Fix dependency issues leading to failed actions and remove unused code

.github/workflows/precommit_and_docs_build_check.yml

@@ -16,7 +16,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v5
         with:
-          python-version: '3.11'
+          python-version: "3.11"
           cache: pip
 
       - name: create venv and install dependencies
@@ -39,7 +39,7 @@ jobs:
       - name: Check docs build successfully
         # still run even if the pre-commit fails, so we
         # have the output on if the docs build succeeded or not
-        if: '!cancelled()'
+        if: "!cancelled()"
         run: |
           . /tmp/kazu-env/bin/activate
           make -C docs html

README.md

@@ -1,3 +1,4 @@
+
 ![Maturity level-1](https://img.shields.io/badge/Maturity%20Level-ML--2-green)
 
 <p align="center">

docs/conf.py

@@ -125,15 +125,13 @@
 
 intersphinx_mapping = {
     "transformers": ("https://huggingface.co/docs/transformers/main/en/", None),
-    "pytorch_lightning": ("https://lightning.ai/docs/pytorch/stable/", None),
     "torch": ("https://pytorch.org/docs/stable/", None),
     "numpy": ("https://numpy.org/doc/stable/", None),
     "pandas": ("https://pandas.pydata.org/docs/", None),
     "python": ("https://docs.python.org/3", None),
     "sklearn": ("https://scikit-learn.org/stable/", None),
     "diskcache": ("https://grantjenks.com/docs/diskcache/", None),
     "rdflib": ("https://rdflib.readthedocs.io/en/stable/", None),
-    "pymongo": ("https://pymongo.readthedocs.io/en/stable/", None),
     # pymongo includes bson
     "bson": ("https://pymongo.readthedocs.io/en/stable/", None),
     "requests": ("https://requests.readthedocs.io/en/latest/", None),
@@ -207,16 +205,12 @@ def linkcode_resolve(domain: str, info: dict[str, Any]) -> Union[str, None]:
     "transformers.tokenization_utils_fast.PreTrainedTokenizerFast": "transformers.PreTrainedTokenizerFast",
     "transformers.utils.generic.PaddingStrategy": "transformers.utils.PaddingStrategy",
     "lightning_fabric.plugins.io.checkpoint_io.CheckpointIO": "lightning.pytorch.plugins.io.CheckpointIO",
-    "pytorch_lightning.core.module.LightningModule": "lightning.pytorch.core.LightningModule",
-    "pytorch_lightning.trainer.trainer.Trainer": "lightning.pytorch.trainer.trainer.Trainer",
     "urllib3.util.retry.Retry": "urllib3.util.Retry",
     "scipy.sparse._csr.csr_matrix": "scipy.sparse.csr_matrix",
 }
 
 
 nitpick_ignore = [
-    # this doesn't exist anymore in lightning 2.0, it becomes on_validation_epoch_end, and there's some migration work for changing to it
-    ("py:meth", "pytorch_lightning.core.LightningModule.validation_epoch_end"),
     # this doesn't appear to have an entry in the transformers docs for some reason.
     ("py:class", "transformers.models.bert.modeling_bert.BertPreTrainedModel"),
     # the kazu.utils.grouping.Key TypeVar tries to generate this automatically.

kazu/conf/config.yaml

@@ -6,7 +6,7 @@ defaults:
       - ot_molecule
       - ot_bio_proc
       - ot_phenotype
-#      - ot_measurement # curations are currently low quality
+      #      - ot_measurement # curations are currently low quality
       - ot_medical_proc
       - cellosaurus
       - chembl
@@ -26,9 +26,7 @@ defaults:
   - SpacyNerStep: default
   - TransformersModelForTokenClassificationNerStep: default
   - DictionaryEntityLinkingStep: default
-  - SapBertTraining: default
   - Pipeline: default
-  - DistillationTraining: default
   - OpsinStep: default
   - SethStep: default
   - SynonymGeneration: default
@@ -50,7 +48,7 @@ defaults:
   - global_actions: default
   - GLiNERStep: default
   - autocurator: default
-  - _self_  # see https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order/
+  - _self_ # see https://hydra.cc/docs/1.2/upgrades/1.0_to_1.1/default_composition_order/
 
 # we set certain env vars here for things that are statically initialised
 hydra: