Latest tooling and deps (#842)

.pre-commit-config.yaml

@@ -23,12 +23,12 @@ repos:
       - id: mixed-line-ending
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.9.1
+    rev: v0.9.4
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 24.10.0
+    rev: 25.1.0
     hooks:
       - id: black
   - repo: https://github.com/rbubley/mirrors-prettier
@@ -40,7 +40,7 @@ repos:
     hooks:
       - id: toml-sort-fix
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.3.0
+    rev: v2.4.1
     hooks:
       - id: codespell
         additional_dependencies: [".[toml]"]
@@ -55,15 +55,15 @@ repos:
     hooks:
       - id: check-mailmap
   - repo: https://github.com/henryiii/validate-pyproject-schema-store
-    rev: 2025.01.10
+    rev: 2025.02.03
     hooks:
       - id: validate-pyproject
   - repo: https://github.com/astral-sh/uv-pre-commit
-    rev: 0.4.30
+    rev: 0.5.26
     hooks:
       - id: uv-lock
   - repo: https://github.com/renovatebot/pre-commit-hooks
-    rev: 39.100.1
+    rev: 39.158.1
     hooks:
       - id: renovate-config-validator
         args: [--strict]

paperqa/agents/env.py

@@ -154,8 +154,8 @@ def make_clinical_trial_status(
 
 # SEE: https://regex101.com/r/L0L5MH/1
 CLINICAL_STATUS_SEARCH_REGEX_PATTERN: str = (
-    r"Status: Paper Count=(\d+) \| Relevant Papers=(\d+)(?:\s\|\sClinical Trial Count=(\d+)\s"
-    r"\|\sRelevant Clinical Trials=(\d+))?\s\|\sCurrent Evidence=(\d+)"
+    r"Status: Paper Count=(\d+) \| Relevant Papers=(\d+)(?:\s\|\sClinical Trial"
+    r" Count=(\d+)\s\|\sRelevant Clinical Trials=(\d+))?\s\|\sCurrent Evidence=(\d+)"
 )
 
 

paperqa/agents/tools.py

@@ -277,8 +277,8 @@ async def gather_evidence(self, question: str, state: EnvironmentState) -> str:
             )
 
         return (
-            f"Added {l1 - l0} pieces of evidence, {l1_relevant - l0_relevant} of which were"
-            f" relevant.{best_evidence}\n\n" + status
+            f"Added {l1 - l0} pieces of evidence, {l1_relevant - l0_relevant} of which"
+            f" were relevant.{best_evidence}\n\n" + status
         )
 
 
@@ -649,9 +649,9 @@ async def clinical_trials_search(self, query: str, state: EnvironmentState) -> s
         self.previous_searches[query] += self.search_count
         if error_message is None:
             return (
-                f"Found clinical trial search results from search {offset} to {offset + new_result_count}"
-                f" among {total_result_count} total results."
-                f" {state.status}"
+                f"Found clinical trial search results from search {offset} to"
+                f" {offset + new_result_count} among {total_result_count} total"
+                f" results. {state.status}"
             )
         return f"Error in clinical trial query syntax: {error_message}"
 

paperqa/llms.py

@@ -284,7 +284,10 @@ async def similarity_search(
 class QdrantVectorStore(VectorStore):
     client: Any = Field(
         default=None,
-        description="Instance of `qdrant_client.AsyncQdrantClient`. Defaults to an in-memory instance.",
+        description=(
+            "Instance of `qdrant_client.AsyncQdrantClient`. Defaults to an in-memory"
+            " instance."
+        ),
     )
     collection_name: str = Field(default_factory=lambda: f"paper-qa-{uuid.uuid4().hex}")
     vector_name: str | None = Field(default=None)
@@ -329,7 +332,8 @@ def validate_client(self):
 
         if self.client and not isinstance(self.client, AsyncQdrantClient):
             raise TypeError(
-                f"'client' should be an instance of AsyncQdrantClient. Got `{type(self.client)}`"
+                "'client' should be an instance of AsyncQdrantClient. Got"
+                f" `{type(self.client)}`"
             )
 
         if not self.client:

paperqa/settings.py

@@ -484,8 +484,9 @@ class AgentSettings(BaseModel):
     agent_evidence_n: int = Field(
         default=1,
         ge=1,
-        description="Top n ranked evidences shown to the "
-        "agent after the GatherEvidence tool.",
+        description=(
+            "Top n ranked evidences shown to the agent after the GatherEvidence tool."
+        ),
     )
     timeout: float = Field(
         default=500.0,

paperqa/sources/clinical_trials.py

@@ -191,13 +191,19 @@ def parse_clinical_trial(json_data: dict[str, Any]) -> str:
         "=" * 25,
         f"NCT Number: {identification.get('nctId', 'Not provided')}",
         f"Title: {identification.get('briefTitle', 'Not provided')}",
-        f"Organization: {identification.get('organization', {}).get('fullName', 'Not provided')}",
+        (
+            "Organization:"
+            f" {identification.get('organization', {}).get('fullName', 'Not provided')}"
+        ),
         # Status Information
         "\nSTUDY STATUS",
         "=" * 13,
         f"Overall Status: {status.get('overallStatus', 'Not provided')}",
         f"Start Date: {status.get('startDateStruct', {}).get('date', 'Not provided')}",
-        f"Completion Date: {status.get('completionDateStruct', {}).get('date', 'Not provided')}",
+        (
+            "Completion Date:"
+            f" {status.get('completionDateStruct', {}).get('date', 'Not provided')}"
+        ),
         # Study Description
         "\nSTUDY DESCRIPTION",
         "=" * 17,
@@ -207,7 +213,10 @@ def parse_clinical_trial(json_data: dict[str, Any]) -> str:
         "=" * 13,
         f"Study Type: {design.get('studyType', 'Not provided')}",
         f"Phase: {', '.join(design.get('phases', ['Not provided']))}",
-        f"Enrollment: {design.get('enrollmentInfo', {}).get('count', 'Not provided')} participants",
+        (
+            "Enrollment:"
+            f" {design.get('enrollmentInfo', {}).get('count', 'Not provided')} participants"
+        ),
         # Eligibility
         "\nELIGIBILITY CRITERIA",
         "=" * 19,

paperqa/types.py

@@ -234,7 +234,8 @@ def filter_content_for_user(self) -> None:
 class Answer(PQASession):
     def __init__(self, *args, **kwargs):
         warnings.warn(
-            "The 'Answer' class is deprecated and will be removed in future versions. Use 'PQASession' instead.",
+            "The 'Answer' class is deprecated and will be removed in future versions."
+            " Use 'PQASession' instead.",
             DeprecationWarning,
             stacklevel=2,
         )

paperqa/utils.py

@@ -501,7 +501,9 @@ def extract_thought(content: str | None) -> str:
     "dataset": "misc",  # No direct equivalent, so 'misc' is used
     "component": "misc",  # No direct equivalent, so 'misc' is used
     "report": "techreport",
-    "report-series": "techreport",  # 'series' implies multiple tech reports, but each is still a 'techreport'
+    "report-series": (  # 'series' implies multiple tech reports, but each is still a 'techreport'
+        "techreport"
+    ),
     "standard": "misc",  # No direct equivalent, so 'misc' is used
     "standard-series": "misc",  # No direct equivalent, so 'misc' is used
     "edited-book": "book",  # Edited books are considered books in BibTeX
@@ -514,7 +516,9 @@ def extract_thought(content: str | None) -> str:
     "book-section": "inbook",  # Sections in books can be considered as 'inbook'
     "book-part": "inbook",  # Parts of books can be considered as 'inbook'
     "book-track": "inbook",  # Tracks in books can be considered as 'inbook'
-    "reference-entry": "inbook",  # Entries in reference books can be considered as 'inbook'
+    "reference-entry": (  # Entries in reference books can be considered as 'inbook'
+        "inbook"
+    ),
     "dissertation": "phdthesis",  # Dissertations are usually PhD thesis
     "posted-content": "misc",  # No direct equivalent, so 'misc' is used
     "peer-review": "misc",  # No direct equivalent, so 'misc' is used

tests/test_clients.py

@@ -376,8 +376,9 @@ async def test_s2_only_fields_filtering() -> None:
         assert s2_details
         assert s2_details.authors, "Authors should be populated"
         assert set(s2_details.other["client_source"]) == {"semantic_scholar"}
-        assert s2_details.citation == (
-            "Andrés M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D."
+        assert (
+            s2_details.citation
+            == "Andrés M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D."
             " White, and P. Schwaller. Augmenting large language models with chemistry"
             " tools. ArXiv, Unknown year. URL:"
             " https://doi.org/10.48550/arxiv.2304.05376,"
@@ -429,7 +430,8 @@ async def test_crossref_journalquality_fields_filtering() -> None:
         )
         nejm_crossref_details = await crossref_client.query(
             title=(
-                "Beta-Blocker Interruption or Continuation after Myocardial Infarction"  # codespell:ignore
+                "Beta-Blocker Interruption or Continuation after Myocardial"
+                " Infarction"  # codespell:ignore
             ),
             fields=["title", "doi", "authors", "journal"],
         )

tests/test_configs.py

@@ -174,6 +174,7 @@ def test_matches_filter_criteria(doc_class, doc_data, filter_criteria, expected_
 def test_citation_prompt_current_year():
     expected_year_text = f"the current year is {get_year()}"
 
-    assert (
-        expected_year_text in citation_prompt
-    ), f"Citation prompt should contain '{expected_year_text}' but got: {citation_prompt}"
+    assert expected_year_text in citation_prompt, (
+        f"Citation prompt should contain '{expected_year_text}' but got:"
+        f" {citation_prompt}"
+    )