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

Jump to bottom

feat: add support for BM25Retriever in InMemoryDocumentStore #3561

Merged
merged 31 commits into from
Nov 22, 2022
Merged

feat: add support for BM25Retriever in InMemoryDocumentStore #3561

merged 31 commits into from
Nov 22, 2022

Commits on Nov 10, 2022

  1. Merge remote-tracking branch 'origin/main' into imds_support_for_bm25

    @anakin87
    anakin87 committed Nov 10, 2022
    Configuration menu
    Copy the full SHA
    cf16c25 View commit details
    Browse the repository at this point in the history

  2. very first draft

    @anakin87
    anakin87 committed Nov 10, 2022
    Configuration menu
    Copy the full SHA
    ee89a34 View commit details
    Browse the repository at this point in the history

Commits on Nov 11, 2022

  1. implement query and query_batch

    @anakin87
    anakin87 committed Nov 11, 2022
    Configuration menu
    Copy the full SHA
    3d7e8aa View commit details
    Browse the repository at this point in the history

Commits on Nov 12, 2022

  1. add more bm25 parameters

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    5890742 View commit details
    Browse the repository at this point in the history

  2. add rank_bm25 dependency

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    d94433f View commit details
    Browse the repository at this point in the history

  3. fix mypy

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    ce5efae View commit details
    Browse the repository at this point in the history

  4. remove tokenizer callable parameter

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    432eff7 View commit details
    Browse the repository at this point in the history

  5. remove unused import

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    91d40ff View commit details
    Browse the repository at this point in the history

  6. only json serializable attributes

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    2e39f05 View commit details
    Browse the repository at this point in the history

  7. try to fix: pylint too-many-public-methods / R0904

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    343f1d4 View commit details
    Browse the repository at this point in the history

  8. bm25 attribute always present

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    514c248 View commit details
    Browse the repository at this point in the history

  9. convert errors into warnings to make the tutorial 1 work

    @anakin87
    anakin87 committed Nov 12, 2022
    Configuration menu
    Copy the full SHA
    03a35a2 View commit details
    Browse the repository at this point in the history

Commits on Nov 13, 2022

  1. add docstrings; tests

    @anakin87
    anakin87 committed Nov 13, 2022
    Configuration menu
    Copy the full SHA
    25d6d42 View commit details
    Browse the repository at this point in the history

  2. try to make tests run

    @anakin87
    anakin87 committed Nov 13, 2022
    Configuration menu
    Copy the full SHA
    707a81b View commit details
    Browse the repository at this point in the history

  3. better docstrings; revert not running tests

    @anakin87
    anakin87 committed Nov 13, 2022
    Configuration menu
    Copy the full SHA
    ac67603 View commit details
    Browse the repository at this point in the history

Commits on Nov 14, 2022

  1. some suggestions from review

    @anakin87
    anakin87 committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    2381901 View commit details
    Browse the repository at this point in the history

  2. Merge remote-tracking branch 'upstream/main' into imds_support_for_bm25

    @anakin87
    anakin87 committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    2d830c9 View commit details
    Browse the repository at this point in the history

  3. rename elasticsearch retriever as bm25 in tests; try to test memory_bm25

    @anakin87
    anakin87 committed Nov 14, 2022
    Configuration menu
    Copy the full SHA
    34fedfc View commit details
    Browse the repository at this point in the history

Commits on Nov 15, 2022

  1. exclude tests with filters

    @anakin87
    anakin87 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    bbd9faa View commit details
    Browse the repository at this point in the history

  2. change elasticsearch to bm25 retriever in test_summarizer

    @anakin87
    anakin87 authored Nov 15, 2022
    Configuration menu
    Copy the full SHA
    b3b2668 View commit details
    Browse the repository at this point in the history

  3. merge; bm25_algorithm as a property

    @anakin87
    anakin87 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    be5969e View commit details
    Browse the repository at this point in the history

  4. Merge branch 'imds_support_for_bm25' of https://github.com/anakin87/h… 

    …aystack into imds_support_for_bm25
    @anakin87
    anakin87 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    47df196 View commit details
    Browse the repository at this point in the history

  5. add tests

    @anakin87
    anakin87 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    d408128 View commit details
    Browse the repository at this point in the history

  6. Merge branch 'main' into imds_support_for_bm25

    @anakin87
    anakin87 committed Nov 15, 2022
    Configuration menu
    Copy the full SHA
    de970e8 View commit details
    Browse the repository at this point in the history

Commits on Nov 17, 2022

  1. try to improve tests

    @anakin87
    anakin87 committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    2e06683 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into imds_support_for_bm25

    @anakin87
    anakin87 committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    1ee1544 View commit details
    Browse the repository at this point in the history

  3. better type hint

    @anakin87
    anakin87 committed Nov 17, 2022
    Configuration menu
    Copy the full SHA
    ba89540 View commit details
    Browse the repository at this point in the history

Commits on Nov 18, 2022

  1. Merge branch 'main' into imds_support_for_bm25

    @anakin87
    anakin87 committed Nov 18, 2022
    Configuration menu
    Copy the full SHA
    832ef82 View commit details
    Browse the repository at this point in the history

  2. adapt test_table_text_retriever_embedding

    @anakin87
    anakin87 committed Nov 18, 2022
    Configuration menu
    Copy the full SHA
    f64016e View commit details
    Browse the repository at this point in the history

Commits on Nov 21, 2022

  1. handle non-textual docs

    @anakin87
    anakin87 committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    99429f6 View commit details
    Browse the repository at this point in the history

  2. query only textual documents

    @anakin87
    anakin87 committed Nov 21, 2022
    Configuration menu
    Copy the full SHA
    aad1970 View commit details
    Browse the repository at this point in the history