34648862720, "expected_md5": "eea90100409a254fdb157b8e4e349deb", "cache_path": "msmarco_v2_doc.tar", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train_queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_train_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_train_queries.tsv", "size_hint": 13511656, "expected_md5": "7821d8bef3971e12780a80a89a3e5cbd", "cache_path": "train/queries.tsv" }, "train_scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_train_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_train_top100.txt.gz", "size_hint": 424107669, "expected_md5": "b4d5915172d5f54bd23c31e966c114de", "cache_path": "train/top100.trec.gz" }, "train_qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_train_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_train_qrels.tsv", "size_hint": 12450533, "expected_md5": "2f788d031c2ca29c4c482167fa5966de", "cache_path": "train/qrels" }, "dev1_queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev_queries.tsv", "size_hint": 191992, "expected_md5": "b05dc19f1d2b8ad729f189328a685aa1", "cache_path": "dev1/queries.tsv" }, "dev1_scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev_top100.txt.gz", "size_hint": 5830666, "expected_md5": "4dd27d511748bede545cd7ae3fc92bf4", "cache_path": "dev1/top100.trec" }, "dev1_qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev_qrels.tsv", "size_hint": 177593, "expected_md5": "aad92d731892ccb0cf9c4c2e37e0f0f1", "cache_path": "dev1/qrels" }, "dev2_queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev2_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev2_queries.tsv", "size_hint": 209911, "expected_md5": "f000319f1893a7acdd60fdcae0703b95", "cache_path": "dev2/queries.tsv" }, "dev2_scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev2_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev2_top100.txt.gz", "size_hint": 6412563, "expected_md5": "e03b5404e9027569c1aa794b1408d8a5", "cache_path": "dev2/top100.trec" }, "dev2_qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_dev2_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_dev2_qrels.tsv", "size_hint": 195474, "expected_md5": "f2eead4b192683ae5fbd66f4d3f08b96", "cache_path": "dev2/qrels" }, "trec-dl-2019/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", "size_hint": 4276, "expected_md5": "eda71eccbe4d251af83150abe065368c", "cache_path": "trec-dl-2019/queries.tsv.gz" }, "trec_dl_2019_qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_trec2019_qrels.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_trec2019_qrels.txt.gz", "size_hint": 107475, "expected_md5": "aa37367d6db77c63d1ee392de6d446e2", "cache_path": "trec-dl-2019/qrels.gz" }, "trec-dl-2020/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", "size_hint": 4131, "expected_md5": "00a406fb0d14ed3752d70d1e4eb98600", "cache_path": "trec-dl-2020/queries.tsv.gz" }, "trec_dl_2020_qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/docv2_trec2020_qrels.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/docv2_trec2020_qrels.txt.gz", "size_hint": 62387, "expected_md5": "06a0a6f29621ee477a093d9dba8e5be9", "cache_path": "trec-dl-2020/qrels.gz" }, "trec-dl-2021/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2021_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2021_queries.tsv", "size_hint": 24585, "expected_md5": "46d863434dda18300f5af33ee29c4b28", "cache_path": "trec-dl-2021/queries.tsv" }, "trec-dl-2021/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2021_document_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2021_document_top100.txt.gz", "size_hint": 618228, "expected_md5": "0bc85e3f2a6f798b91e18f0cd4a6bc6b", "cache_path": "trec-dl-2021/top100.trec.gz" @@ -4659,13 +4659,13 @@ "cache_path": "anchor-text-separate-v2.jsonl.gz" }, "trec-dl-2022/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2022_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2022_queries.tsv", "size_hint": 21508, "expected_md5": "f1bfd53d80e81e58207ce557fd2211a0", "cache_path": "trec-dl-2022/queries.tsv" }, "trec-dl-2022/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2022_document_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2022_document_top100.txt.gz", "size_hint": 642721, "expected_md5": "93f70329ce1b9ce913a5f87008736ff2", "cache_path": "trec-dl-2022/top100.txt.gz" @@ -4678,13 +4678,13 @@ "cache_path": "trec-dl-2022/qrels.inferred.txt" }, "trec-dl-2023/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2023_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2023_queries.tsv", "size_hint": 38128, "expected_md5": "7df9e17b47cc9aa5d1c9fd5b313e273c", "cache_path": "trec-dl-2023/queries.tsv" }, "trec-dl-2023/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2023_document_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2023_document_top100.txt.gz", "size_hint": 902168, "expected_md5": "0f5d548e53afb9e319c837ad67f9046a", "cache_path": "trec-dl-2023/top100.txt.gz" @@ -4693,14 +4693,14 @@ "msmarco-passage": { "collectionandqueries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/collectionandqueries.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/collectionandqueries.tar.gz", "size_hint": 1057717952, "expected_md5": "31644046b18952c1386cd4564ba2ae69", "cache_path": "collectionandqueries.tar.gz", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/queries.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/queries.tar.gz", "size_hint": 18882551, "expected_md5": "c177b2795d5f2dcc524cf00fcd973be1", "cache_path": "queries.tar.gz" @@ -4712,51 +4712,51 @@ "cache_path": "medmarco.qids" }, "train/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/qrels.train.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/qrels.train.tsv", "size_hint": 10589532, "expected_md5": "733fb9fe12d93e497f7289409316eccf", "cache_path": "train/qrels" }, "train/docpairs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/qidpidtriples.train.full.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/qidpidtriples.train.full.tsv.gz", "size_hint": 2633557579, "expected_md5": "215a5204288820672f5e9451d9e202c5", "cache_path": "train/docpairs.tsv.gz", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train/docpairs/v2": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/qidpidtriples.train.full.2.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/qidpidtriples.train.full.2.tsv.gz", "size_hint": 1841693309, "expected_md5": "219083e80a0a751c08b968c2f31a4e0b", "cache_path": "train/qidpidtriples.train.full.2.tsv.gz", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train/docpairs/small": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/triples.train.small.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/triples.train.small.tar.gz", "size_hint": 7930881353, "expected_md5": "c13bf99ff23ca691105ad12eab837f84", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/top1000.train.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/top1000.train.tar.gz", "size_hint": 11519984492, "expected_md5": "d99fdbd5b2ea84af8aa23194a3263052", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "dev/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/qrels.dev.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/qrels.dev.tsv", "size_hint": 1201626, "expected_md5": "9157ccaeaa8227f91722ba5770787b16", "cache_path": "dev/qrels" }, "dev/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/top1000.dev.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/top1000.dev.tar.gz", "size_hint": 687414398, "expected_md5": "8c140662bdf123a98fbfe3bb174c5831", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "eval/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/top1000.eval.tar.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/top1000.eval.tar.gz", "size_hint": 673440221, "expected_md5": "73778cd99f6e0632d12d0b5731b20a02", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} @@ -4769,23 +4769,23 @@ "cache_path": "trec-dl-2019/qrels" }, "trec-dl-2019/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2019-queries.tsv.gz", "size_hint": 4276, "expected_md5": "eda71eccbe4d251af83150abe065368c" }, "trec-dl-2019/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-passagetest2019-top1000.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-passagetest2019-top1000.tsv.gz", "size_hint": 26634062, "expected_md5": "ec9e012746aa9763c7ff10b3336a3ce1" }, "trec-dl-2020/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-test2020-queries.tsv.gz", "size_hint": 4131, "expected_md5": "00a406fb0d14ed3752d70d1e4eb98600", "cache_path": "trec-dl-2020/queries.tsv.gz" }, "trec-dl-2020/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco-passagetest2020-top1000.tsv.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco-passagetest2020-top1000.tsv.gz", "size_hint": 26230218, "expected_md5": "aa6fbc51d66bd1dc745964c0e140a727" }, @@ -4806,74 +4806,74 @@ "msmarco-passage-v2": { "passages": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/msmarco_v2_passage.tar", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/msmarco_v2_passage.tar", "size_hint": 21768192000, "expected_md5": "05946bac48a8ffee62e160213eab3fda", "cache_path": "msmarco_v2_passage.tar", "download_args": {"headers": {"X-Ms-Version": "2019-12-12"}} }, "train/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_train_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_train_queries.tsv", "size_hint": 11608838, "expected_md5": "1835f44e6792c51aa98eed722a8dcc11", "cache_path": "train/queries.tsv" }, "train/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_train_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_train_top100.txt.gz", "size_hint": 340634991, "expected_md5": "7cd731ed984fccb2396f11a284cea800", "cache_path": "train/top100.txt.gz" }, "train/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_train_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_train_qrels.tsv", "size_hint": 11620946, "expected_md5": "a2e37e9a9c7ca13d6e38be0512a52017", "cache_path": "train/qrels.tsv" }, "dev1/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev_queries.tsv", "size_hint": 164507, "expected_md5": "0fa4c6d64a653142ade9fc61d7484239", "cache_path": "dev1/queries.tsv" }, "dev1/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev_top100.txt.gz", "size_hint": 4882727, "expected_md5": "fee817a3ee273be8623379e5d3108c0b", "cache_path": "dev1/top100.txt.gz" }, "dev1/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev_qrels.tsv", "size_hint": 165024, "expected_md5": "10f9263260d206d8fb8f13864aea123a", "cache_path": "dev1/qrels.tsv" }, "dev2/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev2_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev2_queries.tsv", "size_hint": 179603, "expected_md5": "565b84dfa7ccd2f4251fa2debea5947a", "cache_path": "dev2/queries.tsv" }, "dev2/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev2_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev2_top100.txt.gz", "size_hint": 5355464, "expected_md5": "da532bf26169a3a2074fae774471cc9f", "cache_path": "dev2/top100.txt.gz" }, "dev2/qrels": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/passv2_dev2_qrels.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/passv2_dev2_qrels.tsv", "size_hint": 181612, "expected_md5": "8ed8577fa459d34b59cf69b4daa2baeb", "cache_path": "dev2/qrels.tsv" }, "trec-dl-2021/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2021_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2021_queries.tsv", "size_hint": 24585, "expected_md5": "46d863434dda18300f5af33ee29c4b28", "cache_path": "trec-dl-2021/queries.tsv" }, "trec-dl-2021/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2021_passage_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2021_passage_top100.txt.gz", "size_hint": 604533, "expected_md5": "e2be2d307da26d1a3f76eb95507672a3", "cache_path": "trec-dl-2021/top100.trec.gz" @@ -4886,13 +4886,13 @@ "cache_path": "trec-dl-2021/qrels" }, "trec-dl-2022/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2022_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2022_queries.tsv", "size_hint": 21508, "expected_md5": "f1bfd53d80e81e58207ce557fd2211a0", "cache_path": "trec-dl-2022/queries.tsv" }, "trec-dl-2022/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2022_passage_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2022_passage_top100.txt.gz", "size_hint": 630095, "expected_md5": "36004dfad64826167aeecddff1d490a6", "cache_path": "trec-dl-2022/top100.txt.gz" @@ -4905,13 +4905,13 @@ "cache_path": "trec-dl-2022/qrels.withDupes.txt" }, "trec-dl-2023/queries": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2023_queries.tsv", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2023_queries.tsv", "size_hint": 38128, "expected_md5": "7df9e17b47cc9aa5d1c9fd5b313e273c", "cache_path": "trec-dl-2023/queries.tsv" }, "trec-dl-2023/scoreddocs": { - "url": "https://msmarco.blob.core.windows.net/msmarcoranking/2023_passage_top100.txt.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarcoranking/2023_passage_top100.txt.gz", "size_hint": 888898, "expected_md5": "c339ed75e1556cacb387899f34cadad1", "cache_path": "trec-dl-2023/top100.txt.gz" @@ -4926,19 +4926,19 @@ "msmarco-qna": { "train": { - "url": "https://msmarco.blob.core.windows.net/msmarco/train_v2.1.json.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarco/train_v2.1.json.gz", "size_hint": 1112116929, "expected_md5": "576230a745a06943c3a49e76acea1d9d", "cache_path": "train_v2.1.json.gz" }, "dev": { - "url": "https://msmarco.blob.core.windows.net/msmarco/dev_v2.1.json.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarco/dev_v2.1.json.gz", "size_hint": 138303699, "expected_md5": "5e14839f31c933560fbb3bae4ce67829", "cache_path": "dev_v2.1.json.gz" }, "eval": { - "url": "https://msmarco.blob.core.windows.net/msmarco/eval_v2.1_public.json.gz", + "url": "https://msmarco.z22.web.core.windows.net/msmarco/eval_v2.1_public.json.gz", "size_hint": 133851237, "expected_md5": "5fcca9336c7486498c3e1cf81fa89f74", "cache_path": "eval_v2.1_public.json.gz" diff --git a/setup.py b/setup.py index 08b832b9..b7bc3538 100644 --- a/setup.py +++ b/setup.py @@ -6,7 +6,7 @@ setuptools.setup( name="ir_datasets", - version="0.5.5", # NOTE: keep this in sync with ir_datasets/__init__.py + version="0.5.6", # NOTE: keep this in sync with ir_datasets/__init__.py author="Sean MacAvaney", author_email="sean.macavaney@glasgow.ac.uk", description="provides a common interface to many IR ad-hoc ranking benchmarks, training datasets, etc.",