[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Author: pre-commit-ci[bot]

backend/src/app/celery/background_jobs/__init__.py

@@ -103,9 +103,9 @@ def execute_text_preprocessing_pipeline_apply_async(
         execute_text_preprocessing_pipeline_task,
     )
 
-    assert isinstance(
-        execute_text_preprocessing_pipeline_task, Task
-    ), "Not a Celery Task"
+    assert isinstance(execute_text_preprocessing_pipeline_task, Task), (
+        "Not a Celery Task"
+    )
 
     for cargo in cargos:
         execute_text_preprocessing_pipeline_task.apply_async(kwargs={"cargo": cargo})
@@ -118,9 +118,9 @@ def execute_image_preprocessing_pipeline_apply_async(
         execute_image_preprocessing_pipeline_task,
     )
 
-    assert isinstance(
-        execute_image_preprocessing_pipeline_task, Task
-    ), "Not a Celery Task"
+    assert isinstance(execute_image_preprocessing_pipeline_task, Task), (
+        "Not a Celery Task"
+    )
 
     for cargo in cargos:
         execute_image_preprocessing_pipeline_task.apply_async(kwargs={"cargo": cargo})
@@ -133,9 +133,9 @@ def execute_audio_preprocessing_pipeline_apply_async(
         execute_audio_preprocessing_pipeline_task,
     )
 
-    assert isinstance(
-        execute_audio_preprocessing_pipeline_task, Task
-    ), "Not a Celery Task"
+    assert isinstance(execute_audio_preprocessing_pipeline_task, Task), (
+        "Not a Celery Task"
+    )
 
     for cargo in cargos:
         execute_audio_preprocessing_pipeline_task.apply_async(kwargs={"cargo": cargo})
@@ -148,9 +148,9 @@ def execute_video_preprocessing_pipeline_apply_async(
         execute_video_preprocessing_pipeline_task,
     )
 
-    assert isinstance(
-        execute_video_preprocessing_pipeline_task, Task
-    ), "Not a Celery Task"
+    assert isinstance(execute_video_preprocessing_pipeline_task, Task), (
+        "Not a Celery Task"
+    )
 
     for cargo in cargos:
         execute_video_preprocessing_pipeline_task.apply_async(kwargs={"cargo": cargo})

backend/src/app/core/analysis/cota/pipeline/pipeline.py

@@ -82,8 +82,7 @@ def execute(self, job: COTARefinementJobRead) -> COTARefinementJobRead:
         stop_t = time.perf_counter()
 
         logger.info(
-            f"Executing the COTARefinementPipeline took"
-            f" {stop_t - start_t:0.4f} seconds"
+            f"Executing the COTARefinementPipeline took {stop_t - start_t:0.4f} seconds"
         )
 
         return job
@@ -163,7 +162,7 @@ def _run_step(self, cargo: Cargo, step: PipelineStep) -> Cargo:
                     logger.error(msg)
                     raise ValueError(msg)
 
-            logger.info((f"Running: {step} for " f"COTARefinementJob {cargo.job.id} "))
+            logger.info((f"Running: {step} for COTARefinementJob {cargo.job.id} "))
             cargo = self._update_cota_job(
                 cargo=cargo,
                 current_step_name=step.name,

backend/src/app/core/data/crud/memo.py

@@ -138,9 +138,9 @@ def create_for_attached_object(
                 raise NotImplementedError(
                     f"Unknown AttachedObjectType: {attached_object_type}"
                 )
-        assert (
-            oh_create_dto is not None
-        ), f"Unknown AttachedObjectType: {attached_object_type}"
+        assert oh_create_dto is not None, (
+            f"Unknown AttachedObjectType: {attached_object_type}"
+        )
 
         # create an ObjectHandle for the attached object
         oh_db_obj = crud_object_handle.create(db=db, create_dto=oh_create_dto)

backend/src/app/core/data/dto/search.py

@@ -70,7 +70,7 @@ class ElasticSearchMemoRead(BaseModel):
         description="The ID of the Object the Memo is attached to"
     )
     attached_object_type: Optional[AttachedObjectType] = Field(
-        description=("The type of the Object the Memo is " "attached to")
+        description=("The type of the Object the Memo is attached to")
     )
     updated: Optional[datetime] = Field(
         description="The created date of the Memo", default=datetime.now()

backend/src/app/core/data/llm/llm_service.py

@@ -448,12 +448,12 @@ def _llm_document_tagging(
         approach_parameters: ZeroShotParams,
         task_parameters: DocumentTaggingParams,
     ) -> LLMJobResult:
-        assert isinstance(
-            task_parameters, DocumentTaggingParams
-        ), "Wrong task parameters!"
-        assert isinstance(
-            approach_parameters, ZeroShotParams
-        ), "Wrong approach parameters!"
+        assert isinstance(task_parameters, DocumentTaggingParams), (
+            "Wrong task parameters!"
+        )
+        assert isinstance(approach_parameters, ZeroShotParams), (
+            "Wrong approach parameters!"
+        )
 
         msg = f"Started LLMJob - Document Tagging, num docs: {len(task_parameters.sdoc_ids)}"
         self._update_llm_job_description(
@@ -573,12 +573,12 @@ def _llm_metadata_extraction(
         approach_parameters: ZeroShotParams,
         task_parameters: MetadataExtractionParams,
     ) -> LLMJobResult:
-        assert isinstance(
-            task_parameters, MetadataExtractionParams
-        ), "Wrong task parameters!"
-        assert isinstance(
-            approach_parameters, ZeroShotParams
-        ), "Wrong approach parameters!"
+        assert isinstance(task_parameters, MetadataExtractionParams), (
+            "Wrong task parameters!"
+        )
+        assert isinstance(approach_parameters, ZeroShotParams), (
+            "Wrong approach parameters!"
+        )
 
         msg = f"Started LLMJob - Metadata Extraction, num docs: {len(task_parameters.sdoc_ids)}"
         self._update_llm_job_description(
@@ -721,9 +721,9 @@ def _llm_annotation(
         task_parameters: AnnotationParams,
     ) -> LLMJobResult:
         assert isinstance(task_parameters, AnnotationParams), "Wrong task parameters!"
-        assert isinstance(
-            approach_parameters, ZeroShotParams
-        ), "Wrong approach parameters!"
+        assert isinstance(approach_parameters, ZeroShotParams), (
+            "Wrong approach parameters!"
+        )
 
         msg = f"Started LLMJob - Annotation, num docs: {len(task_parameters.sdoc_ids)}"
         self._update_llm_job_description(
@@ -887,9 +887,9 @@ def _llm_sentence_annotation(
         approach_parameters: Union[ZeroShotParams, FewShotParams],
         task_parameters: SentenceAnnotationParams,
     ) -> LLMJobResult:
-        assert isinstance(
-            task_parameters, SentenceAnnotationParams
-        ), "Wrong task parameters!"
+        assert isinstance(task_parameters, SentenceAnnotationParams), (
+            "Wrong task parameters!"
+        )
         assert isinstance(approach_parameters, ZeroShotParams) or isinstance(
             approach_parameters, FewShotParams
         ), "Wrong approach parameters!"
@@ -1101,12 +1101,12 @@ def _ray_sentence_annotation(
         approach_parameters: ModelTrainingParams,
         task_parameters: SentenceAnnotationParams,
     ) -> LLMJobResult:
-        assert isinstance(
-            task_parameters, SentenceAnnotationParams
-        ), "Wrong task parameters!"
-        assert isinstance(
-            approach_parameters, ModelTrainingParams
-        ), "Wrong approach parameters!"
+        assert isinstance(task_parameters, SentenceAnnotationParams), (
+            "Wrong task parameters!"
+        )
+        assert isinstance(approach_parameters, ModelTrainingParams), (
+            "Wrong approach parameters!"
+        )
 
         msg = f"Started LLMJob - Sentence Annotation (RAY), num docs: {len(task_parameters.sdoc_ids)}"
         self._update_llm_job(

backend/src/app/core/data/llm/ollama_service.py

@@ -40,9 +40,9 @@ def __new__(cls, *args, **kwargs):
                 )
                 logger.info(f"Model {model} has been created successfully.")
             available_models = [x.model for x in ollamac.list()["models"]]
-            assert (
-                model in available_models
-            ), f"Model {model} is not available. Available models are: {available_models}"
+            assert model in available_models, (
+                f"Model {model} is not available. Available models are: {available_models}"
+            )
 
             cls.__model = model
             cls.__client = ollamac

backend/src/app/core/data/llm/prompts/sentence_annotation_prompt_builder.py

@@ -140,9 +140,9 @@ def _build_user_prompt_template(
 
             # check that there are at least 4 examples per code
             for code_id, annotations in code_id2sentence_annotations.items():
-                assert (
-                    len(annotations) >= sent_anno_conf.few_shot_threshold
-                ), f"Code {code_id} has less than {sent_anno_conf.few_shot_threshold} annotations!"
+                assert len(annotations) >= sent_anno_conf.few_shot_threshold, (
+                    f"Code {code_id} has less than {sent_anno_conf.few_shot_threshold} annotations!"
+                )
 
             # find corrsponding sdoc datas
             sdoc_ids = [sa.sdoc_id for sa in sentence_annotations]

backend/src/app/core/db/simsearch_service.py

@@ -71,9 +71,9 @@ def _encode_text(self, text: List[str], return_avg_emb: bool = False) -> np.ndar
     def _get_image_path_from_sdoc_id(self, sdoc_id: int) -> Path:
         with self.sqls.db_session() as db:
             sdoc = SourceDocumentRead.model_validate(crud_sdoc.read(db=db, id=sdoc_id))
-            assert (
-                sdoc.doctype == DocType.image
-            ), f"SourceDocument with {sdoc_id=} is not an image!"
+            assert sdoc.doctype == DocType.image, (
+                f"SourceDocument with {sdoc_id=} is not an image!"
+            )
         return self.repo.get_path_to_sdoc_file(sdoc=sdoc, raise_if_not_exists=True)
 
     def _encode_image(self, image_sdoc_id: int) -> np.ndarray:

backend/src/app/preprocessing/pipeline/preprocessing_pipeline.py

@@ -143,9 +143,7 @@ def __update_status_of_ppj(
     ) -> PipelineCargo:
         ppj_id = cargo.ppj_payload.prepro_job_id
         update_dto = PreprocessingJobUpdate(status=status)
-        logger.info(
-            f"Updating PreprocessingJob {ppj_id} " f"Status to {status.value}..."
-        )
+        logger.info(f"Updating PreprocessingJob {ppj_id} Status to {status.value}...")
         with self.sqls.db_session() as db:
             _ = crud_prepro_job.update(db=db, uuid=ppj_id, update_dto=update_dto)
         return cargo

backend/src/app/preprocessing/pipeline/steps/image/store_metadata_to_database.py

@@ -85,6 +85,6 @@ def store_metadata_to_database(cargo: PipelineCargo) -> PipelineCargo:
             db.rollback()
             raise e
         else:
-            logger.info(f"Persisted SourceDocument Metadata " f"for {ppid.filename}!")
+            logger.info(f"Persisted SourceDocument Metadata for {ppid.filename}!")
 
     return cargo

backend/src/app/preprocessing/pipeline/steps/image/write_ppid_to_database.py

@@ -121,9 +121,7 @@ def write_ppid_to_database(cargo: PipelineCargo) -> PipelineCargo:
             db.rollback()
             raise e
         else:
-            logger.info(
-                f"Persisted PreprocessingPipeline Results " f"for {ppid.filename}!"
-            )
+            logger.info(f"Persisted PreprocessingPipeline Results for {ppid.filename}!")
 
             cargo.data["sdoc_id"] = sdoc_db_obj.id
     return cargo

backend/src/app/preprocessing/pipeline/steps/text/write_pptd_to_database.py

@@ -233,9 +233,7 @@ def write_pptd_to_database(cargo: PipelineCargo) -> PipelineCargo:
             db.rollback()
             raise e
         else:
-            logger.info(
-                f"Persisted PreprocessingPipeline Results " f"for {pptd.filename}!"
-            )
+            logger.info(f"Persisted PreprocessingPipeline Results for {pptd.filename}!")
 
             cargo.data["sdoc_id"] = sdoc_db_obj.id
 

backend/src/app/preprocessing/pipeline/steps/video/write_ppvd_to_database.py

@@ -119,9 +119,7 @@ def write_ppvd_to_database(cargo: PipelineCargo) -> PipelineCargo:
             db.rollback()
             raise e
         else:
-            logger.info(
-                f"Persisted PreprocessingPipeline Results " f"for {ppvd.filename}!"
-            )
+            logger.info(f"Persisted PreprocessingPipeline Results for {ppvd.filename}!")
 
             cargo.data["sdoc_id"] = sdoc_db_obj.id
     return cargo

backend/src/app/preprocessing/preprocessing_service.py

@@ -206,8 +206,7 @@ def abort_preprocessing_job(self, ppj_id: str) -> PreprocessingJobRead:
         if ppj.status != BackgroundJobStatus.RUNNING:
             raise HTTPException(
                 detail=(
-                    f"Cannot abort PreprocessingJob {ppj_id} "
-                    "because it is not running!"
+                    f"Cannot abort PreprocessingJob {ppj_id} because it is not running!"
                 ),
                 status_code=400,
             )

backend/src/app/preprocessing/ray_model_worker/models/blip2.py

@@ -57,9 +57,9 @@ def __init__(self):
             device_map=device_map,
             torch_dtype=data_type,
         )
-        assert isinstance(
-            captioning_model, Blip2ForConditionalGeneration
-        ), "Failed to load captioning model"
+        assert isinstance(captioning_model, Blip2ForConditionalGeneration), (
+            "Failed to load captioning model"
+        )
 
         captioning_model.eval()
         self.data_type = data_type

backend/src/app/preprocessing/ray_model_worker/models/detr.py

@@ -23,15 +23,15 @@ class DETRModel:
     def __init__(self):
         logger.debug(f"Loading DetrFeatureExtractor {MODEL} ...")
         feature_extractor = DetrFeatureExtractor.from_pretrained(MODEL, device=DEVICE)
-        assert isinstance(
-            feature_extractor, DetrFeatureExtractor
-        ), "Failed to load feature extractor"
+        assert isinstance(feature_extractor, DetrFeatureExtractor), (
+            "Failed to load feature extractor"
+        )
 
         logger.debug(f"Loading DetrForObjectDetection {MODEL} ...")
         object_detection_model = DetrForObjectDetection.from_pretrained(MODEL)
-        assert isinstance(
-            object_detection_model, DetrForObjectDetection
-        ), "Failed to load object detection model"
+        assert isinstance(object_detection_model, DetrForObjectDetection), (
+            "Failed to load object detection model"
+        )
 
         object_detection_model.to(DEVICE)
         object_detection_model.eval()

backend/src/app/preprocessing/ray_model_worker/models/seqsenttagger.py

@@ -200,7 +200,9 @@ def collate_fn(batch):
         == len(new_padded_embeddings)
         == len(new_padded_labels)
         == len(new_mask)
-    ), f"Lengths must match: {len(padded_embeddings)}, {len(padded_labels)}, {len(mask)}, {len(new_padded_embeddings)}, {len(new_padded_labels)}, {len(new_mask)}"
+    ), (
+        f"Lengths must match: {len(padded_embeddings)}, {len(padded_labels)}, {len(mask)}, {len(new_padded_embeddings)}, {len(new_padded_labels)}, {len(new_mask)}"
+    )
 
     return (
         torch.tensor(new_padded_embeddings),

backend/src/main.py

@@ -274,9 +274,9 @@ def invalid_error_handler(_, exc: InvalidError):
 def main() -> None:
     # read port from config
     port = int(conf.api.port)
-    assert (
-        port is not None and isinstance(port, int) and port > 0
-    ), "The API port has to be a positive integer! E.g. 8081"
+    assert port is not None and isinstance(port, int) and port > 0, (
+        "The API port has to be a positive integer! E.g. 8081"
+    )
 
     is_debug = conf.api.production_mode == "0"
 

backend/src/test/api/endpoints/test_authentication.py

@@ -41,9 +41,9 @@ def test_authentication_required():
                 and dep.dependency.__qualname__ == "get_current_user"
             ]
 
-            assert (
-                len(auth_dep) == 1
-            ), f"route {route.methods} {route.path} is not protected by authentication"
+            assert len(auth_dep) == 1, (
+                f"route {route.methods} {route.path} is not protected by authentication"
+            )
         elif isinstance(route, starlette.routing.Route):
             # These routes are usually built into FastAPI, and
             # we expect them to not require authentication.

backend/src/test/app/core/data/crud/test_user_crud.py

@@ -13,7 +13,7 @@
 
 
 def test_create_delete_user(db: Session) -> None:
-    email = f'{"".join(random.choices(string.ascii_letters, k=15))}@gmail.com'
+    email = f"{''.join(random.choices(string.ascii_letters, k=15))}@gmail.com"
     first_name = "".join(random.choices(string.ascii_letters, k=15))
     last_name = "".join(random.choices(string.ascii_letters, k=15))
     password = "".join(random.choices(string.ascii_letters, k=15))
@@ -44,7 +44,7 @@ def test_create_delete_user(db: Session) -> None:
 
 
 def test_update_user(db: Session, user: UserORM) -> None:
-    email = f'{"".join(random.choices(string.ascii_letters, k=15))}@gmail.com'
+    email = f"{''.join(random.choices(string.ascii_letters, k=15))}@gmail.com"
     first_name = "".join(random.choices(string.ascii_letters, k=15))
     last_name = "".join(random.choices(string.ascii_letters, k=15))
     password = "".join(random.choices(string.ascii_letters, k=15))

backend/src/test/conftest.py

@@ -317,9 +317,9 @@ def create(self, upload_list: list, user: dict, project: dict):
             response = client.put(
                 f"/project/{project['id']}/sdoc", headers=user_headers, files=files
             )
-            assert (
-                response.status_code == 200
-            ), f"Failed to upload files. Response: {response}. Files: {files}"
+            assert response.status_code == 200, (
+                f"Failed to upload files. Response: {response}. Files: {files}"
+            )
             response = response.json()
             docs = {}
             for file in response["payloads"]: