castorini/pyserini

Issues

• mContriever pre-built index for Mr.TyDi datasets

  #1904 opened 2 days ago by cramraj8
  0

• How are you handling duplicate entries for the corpus and qrels?

  #1902 opened 4 days ago by steven-channel
  1

• Does pyserini.search include deep learning 2023 (dl23) track of the TREC dataset?

  #1878 opened 5 days ago by sina-nabavi
  2

• Install Failed building wheel for nmslib with pybind11-2.6.1

  #1896 opened 6 days ago by GrigoriiTarasov
  0

• 'io.anserini.search.ScoredDoc' object has no attribute 'raw'

  #1773 opened 5 months ago by nactran
  2

• Pyserini download index doesn't actually appear to check tarball size

  #1886 opened 22 days ago by lintool
  0

• merge a large index with small index \ adding small collection of docs to a large index

  #1883 opened 23 days ago by tommymordo33
  0

• The anserini library does not load on Windows when the user name is in Chinese.

  #1880 opened a month ago by xzzvsxd
  0

• Feature request: docker build for portability

  #1733 opened 6 months ago by sueszli
  3

• Which tokenization technique is employed by BM25?

  #1875 opened a month ago by lxx1220
  0

• Connection Reset Error in Reproducing DPR

  #1869 opened a month ago by AnsrM
  0

• pyserini segfaults during search with ray

  #1867 opened a month ago by jasper-xian
  2

• version conflict： the doc of experiments-nfcorpus.md

  #1865 opened 2 months ago by Adeshen
  3

• number of hits for a given query is not as specified in the retrieval command

  #1864 opened 2 months ago by NourOM02
  0

• Pyserini library not working in google colab

  #1862 opened 2 months ago by bhavikchandana
  3

• error when using four fields in contents ,following pyserini/docs /usage-index.md

  #1859 opened 2 months ago by ywm5
  2

• Add convenience method to get raw text from dense retrieval for prebuilt indexes

  #1856 opened 2 months ago by lintool
  0

• Unable to read topics: MIRACL_V10_FI_DEV java.io.IOException

  #1850 opened 2 months ago by wxywb
  1

• how to use trained retriever?

  #1787 opened 2 months ago by stellakke
  2

• Incorporate SPLADE++ ED BEIR regressions

  #1747 opened 2 months ago by lintool
  2

• Missing MS MARCO v2 doc 2CRs

  #1809 opened 2 months ago by lintool
  7

• no attribute 'TREC2023_DL

  #1822 opened 2 months ago by kisozinov
  2

• Custom path for index download in installation sample code

  #1837 opened 2 months ago by sdan2
  0

• Pyserini.encode : 'texts': batch_info['text'], KeyError: 'text'

  #1821 opened 2 months ago by ashishakkumar
  2

• Bug: init_query_encoder() missing 1 required positional argument: 'multimodal'

  #1830 opened 2 months ago by lintool
  1

• DeprecationWarning: pkg_resources for 2CR

  #1808 opened 2 months ago by lintool
  1

• AutoQueryEncoder not using query prefixes (for E5-like and other models)

  #1812 opened 3 months ago by orionw
  1

• Results pagination support in pyserini

  #1814 opened 3 months ago by bevankoopman
  2

• `pyserini.search.lucene` recall result not good as `LuceneSearcher.search`

  #1823 opened 2 months ago by better629
  0

• Having problem loading splade-pp-ed BEIR prebuilt indexes

  #1818 opened 2 months ago by zwc662
  1

• test cases time out

  #1736 opened 3 months ago by sueszli
  0

• ValueError: Topic beir-v1.0.0-robust04.test.splade-pp-ed Not Found

  #1782 opened 3 months ago by ChuanMeng
  1

• How to run custom topic on convert_trec_run_to_dpr_run

  #1793 opened 3 months ago by kerkathy
  1

• How to get raw content

  #1752 opened 5 months ago by BeastyZ
  4

• No matching jar found

  #1775 opened 4 months ago by AlexStan0
  2

• `castorini/unicoil-d2q-msmarco-passage` referenced in documentation is missing

  #1767 opened 5 months ago by zeuner
  1

• LuceneSearcher + multiprocessing problem

  #1761 opened 5 months ago by davidoterof
  0

• Upgrading to Pyserini 0.24 means `.raw` option not available.

  #1762 opened 5 months ago by bevankoopman
  1

• trec_eval error

  #1756 opened 5 months ago by BeastyZ
  6

• In Splade example for MS Marco evaluation why index 8.8M train passages and evaluate wiht 6980 queries from dev ?

  #1754 opened 5 months ago by PrithivirajDamodaran
  0

• How to build collections using msmarco and beir

  #1751 opened 5 months ago by BeastyZ
  2

• BM25 batch search with multi threads error: java.lang.OutOfMemoryError: Java heap space

  #1740 opened 6 months ago by zhiyuanpeng
  1

• Normalize embeddings when using a custom dense encoder?

  #1720 opened 6 months ago by orionw
  3

• duplicate query encoder code

  #1728 opened 6 months ago by MXueguang
  0

• How to add stop words when building BM25 index?

  #1725 opened 6 months ago by RulinShao
  0

• Bug introduced by #1622 max_length in init_query_encoder

  #1699 opened 7 months ago by lintool
  1

• ODQA NQ regression error

  #1690 opened 7 months ago by lintool
  1

• Will different searcher and document_searcher affect the search results?

  #1695 opened 7 months ago by Luoyang144
  0

• Unrecognized index name wikipedia-dpr-100w.dpr-multi

  #1693 opened 7 months ago by abdoelsayed2016
  0

• Is it possible to seperate bm25 search module in pyserini?

  #1686 opened 7 months ago by zixiliuUSC
  0