merge clear_ram and dump_modules into keep_in_ram

Author: voorhs

autointent/configs/_optimization.py

@@ -28,10 +28,8 @@ class LoggingConfig(BaseModel):
     """Path to the directory with different runs."""
     run_name: str = Field(default_factory=get_run_name)
     """Name of the run. If None, a random name will be generated"""
-    dump_modules: bool = False
-    """Whether to dump the modules or not"""
-    clear_ram: bool = False
-    """Whether to clear the RAM after dumping the modules"""
+    keep_in_ram: bool = True
+    """Whether to store modules in RAM or dump them into file system."""
     report_to: list[str] | None = None
     """List of callbacks to report to. If None, no callbacks will be used"""
 

autointent/context/_context.py

@@ -208,7 +208,7 @@ def get_dump_dir(self) -> Path | None:
 
         :return: Path to the dump directory or None if dumping is disabled.
         """
-        if self.logging_config.dump_modules:
+        if not self.logging_config.keep_in_ram:
             return self.logging_config.dump_dir
         return None
 
@@ -234,7 +234,7 @@ def is_ram_to_clear(self) -> bool:
 
         :return: True if RAM clearing is enabled, False otherwise.
         """
-        return self.logging_config.clear_ram
+        return not self.logging_config.keep_in_ram
 
     def has_saved_modules(self) -> bool:
         """

tests/callback/test_callback.py

@@ -83,7 +83,7 @@ def test_pipeline_callbacks(dataset):
     pipeline_optimizer = Pipeline.from_search_space(search_space)
     context = Context()
     context.configure_vector_index(VectorIndexConfig(save_db=True))
-    context.configure_logging(LoggingConfig(run_name="dummy_run_name", project_dir=project_dir, dump_modules=False))
+    context.configure_logging(LoggingConfig(run_name="dummy_run_name", project_dir=project_dir, keep_in_ram=True))
     context.callback_handler = CallbackHandler([DummyCallback])
     context.set_dataset(dataset)
 

tests/nodes/conftest.py

@@ -82,7 +82,7 @@ def get_context(multilabel):
     if multilabel:
         dataset = dataset.to_multilabel()
     res.set_dataset(dataset)
-    res.configure_logging(LoggingConfig(project_dir=project_dir, dump_modules=True))
+    res.configure_logging(LoggingConfig(project_dir=project_dir, keep_in_ram=False))
     res.configure_vector_index(VectorIndexConfig(), EmbedderConfig(device="cpu"))
     res.configure_cross_encoder(CrossEncoderConfig())
     return res

tests/pipeline/test_inference.py

@@ -15,7 +15,7 @@ def test_inference_config(dataset, task_type):
 
     pipeline_optimizer = Pipeline.from_search_space(search_space)
 
-    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, dump_modules=True, clear_ram=True))
+    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, keep_in_ram=False))
     pipeline_optimizer.set_config(VectorIndexConfig(save_db=True))
     pipeline_optimizer.set_config(EmbedderConfig(batch_size=16, max_length=32, device="cpu"))
     pipeline_optimizer.set_config(CrossEncoderConfig())
@@ -47,7 +47,7 @@ def test_inference_context(dataset, task_type):
 
     pipeline = Pipeline.from_search_space(search_space)
 
-    pipeline.set_config(LoggingConfig(project_dir=project_dir, dump_modules=False, clear_ram=False))
+    pipeline.set_config(LoggingConfig(project_dir=project_dir, keep_in_ram=True))
     pipeline.set_config(VectorIndexConfig(save_db=True))
     pipeline.set_config(EmbedderConfig(batch_size=16, max_length=32, device="cpu"))
 

tests/pipeline/test_optimization.py

@@ -24,7 +24,7 @@ def test_no_context_optimization(dataset, task_type):
 
     pipeline_optimizer = Pipeline.from_search_space(search_space)
 
-    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, dump_modules=False))
+    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, keep_in_ram=True))
     pipeline_optimizer.set_config(VectorIndexConfig())
     pipeline_optimizer.set_config(EmbedderConfig(batch_size=16, max_length=32, device="cpu"))
 
@@ -45,7 +45,7 @@ def test_save_db(dataset, task_type):
 
     pipeline_optimizer = Pipeline.from_search_space(search_space)
 
-    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, dump_modules=False))
+    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, keep_in_ram=True))
     pipeline_optimizer.set_config(VectorIndexConfig(save_db=True))
     pipeline_optimizer.set_config(EmbedderConfig(batch_size=16, max_length=32, device="cpu"))
 
@@ -66,7 +66,7 @@ def test_dump_modules(dataset, task_type):
 
     pipeline_optimizer = Pipeline.from_search_space(search_space)
 
-    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, dump_modules=True))
+    pipeline_optimizer.set_config(LoggingConfig(project_dir=project_dir, keep_in_ram=False))
     pipeline_optimizer.set_config(VectorIndexConfig())
     pipeline_optimizer.set_config(EmbedderConfig(batch_size=16, max_length=32, device="cpu"))
 

user_guides/advanced/04_reporting.py

@@ -74,7 +74,7 @@
 from pathlib import Path
 
 log_config = LoggingConfig(
-    run_name="test_tensorboard", report_to=["tensorboard"], dirpath=Path("test_tensorboard"), dump_modules=False
+    run_name="test_tensorboard", report_to=["tensorboard"], dirpath=Path("test_tensorboard"), keep_in_ram=True
 )
 
 pipeline_optimizer.set_config(log_config)

user_guides/basic_usage/03_automl.py

@@ -124,7 +124,7 @@
 from pathlib import Path
 from autointent.configs import LoggingConfig
 
-logging_config = LoggingConfig(project_dir=Path.cwd() / "runs", dump_modules=False, clear_ram=False)
+logging_config = LoggingConfig(project_dir=Path.cwd() / "runs", keep_in_ram=True)
 custom_pipeline.set_config(logging_config)
 
 # %% [markdown]

user_guides/basic_usage/04_inference.py

@@ -67,7 +67,7 @@
 # %%
 from autointent.configs import LoggingConfig
 
-logging_config = LoggingConfig(dump_modules=True, clear_ram=True)
+logging_config = LoggingConfig(keep_in_ram=False)
 
 # %% [markdown]
 """
@@ -82,7 +82,7 @@
 
 dataset = Dataset.from_hub("AutoIntent/clinc150_subset")
 pipeline = Pipeline.from_search_space(search_space)
-pipeline.set_config(LoggingConfig(dump_modules=True, clear_ram=True))
+pipeline.set_config(LoggingConfig(keep_in_ram=False))
 pipeline.set_config(VectorIndexConfig(save_db=True))
 
 # %% [markdown]