[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -20,12 +20,12 @@ repos:
     - id: check-toml
 
   - repo: https://github.com/astral-sh/uv-pre-commit
-    rev: 0.8.22
+    rev: 0.10.10
     hooks:
       - id: uv-lock
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.12.12'
+    rev: 'v0.15.6'
     hooks:
     - id: ruff-check
       args: [--fix, --unsafe-fixes, --exit-non-zero-on-fix]
@@ -34,7 +34,7 @@ repos:
       types_or: [python, jupyter]
 
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.17.1
+    rev: v1.19.1
     hooks:
     - id: mypy
       entry: python3 -m mypy --config-file pyproject.toml
@@ -43,7 +43,7 @@ repos:
       exclude: "data"
 
   - repo: https://github.com/crate-ci/typos
-    rev: v1.37.1
+    rev: v1
     hooks:
       - id: typos
         exclude: ^data/

src/biothink/self_reflection/data_process/process_data.py

@@ -201,9 +201,11 @@ def process_dataset(dataset, remove_original_output=False):
     # First, filter out rows with unwanted tokens to avoid multiprocessing issues
     print("Filtering dataset to remove unwanted tokens...")
     filtered = dataset.filter(
-        lambda x: "[No Retrieval]" not in x.get("output", "")
-        and "[Continue to Use Evidence]" not in x.get("output", "")
-        and x.get("output", "").startswith("[Retrieval]"),
+        lambda x: (
+            "[No Retrieval]" not in x.get("output", "")
+            and "[Continue to Use Evidence]" not in x.get("output", "")
+            and x.get("output", "").startswith("[Retrieval]")
+        ),
         num_proc=4,
     )