* Parsers can now return any number of fields, and can access the whole item
* nit: change gpt-4o to gpt-4o-mini in tests
* feat: add verbose parameter for gleaning
* feat: add verbose parameter for gleaning
* fix: tokenizers should be wrapped in try catch
* fix: resort to eval if ast eval does not work
* docs: update docs to reflect new custom parsing API
Co-authored-by: redhog <redhog@users.noreply.github.com>
* Clustering (#84)
* nit: change gpt-4o to gpt-4o-mini in tests
* feat: add verbose parameter for gleaning
* feat: add verbose parameter for gleaning
* fix: tokenizers should be wrapped in try catch
* fix: resort to eval if ast eval does not work
* Merge staging to main (after parsers refactor) (#82)
* Parsers can now return any number of fields, and can access the whole item
* nit: change gpt-4o to gpt-4o-mini in tests
* feat: add verbose parameter for gleaning
* feat: add verbose parameter for gleaning
* fix: tokenizers should be wrapped in try catch
* fix: resort to eval if ast eval does not work
* docs: update docs to reflect new custom parsing API
---------
Co-authored-by: Egil <egil.moller@freecode.no>
* Added new clustering operation
* Reverse path
* Added docs for cluster operator
* Bugfix for docs formatting
* docs: add sample parameter (#87)
* Added new clustering operation
* Reverse path
* Added docs for cluster operator
* Bugfix for docs formatting
* add tests and link to doc
---------
Co-authored-by: Shreya Shankar <ss.shankar505@gmail.com>
Co-authored-by: Egil <egil.moller@freecode.no>
* fix: fixing params in test
---------
Co-authored-by: Egil <egil.moller@freecode.no>
Co-authored-by: redhog <redhog@users.noreply.github.com>
Co-authored-by: Egil Möller <redhog@redhog.org>
Shreya Shankar