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

[ML] Apply windowing and chunking to long documents #104363

Merged
merged 24 commits into from
Feb 1, 2024
Merged

[ML] Apply windowing and chunking to long documents #104363

merged 24 commits into from
Feb 1, 2024

Commits on Jan 15, 2024

  1. Chunk text expansion and embedding results

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    3ba84bd View commit details
    Browse the repository at this point in the history

  2. Add windowing options

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    07237e6 View commit details
    Browse the repository at this point in the history

  3. Update docs/changelog/104363.yaml

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    8c077ec View commit details
    Browse the repository at this point in the history

  4. timout

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    f2657a9 View commit details
    Browse the repository at this point in the history

  5. oops

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    44caf21 View commit details
    Browse the repository at this point in the history

  6. fix operatorprivilegesit

    @davidkyle
    davidkyle committed Jan 15, 2024
    Configuration menu
    Copy the full SHA
    9690911 View commit details
    Browse the repository at this point in the history

Commits on Jan 18, 2024

  1. Address review comments

    @davidkyle
    davidkyle committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    f567e87 View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into chunking 

    # Conflicts:
#	server/src/main/java/org/elasticsearch/TransportVersions.java
    @davidkyle
    davidkyle committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    45f275a View commit details
    Browse the repository at this point in the history

  3. fix test

    @davidkyle
    davidkyle committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    cc752e3 View commit details
    Browse the repository at this point in the history

  4. Default span value

    @davidkyle
    davidkyle committed Jan 18, 2024
    Configuration menu
    Copy the full SHA
    aaed765 View commit details
    Browse the repository at this point in the history

Commits on Jan 25, 2024

  1. Merge branch 'main' into chunking 

    # Conflicts:
#	server/src/main/java/org/elasticsearch/TransportVersions.java
    @davidkyle
    davidkyle committed Jan 25, 2024
    Configuration menu
    Copy the full SHA
    ef277e6 View commit details
    Browse the repository at this point in the history

Commits on Jan 31, 2024

  1. Add chunked inference method to services

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    27e277d View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into chunking 

    # Conflicts:
#	server/src/main/java/org/elasticsearch/TransportVersions.java
    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    b92a2cf View commit details
    Browse the repository at this point in the history

  3. fix compilation after merge

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    4ab95be View commit details
    Browse the repository at this point in the history

  4. Remove chunked inference action

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    f0037a9 View commit details
    Browse the repository at this point in the history

  5. Add input type to chunk method

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    20fbd93 View commit details
    Browse the repository at this point in the history

  6. more tests for tokenisation update

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    1a3cdf9 View commit details
    Browse the repository at this point in the history

  7. validation on window size

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    2a2bcaa View commit details
    Browse the repository at this point in the history

  8. fix compilation

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    be4a8cd View commit details
    Browse the repository at this point in the history

  9. Fix operator privileges test

    @davidkyle
    davidkyle committed Jan 31, 2024
    Configuration menu
    Copy the full SHA
    3fde8b2 View commit details
    Browse the repository at this point in the history

Commits on Feb 1, 2024

  1. address review feedback

    @davidkyle
    davidkyle committed Feb 1, 2024
    Configuration menu
    Copy the full SHA
    2c7736f View commit details
    Browse the repository at this point in the history

  2. Merge branch 'main' into chunking 

    # Conflicts:
#	server/src/main/java/org/elasticsearch/TransportVersions.java
    @davidkyle
    davidkyle committed Feb 1, 2024
    Configuration menu
    Copy the full SHA
    9a6d644 View commit details
    Browse the repository at this point in the history

  3. revert accidental serialisation change

    @davidkyle
    davidkyle committed Feb 1, 2024
    Configuration menu
    Copy the full SHA
    40173a1 View commit details
    Browse the repository at this point in the history

  4. Merge branch 'main' into chunking 

    # Conflicts:
#	server/src/main/java/org/elasticsearch/TransportVersions.java
    @davidkyle
    davidkyle committed Feb 1, 2024
    Configuration menu
    Copy the full SHA
    d51ed8b View commit details
    Browse the repository at this point in the history