synapse-sdk 1.0.0a53__py3-none-any.whl → 1.0.0a55__py3-none-any.whl

synapse_sdk/clients/backend/__init__.py

@@ -1,6 +1,6 @@
 from synapse_sdk.clients.backend.annotation import AnnotationClientMixin
 from synapse_sdk.clients.backend.core import CoreClientMixin
-from synapse_sdk.clients.backend.data_collection import DataCollectionClientMixin
+from synapse_sdk.clients.backend.dataset import DatasetClientMixin
 from synapse_sdk.clients.backend.hitl import HITLClientMixin
 from synapse_sdk.clients.backend.integration import IntegrationClientMixin
 from synapse_sdk.clients.backend.ml import MLClientMixin
@@ -9,7 +9,7 @@ from synapse_sdk.clients.backend.ml import MLClientMixin
 class BackendClient(
     AnnotationClientMixin,
     CoreClientMixin,
-    DataCollectionClientMixin,
+    DatasetClientMixin,
     IntegrationClientMixin,
     MLClientMixin,
     HITLClientMixin,

synapse_sdk/clients/backend/{data_collection.py → dataset.py}

@@ -8,13 +8,13 @@ from synapse_sdk.clients.base import BaseClient
 from synapse_sdk.clients.utils import get_batched_list
 
 
-class DataCollectionClientMixin(BaseClient):
-    def list_data_collection(self):
+class DatasetClientMixin(BaseClient):
+    def list_dataset(self):
         path = 'data_collections/'
         return self._list(path)
 
-    def get_data_collection(self, data_collection_id):
-        """Get data_collection from synapse-backend.
+    def get_dataset(self, data_collection_id):
+        """Get dataset from synapse-backend.
 
         Args:
             data_collection_id: The data_collection id to get.
@@ -40,19 +40,19 @@ class DataCollectionClientMixin(BaseClient):
         path = 'data_units/'
         return self._post(path, data=data)
 
-    def upload_data_collection(
+    def upload_dataset(
         self,
-        data_collection_id: int,
-        data_collection: Dict,
+        dataset_id: int,
+        dataset: Dict,
         project_id: Optional[int] = None,
         batch_size: int = 1000,
         process_pool: int = 10,
     ):
-        """Upload data_collection to synapse-backend.
+        """Upload dataset to synapse-backend.
 
         Args:
-            data_collection_id: The data_collection id to upload the data to.
-            data_collection: The data_collection to upload.
+            dataset_id: The dataset id to upload the data to.
+            dataset: The dataset to upload.
                 * structure:
                     - files: The files to upload. (key: file name, value: file pathlib object)
                     - meta: The meta data to upload.
@@ -60,14 +60,14 @@ class DataCollectionClientMixin(BaseClient):
             batch_size: The batch size to upload the data.
             process_pool: The process pool to upload the data.
         """
-        # TODO validate data_collection with schema
+        # TODO validate dataset with schema
 
-        params = [(data, data_collection_id) for data in data_collection]
+        params = [(data, dataset_id) for data in dataset]
 
         with Pool(processes=process_pool) as pool:
-            data_collection = pool.starmap(self.upload_data_file, tqdm(params))
+            dataset = pool.starmap(self.upload_data_file, tqdm(params))
 
-        batches = get_batched_list(data_collection, batch_size)
+        batches = get_batched_list(dataset, batch_size)
 
         for batch in tqdm(batches):
             data_units = self.create_data_units(batch)
@@ -90,7 +90,7 @@ class DataCollectionClientMixin(BaseClient):
                 * structure:
                     - files: The files to upload. (key: file name, value: file pathlib object)
                     - meta: The meta data to upload.
-            data_collection_id: The data_collection id to upload the data to.
+            data_collection_id: The dataset id to upload the data to.
 
         Returns:
             Dict: The result of the upload.

synapse_sdk/clients/ray/serve.py

@@ -8,6 +8,7 @@ class ServeClientMixin(BaseClient):
         response = self._get(path, params=params)
         for key, item in response['applications'].items():
             response['applications'][key]['deployments'] = list(item['deployments'].values())
+            response['applications'][key]['route_prefix'] = item['route_prefix']
         return list(response['applications'].values())
 
     def get_serve_application(self, pk, params=None):
@@ -15,6 +16,7 @@ class ServeClientMixin(BaseClient):
         response = self._get(path, params=params)
         try:
             response['applications'][pk]['deployments'] = list(response['applications'][pk]['deployments'].values())
+            response['applications'][pk]['route_prefix'] = response['applications'][pk]['route_prefix']
             return response['applications'][pk]
         except KeyError:
             raise ClientError(404, 'Serve Application Not Found')

synapse_sdk/plugins/categories/export/actions/export.py

@@ -27,13 +27,6 @@ class ExportRun(Run):
         error: str | None = None
         created: str
 
-    class MetricsRecord(BaseModel):
-        """Metrics record model."""
-
-        stand_by: int
-        failed: int
-        success: int
-
     def log_file(
         self, log_type: str, target_id: int, data_file_info: dict, status: ExportStatus, error: str | None = None
     ):
@@ -58,16 +51,6 @@ class ExportRun(Run):
             ).model_dump(),
         )
 
-    def log_metrics(self, record: MetricsRecord, category: str):
-        """Log export metrics.
-
-        Args:
-            record (MetricsRecord): The metrics record to log.
-            category (str): The category of the metrics.
-        """
-        record = self.MetricsRecord.model_validate(record)
-        self.set_metrics(value=record.dict(), category=category)
-
     def export_log_json_file(
         self,
         target_id: int,
@@ -280,7 +263,6 @@ class ExportAction(Action):
             'proportion': 100,
         }
     }
-    metrics_categories = {'data_file', 'original_file'}
 
     def get_filtered_results(self, filters, handler):
         """Get filtered target results."""

synapse_sdk/plugins/categories/export/templates/plugin/export.py

@@ -42,8 +42,6 @@ def export(run, export_items, path_root, **params):
     origin_files_output_path.mkdir(parents=True, exist_ok=True)
 
     total = params['count']
-    original_file_metrics_record = run.MetricsRecord(stand_by=total, success=0, failed=0)
-    data_file_metrics_record = run.MetricsRecord(stand_by=total, success=0, failed=0)
     # progress init
     run.set_progress(0, total, category='dataset_conversion')
     for no, export_item in enumerate(export_items, start=1):
@@ -58,30 +56,12 @@ def export(run, export_items, path_root, **params):
         if save_original_file_flag:
             if no == 1:
                 run.log_message('Saving original file.')
-            original_status = save_original_file(run, final_data, origin_files_output_path, errors_original_file_list)
-
-            original_file_metrics_record.stand_by -= 1
-            if original_status == ExportStatus.FAILED:
-                original_file_metrics_record.failed += 1
-                continue
-            else:
-                original_file_metrics_record.success += 1
-
-        run.log_metrics(record=original_file_metrics_record, category='original_file')
+            save_original_file(run, final_data, origin_files_output_path, errors_original_file_list)
 
         # Extract data as JSON files
         if no == 1:
             run.log_message('Saving json file.')
-        data_status = save_as_json(run, final_data, json_output_path, errors_json_file_list)
-
-        data_file_metrics_record.stand_by -= 1
-        if data_status == ExportStatus.FAILED:
-            data_file_metrics_record.failed += 1
-            continue
-        else:
-            data_file_metrics_record.success += 1
-
-        run.log_metrics(record=data_file_metrics_record, category='data_file')
+        save_as_json(run, final_data, json_output_path, errors_json_file_list)
 
     run.end_log()
 
@@ -146,7 +126,6 @@ def save_original_file(run, result, base_path, error_file_list):
         status = ExportStatus.FAILED
 
     run.export_log_original_file(result['id'], file_info, status, error_msg)
-    return status
 
 
 def save_as_json(run, result, base_path, error_file_list):
@@ -173,4 +152,3 @@ def save_as_json(run, result, base_path, error_file_list):
         status = ExportStatus.FAILED
 
     run.export_log_json_file(result['id'], file_info, status, error_msg)
-    return status

synapse_sdk/plugins/categories/upload/actions/upload.py

@@ -1,6 +1,8 @@
 import json
+import re
 from datetime import datetime
 from enum import Enum
+from pathlib import Path
 from typing import Annotated, Dict, List
 
 from pydantic import AfterValidator, BaseModel, field_validator
@@ -105,6 +107,8 @@ class UploadParams(BaseModel):
     storage: int
     collection: int
     project: int | None
+    is_generate_tasks: bool = False
+    is_generate_ground_truths: bool = False
 
     @field_validator('storage', mode='before')
     @classmethod
@@ -129,7 +133,7 @@ class UploadParams(BaseModel):
         action = info.context['action']
         client = action.client
         try:
-            client.get_data_collection(value)
+            client.get_dataset(value)
         except ClientError:
             raise PydanticCustomError('client_error', _('Error occurred while checking collection exists.'))
         return value
@@ -163,6 +167,8 @@ class UploadAction(Action):
         analyze_collection: The progress category for the analyze collection process.
         data_file_upload: The progress category for the upload process.
         generate_data_units: The progress category for the generate data units process.
+        generate_tasks: The progress category for the generate tasks process.
+        generate_ground_truths: The progress category for the generate ground truths process.
     """
 
     name = 'upload'
@@ -171,19 +177,51 @@ class UploadAction(Action):
     run_class = UploadRun
     progress_categories = {
         'analyze_collection': {
-            'proportion': 10,
+            'proportion': 0,
         },
         'upload_data_files': {
-            'proportion': 50,
+            'proportion': 0,
         },
         'generate_data_units': {
-            'proportion': 40,
+            'proportion': 0,
+        },
+        'generate_tasks': {
+            'proportion': 0,
+        },
+        'generate_ground_truths': {
+            'proportion': 0,
         },
     }
 
-    def get_uploader(self, path):
+    def __init__(self, *args, **kwargs):
+        """Initialize UploadAction."""
+        super().__init__(*args, **kwargs)
+
+        # Setup progress categories ratio by options.
+        progress_ratios = {
+            'upload_only': (5, 60, 35, 0, 0),
+            'generate_tasks': (5, 45, 25, 25, 0),
+            'generate_ground_truths': (5, 35, 30, 15, 15),
+        }
+        options = self.config.get('options', {})
+        progress_categories = self.progress_categories
+        if options['allow_generate_tasks'] and not kwargs['params']['allow_generate_ground_truths']:
+            ratio_name = 'generate_tasks'
+        elif options['allow_generate_ground_truths'] and kwargs['params']['allow_generate_tasks']:
+            ratio_name = 'generate_ground_truths'
+        else:
+            ratio_name = 'upload_only'
+
+        assert len(progress_categories) == len(progress_ratios[ratio_name]), (
+            'Progress categories and ratios length mismatch.'
+        )
+        for i, category in enumerate(progress_categories):
+            progress_categories[category]['proportion'] = progress_ratios[ratio_name][i]
+        self.progress_categories = progress_categories
+
+    def get_uploader(self, path, file_specification, organized_files):
         """Get uploader from entrypoint."""
-        return self.entrypoint(self.run, path)
+        return self.entrypoint(self.run, path, file_specification, organized_files)
 
     def start(self) -> Dict:
         """Start upload process.
@@ -195,19 +233,23 @@ class UploadAction(Action):
         storage = self.client.get_storage(self.params['storage'])
         pathlib_cwd = get_pathlib(storage, self.params['path'])
 
-        # Initialize uploader.
-        uploader = self.get_uploader(pathlib_cwd)
-
         # Analyze Collection file specifications to determine the data structure for upload.
         file_specification_template = self._analyze_collection()
+        organized_files = self._organize_files(pathlib_cwd, file_specification_template)
+
+        # Initialize uploader.
+        uploader = self.get_uploader(pathlib_cwd, file_specification_template, organized_files)
 
         # Setup result dict.
         result = {}
 
-        # Organize data according to Collection file specification structure.
+        # Get organized files from the uploader (plugin developer's custom implementation)
+        # or use the default organization method if uploader doesn't provide valid files
         organized_files = uploader.handle_upload_files()
-        if not self._validate_organized_files(file_specification_template, organized_files):
-            self.run.log_message('Validate organized files failed.')
+
+        # Validate the organized files
+        if not self._validate_organized_files(organized_files, file_specification_template):
+            self.run.log_message('Validation failed.', context=Context.ERROR.value)
             self.run.end_log()
             return result
 
@@ -229,6 +271,26 @@ class UploadAction(Action):
         generated_data_units = self._generate_data_units(uploaded_files, upload_result_count)
         result['generated_data_units_count'] = len(generated_data_units)
 
+        # Setup task with uploaded synapse-backend data units.
+        if not len(generated_data_units):
+            self.run.log_message('No data units were generated.', context=Context.WARNING.value)
+            self.run.end_log()
+            return result
+
+        if self.config['options']['allow_generate_tasks'] and self.params['is_generate_tasks']:
+            generated_tasks = self._generate_tasks(generated_data_units)
+            result['generated_tasks_count'] = len(generated_tasks)
+        else:
+            self.run.log_message('Generating tasks process has passed.')
+
+        # Generate ground truths for the uploaded data.
+        # TODO: Need to add ground truths generation logic later.
+        if self.config['options']['allow_generate_ground_truths'] and self.params['is_generate_ground_truths']:
+            generated_ground_truths = self._generate_ground_truths()
+            result['generated_ground_truths_count'] = len(generated_ground_truths)
+        else:
+            self.run.log_message('Generating ground truths process has passed.')
+
         self.run.end_log()
         return result
 
@@ -244,18 +306,13 @@ class UploadAction(Action):
 
         client = self.run.client
         collection_id = self.params['collection']
-        collection = client.get_data_collection(collection_id)
+        collection = client.get_dataset(collection_id)
 
         # Finish progress
         self.run.set_progress(1, 1, category='analyze_collection')
 
         return collection['file_specifications']
 
-    def _validate_organized_files(self, file_specification_template: Dict, organized_files: List) -> bool:
-        """Validate organized files from Uploader."""
-        validator = FileSpecificationValidator(file_specification_template, organized_files)
-        return validator.validate()
-
     def _upload_files(self, organized_files, organized_files_count: int) -> List:
         """Upload files to synapse-backend.
 
@@ -313,3 +370,224 @@ class UploadAction(Action):
         self.run.set_progress(upload_result_count, upload_result_count, category='generate_data_units')
 
         return sum(generated_data_units, [])
+
+    def _generate_tasks(self, generated_data_units: List) -> List:
+        """Setup task with uploaded synapse-backend data units.
+
+        TODO: make batch size configurable.
+        """
+        # Initialize progress
+        self.run.set_progress(0, 1, category='generate_tasks')
+        self.run.log_message('Generating tasks with data files...')
+
+        # Prepare batches for processing
+        client = self.run.client
+        project_id = self.params['project']
+        current_progress = 0
+
+        # Generate tasks
+        generated_tasks = []
+        generated_data_units_count = len(generated_data_units)
+        for data_unit in generated_data_units:
+            tasks_data = []
+            task_data = {'project': project_id, 'data_unit': data_unit['id']}
+            tasks_data.append(task_data)
+            if tasks_data:
+                created_tasks = client.create_tasks(tasks_data)
+                created_task_ids = [created_task['id'] for created_task in created_tasks]
+                generated_tasks.append(created_task_ids)
+                for created_task_id in created_task_ids:
+                    self.run.log_task(created_task_id, UploadStatus.SUCCESS)
+
+            self.run.set_progress(current_progress, generated_data_units_count, category='generate_tasks')
+            current_progress += 1
+
+        # Finish progress
+        self.run.log_message('Generating tasks completed')
+        self.run.set_progress(1, 1, category='generate_tasks')
+
+        return sum(generated_tasks, [])
+
+    def _generate_ground_truths(self):
+        """Generate ground truths for the uploaded data.
+
+        TODO: Need to add ground truths generation logic later.
+        """
+        # Initialize progress
+        self.run.set_progress(0, 1, category='generate_ground_truths')
+        self.run.log_message('Generating ground truths...')
+
+        # Finish progress
+        self.run.log_message('Generating ground truths completed')
+        self.run.set_progress(1, 1, category='generate_ground_truths')
+
+    def _validate_organized_files(self, organized_files: List, file_specification_template: Dict) -> bool:
+        """Validate organized files from Uploader."""
+        validator = FileSpecificationValidator(file_specification_template, organized_files)
+        return validator.validate()
+
+    def _organize_files(self, directory: Path, file_specification: List) -> List:
+        """Organize files according to the file specification.
+        This method handles type-based directory structure where files are organized in
+        directories named after file types (e.g., 'image_1/' directory contains image files
+        like '1.jpg', '2.jpg'). For each dataset ID found in the primary directory, it attempts
+        to find corresponding files in all type directories.
+
+        TODO : Add Logic to handle file specific name patterns and extensions.
+        (e.g. pcd:S_DCH_230725_0156_LR_037.pcd, image_1:S_DCH_230725_0156_FC_037, image_2:S_DCH_230725_0156_LF_037.jpg)
+        Args:
+            directory (Path): Root directory containing files to organize.
+            file_specification (List): File specification list.
+        Returns:
+            List: List of dictionaries containing organized files.
+        """
+        organized_files = []
+        self.run.log_message(f'Looking for files in {directory}...')
+
+        # Check for type-based directory structure (e.g., image_1/, pcd_1/)
+        type_dirs = {}
+        type_extensions = {}  # Store common extensions for each type directory
+
+        for spec in file_specification:
+            spec_name = spec['name']
+
+            spec_dir = directory / spec_name
+            if spec_dir.exists() and spec_dir.is_dir():
+                type_dirs[spec_name] = spec_dir
+
+                # Analyze file extensions in this directory
+                extensions = {}
+                for file_path in spec_dir.glob('*'):
+                    if file_path.is_file():
+                        ext = file_path.suffix.lower()
+                        extensions[ext] = extensions.get(ext, 0) + 1
+
+                # Find the most common extension
+                if extensions:
+                    common_ext = max(extensions.items(), key=lambda x: x[1])[0]
+                    type_extensions[spec_name] = common_ext
+                    self.run.log_message(f'Found type directory: {spec_name} (common extension: {common_ext})')
+
+        # If type-based directories don't exist, exit early
+        if not type_dirs:
+            self.run.log_message('No type-based directory structure found.', context=Context.INFO.value)
+            return organized_files
+
+        self.run.log_message('Detected type-based directory structure')
+
+        # Build a comprehensive map of all dataset IDs across all type directories
+        dataset_files = {}  # Dictionary: file_name -> {spec_name -> file_path}
+
+        # First pass: collect all dataset IDs from all type directories
+        for spec_name, dir_path in type_dirs.items():
+            for file_path in dir_path.glob('*'):
+                if file_path.is_file():
+                    file_name = file_path.stem
+
+                    # Initialize dataset entry if it doesn't exist
+                    if file_name not in dataset_files:
+                        dataset_files[file_name] = {}
+
+                    # Map this file to its specification
+                    if spec_name not in dataset_files[file_name]:
+                        dataset_files[file_name][spec_name] = file_path
+                    else:
+                        # If multiple files with same file_name for same spec, use most recent
+                        existing_file = dataset_files[file_name][spec_name]
+                        if file_path.stat().st_mtime > existing_file.stat().st_mtime:
+                            dataset_files[file_name][spec_name] = file_path
+                            self.run.log_message(
+                                f"Found newer file for name of {file_name}, spec '{spec_name}': "
+                                f'{file_path.name} (replacing {existing_file.name})'
+                            )
+
+        if not dataset_files:
+            self.run.log_message('No dataset files found.', context=Context.WARNING.value)
+            return organized_files
+
+        self.run.log_message(f'Found {len(dataset_files)} potential datasets by ID')
+
+        # Second pass: organize valid datasets
+        for file_name, files_dict in sorted(dataset_files.items()):
+            self.run.log_message(f'Processing file name: {file_name}')
+
+            # Add file spec details for logging
+            for spec_name, file_path in files_dict.items():
+                self.run.log_message(f"Mapped '{spec_name}' to: {file_path.name}")
+
+            # Check if all required files are present
+            required_specs = [spec['name'] for spec in file_specification if spec.get('is_required', False)]
+            if all(req in files_dict for req in required_specs):
+                # Create metadata for this dataset
+                meta_data = {
+                    'origin_file_stem': file_name,
+                    'created_at': datetime.now().isoformat(),
+                }
+
+                # Add the organized dataset
+                organized_files.append({'files': files_dict, 'meta': meta_data})
+                self.run.log_message(f'Successfully organized dataset for ID {file_name}')
+            else:
+                # Missing required files warning
+                missing = [req for req in required_specs if req not in files_dict]
+                self.run.log_message(
+                    f'Dataset ID {file_name} is missing required files: {", ".join(missing)}',
+                    context=Context.WARNING.value,
+                )
+
+        self.run.log_message(f'Total datasets organized: {len(organized_files)}')
+        return organized_files
+
+    def _map_files_to_specification(self, directory: Path, file_specification: List) -> Dict[str, Path]:
+        """Map files in a directory to the file specification.
+
+        Args:
+            directory (Path): Directory containing files to map.
+            file_specification (List): File specification list.
+
+        Returns:
+            Dict[str, Path]: Dictionary mapping file specification names to file paths.
+        """
+        files_dict = {}
+
+        # Get all files in the directory once
+        all_files = [f for f in directory.iterdir() if f.is_file()]
+
+        # Process each file specification
+        for file_spec in file_specification:
+            file_name = file_spec['name']
+            is_required = file_spec.get('is_required', False)
+
+            # Generate name pattern based on the specification
+            name_parts = re.split(r'_(\d+)$', file_name)
+
+            # Find files matching the pattern
+            matching_files = []
+            if len(name_parts) > 1:
+                base_name = name_parts[0]
+                index = name_parts[1]
+                # Match patterns like "pcd_1.ext", "point_cloud_1.ext", etc.
+                for file in all_files:
+                    if base_name in file.stem and f'_{index}' in file.stem:
+                        matching_files.append(file)
+            else:
+                # Simple match - just find files containing the pattern
+                for file in all_files:
+                    if file_name in file.stem:
+                        matching_files.append(file)
+
+            # Process matching files
+            if matching_files:
+                # Sort by modification time (newest first) if multiple files match
+                if len(matching_files) > 1:
+                    matching_files.sort(key=lambda f: f.stat().st_mtime, reverse=True)
+                    self.run.log_message(
+                        f"Multiple files match '{file_name}'. Using most recent: {matching_files[0].name}"
+                    )
+
+                files_dict[file_name] = matching_files[0]
+                self.run.log_message(f"Mapped '{file_name}' to: {matching_files[0].name}")
+            elif is_required:
+                self.run.log_message(f"Required file '{file_name}' not found.", context=Context.WARNING.value)
+
+        return files_dict

synapse_sdk/plugins/categories/upload/templates/config.yaml

@@ -1,10 +1,9 @@
 actions:
   upload:
     entrypoint: plugin.upload.Uploader
+    options:
+      allow_generate_tasks: false # Allow the plugin to generate tasks for the uploaded data
+      allow_generate_ground_truths: false # Allow the plugin to generate ground truths for the uploaded data
     supported_data_type: image # A primary data type of synapse backend collection. (e.g. 'image', 'text', 'video', 'pcd', 'audio')
     ui_schema: |
       Dumped FormKit Schema for upload plugin custom options
-  task_pre_annotation:
-    entrypoint: plugin.upload.TaskPreAnnotation
-    ui_schema: |
-      Dumped FormKit Schema for upload plugin custom options

synapse_sdk/plugins/categories/upload/templates/plugin/upload.py

@@ -3,42 +3,38 @@ from typing import List
 
 
 class Uploader:
-    """Plugin upload action class.
+    """Plugin upload action interface for organizing files.
 
-    * Organize, upload, setup task, generate ground truths for the uploaded data.
+    This class provides a minimal interface for plugin developers to implement
+    their own file organization logic.
     """
 
-    def __init__(self, run, path: Path, *args, **kwargs):
+    def __init__(self, run, path: Path, file_specification: List = None, organized_files: List = None):
         """Initialize the plugin upload action class.
 
         Args:
-            run: Plugin run object.
-            path: pathlib object by upload target destination path.
+            run: Plugin run object with logging capabilities.
+            path: Path object pointing to the upload target directory.
+            file_specification: List of specifications that define the structure of files to be uploaded.
+                Each specification contains details like file name, type, and requirements.
         """
         self.run = run
         self.path = path
+        self.file_specification = file_specification
+        self.organized_files = organized_files
 
     def handle_upload_files(self) -> List:
-        """Handle upload files.
+        """Customize the organization of files for upload.
 
-        * Organize data according to collection file specification structure.
-        * Structure files according to the file specification of the target collection.
+        This method provides a hook for plugin developers to modify the default file organization.
+        You can override this method to filter files, transform data, or add custom metadata
+        based on your specific requirements.
+
+        Args:
+            organized_files (List): The default organized files structure.
+                Each item is a dictionary with 'files' and 'meta' keys.
 
         Returns:
-            List: List of dictionaries containing 'files' and 'meta'.
-
-        Examples:
-            [
-              {
-          "files": {
-              'image_1': image_1_pathlib_object,
-              'image_2': image_2_pathlib_object,
-              'meta_1': meta_1_pathlib_object,
-          },
-          "meta": {
-            "key": "value"
-          }
-              }
-            ]
+            List: The modified list of organized files to be uploaded.
         """
-        return []
+        return self.organized_files

{synapse_sdk-1.0.0a53.dist-info → synapse_sdk-1.0.0a55.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: synapse-sdk
-Version: 1.0.0a53
+Version: 1.0.0a55
 Summary: synapse sdk
 Author-email: datamaker <developer@datamaker.io>
 License: MIT

{synapse_sdk-1.0.0a53.dist-info → synapse_sdk-1.0.0a55.dist-info}/RECORD

@@ -28,17 +28,17 @@ synapse_sdk/clients/agent/__init__.py,sha256=Pz8_iTbIbnb7ywGJ3feqoZVmO2I3mEbwpWs
 synapse_sdk/clients/agent/core.py,sha256=x2jgORTjT7pJY67SLuc-5lMG6CD5OWpy8UgGeTf7IhA,270
 synapse_sdk/clients/agent/ray.py,sha256=JrwLyVOUDG2yYsbPrxyUtWbM-FWp9B6Bl_GdDby0rt8,1559
 synapse_sdk/clients/agent/service.py,sha256=s7KuPK_DB1nr2VHrigttV1WyFonaGHNrPvU8loRxHcE,478
-synapse_sdk/clients/backend/__init__.py,sha256=MC3pndBk-SPyW9L6WnrTozoub9-EK7auXFvPHCaxeFU,1209
+synapse_sdk/clients/backend/__init__.py,sha256=Fiehino2n3voaHTdpJHXSY7K_CDnMkQeokapbgeoTBk,1187
 synapse_sdk/clients/backend/annotation.py,sha256=f4jS4qlXH7M7mQ3EuCq-NrjJ_hJNDz8pEFAYqf-e008,996
 synapse_sdk/clients/backend/core.py,sha256=5XAOdo6JZ0drfk-FMPJ96SeTd9oja-VnTwzGXdvK7Bg,1027
-synapse_sdk/clients/backend/data_collection.py,sha256=kj9TurBAljK_mFF75oaazlqnL0bd6PHbgRfR3KyTUmI,3623
+synapse_sdk/clients/backend/dataset.py,sha256=eQ0O43Ck91z5Om7mb-vW_P5NIaX1OZKirjGs-WQHdM4,3480
 synapse_sdk/clients/backend/hitl.py,sha256=na2mSXFud92p4zUEuagcDWk2klxO7xn-e86cm0VZEvs,709
 synapse_sdk/clients/backend/integration.py,sha256=9LjkYcBpi7aog-MODSDS4RlmYahypu65qxBj-AcY7xc,2683
 synapse_sdk/clients/backend/ml.py,sha256=JoPH9Ly2E3HJ7S5mdGLtcGq7ruQVVrYfWArogwZLlms,1193
 synapse_sdk/clients/backend/models.py,sha256=s5d9sGGQ0Elj0HOGC1TuwE-eBkY1aTfJPl6ls11bNCk,1961
 synapse_sdk/clients/ray/__init__.py,sha256=9ZSPXVVxlJ8Wp8ku7l021ENtPjVrGgQDgqifkkVAXgM,187
 synapse_sdk/clients/ray/core.py,sha256=a4wyCocAma2HAm-BHlbZnoVbpfdR-Aad2FM0z6vPFvw,731
-synapse_sdk/clients/ray/serve.py,sha256=rbCpXZYWf0oP8XJ9faa9QFNPYU7h8dltIG8xn9ZconY,907
+synapse_sdk/clients/ray/serve.py,sha256=eFhCYIv_irc_2RyuV3bzeWIVyz_1NlqwoNVh5KSWilY,1092
 synapse_sdk/clients/validators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 synapse_sdk/clients/validators/collections.py,sha256=LtnwvutsScubOUcZ2reGHLCzseXxtNIdnH2nv098aUU,1195
 synapse_sdk/plugins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -61,10 +61,10 @@ synapse_sdk/plugins/categories/data_validation/templates/plugin/validation.py,sh
 synapse_sdk/plugins/categories/export/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 synapse_sdk/plugins/categories/export/enums.py,sha256=gtyngvQ1DKkos9iKGcbecwTVQQ6sDwbrBPSGPNb5Am0,127
 synapse_sdk/plugins/categories/export/actions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-synapse_sdk/plugins/categories/export/actions/export.py,sha256=2lIjur8EiwTB9sc16FV8ZaPXFxUtGRPx9hreG_DKLQA,10483
+synapse_sdk/plugins/categories/export/actions/export.py,sha256=xqPB_MufeMP3riaKCbGVFGukV8RdXcg6-zUrkw4t1-A,9922
 synapse_sdk/plugins/categories/export/templates/config.yaml,sha256=N7YmnFROb3s3M35SA9nmabyzoSb5O2t2TRPicwFNN2o,56
 synapse_sdk/plugins/categories/export/templates/plugin/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-synapse_sdk/plugins/categories/export/templates/plugin/export.py,sha256=zG8mSn7ZGIj8cttWmb7GEPcGgQRbZ97brJCzkuK7RP8,6106
+synapse_sdk/plugins/categories/export/templates/plugin/export.py,sha256=JA2Y_A30QyJekSqDq8PeRuFR9k0yjQjOG-Xy6C8zPew,5196
 synapse_sdk/plugins/categories/neural_net/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 synapse_sdk/plugins/categories/neural_net/actions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 synapse_sdk/plugins/categories/neural_net/actions/deployment.py,sha256=y2LrS-pwazqRI5O0q1NUy45NQYsBj6ykbrXnDMs_fqE,1987
@@ -100,12 +100,10 @@ synapse_sdk/plugins/categories/smart_tool/templates/plugin/__init__.py,sha256=47
 synapse_sdk/plugins/categories/smart_tool/templates/plugin/auto_label.py,sha256=eevNg0nOcYFR4z_L_R-sCvVOYoLWSAH1jwDkAf3YCjY,320
 synapse_sdk/plugins/categories/upload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 synapse_sdk/plugins/categories/upload/actions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-synapse_sdk/plugins/categories/upload/actions/task_pre_annotation.py,sha256=YkQZ7QECu6-PnSEv2lAbbL3smxeIHxUiu9ruBdA0_0k,3066
-synapse_sdk/plugins/categories/upload/actions/upload.py,sha256=xTO40dB00uE9xSQxnQYIyuZEvTzx99cSxfCOXLKZAsQ,11294
-synapse_sdk/plugins/categories/upload/templates/config.yaml,sha256=1O0kMfkFMGYwnpBcttrlC9bu4xzU9docw2MBOq_Elmo,417
+synapse_sdk/plugins/categories/upload/actions/upload.py,sha256=L9OqHWNyzO5qXi9-afkgRI1hfL7ysJjY0z0a5kujJrQ,24202
+synapse_sdk/plugins/categories/upload/templates/config.yaml,sha256=kwHNWHFYbzDi1mEh40KozatPZbZGH44dlP0t0J7ejJw,483
 synapse_sdk/plugins/categories/upload/templates/plugin/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-synapse_sdk/plugins/categories/upload/templates/plugin/task_pre_annotation.py,sha256=9XkUZu7USjVjDPufM0NlYmkdKfV7Hf_9v5GN1RgZzS0,350
-synapse_sdk/plugins/categories/upload/templates/plugin/upload.py,sha256=dnK8gy33GjG5ettayawDJv1gM3xCm1K6lM-PfeeTjQw,1163
+synapse_sdk/plugins/categories/upload/templates/plugin/upload.py,sha256=IZU4sdSMSLKPCtlNqF7DP2howTdYR6hr74HCUZsGdPk,1559
 synapse_sdk/plugins/templates/cookiecutter.json,sha256=NxOWk9A_v1pO0Ny4IYT9Cj5iiJ16--cIQrGC67QdR0I,396
 synapse_sdk/plugins/templates/hooks/post_gen_project.py,sha256=jqlYkY1O2TxIR-Vh3gnwILYy8k-D39Xx66d2KNQVMCs,147
 synapse_sdk/plugins/templates/hooks/pre_prompt.py,sha256=aOAMM623s0sKFGjTZaotAOYFvsNMxeii4tPyhOAFKVE,539
@@ -136,9 +134,9 @@ synapse_sdk/utils/storage/providers/__init__.py,sha256=x7RGwZryT2FpVxS7fGWryRVpq
 synapse_sdk/utils/storage/providers/gcp.py,sha256=i2BQCu1Kej1If9SuNr2_lEyTcr5M_ncGITZrL0u5wEA,363
 synapse_sdk/utils/storage/providers/s3.py,sha256=W94rQvhGRXti3R4mYP7gmU5pcyCQpGFIBLvxxqLVdRM,2231
 synapse_sdk/utils/storage/providers/sftp.py,sha256=_8s9hf0JXIO21gvm-JVS00FbLsbtvly4c-ETLRax68A,1426
-synapse_sdk-1.0.0a53.dist-info/licenses/LICENSE,sha256=bKzmC5YAg4V1Fhl8OO_tqY8j62hgdncAkN7VrdjmrGk,1101
-synapse_sdk-1.0.0a53.dist-info/METADATA,sha256=QZFYv1IY06vc9HM-VCqi8aL3G4D54ruvDPUgX4RlRDg,1303
-synapse_sdk-1.0.0a53.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-synapse_sdk-1.0.0a53.dist-info/entry_points.txt,sha256=VNptJoGoNJI8yLXfBmhgUefMsmGI0m3-0YoMvrOgbxo,48
-synapse_sdk-1.0.0a53.dist-info/top_level.txt,sha256=ytgJMRK1slVOKUpgcw3LEyHHP7S34J6n_gJzdkcSsw8,12
-synapse_sdk-1.0.0a53.dist-info/RECORD,,
+synapse_sdk-1.0.0a55.dist-info/licenses/LICENSE,sha256=bKzmC5YAg4V1Fhl8OO_tqY8j62hgdncAkN7VrdjmrGk,1101
+synapse_sdk-1.0.0a55.dist-info/METADATA,sha256=d2fJLQn1LuXa0NeLokHzsjeE8zgIyOJrOH3bRBUoIw0,1303
+synapse_sdk-1.0.0a55.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+synapse_sdk-1.0.0a55.dist-info/entry_points.txt,sha256=VNptJoGoNJI8yLXfBmhgUefMsmGI0m3-0YoMvrOgbxo,48
+synapse_sdk-1.0.0a55.dist-info/top_level.txt,sha256=ytgJMRK1slVOKUpgcw3LEyHHP7S34J6n_gJzdkcSsw8,12
+synapse_sdk-1.0.0a55.dist-info/RECORD,,

synapse_sdk/plugins/categories/upload/actions/task_pre_annotation.py

@@ -1,101 +0,0 @@
-from enum import Enum
-from typing import Annotated
-
-from pydantic import AfterValidator, BaseModel, field_validator
-from pydantic_core import PydanticCustomError
-
-from synapse_sdk.clients.exceptions import ClientError
-from synapse_sdk.plugins.categories.base import Action
-from synapse_sdk.plugins.categories.decorators import register_action
-from synapse_sdk.plugins.enums import PluginCategory, RunMethod
-from synapse_sdk.plugins.models import Run
-from synapse_sdk.utils.pydantic.validators import non_blank
-
-
-class TaskDataAnnotationType(str, Enum):
-    FILE = 'file'
-    INFERENCE = 'inference'
-
-
-class TaskPreAnnotationRun(Run):
-    pass
-
-
-class TaskPreAnnotationParams(BaseModel):
-    """TaskPreAnnotation action parameters.
-
-    Args:
-        name (str): The name of the action.
-        description (str | None): The description of the action.
-        project (int): The project ID.
-        data_collection (int): The data collection ID.
-        task_data_annotation_type (TaskDataAnnotationType): The type of task data annotation.
-    """
-
-    name: Annotated[str, AfterValidator(non_blank)]
-    description: str | None
-    project: int
-    data_collection: int
-    task_data_annotation_type: TaskDataAnnotationType
-
-    @field_validator('data_collection', mode='before')
-    @classmethod
-    def check_data_collection_exists(cls, value: str, info) -> str:
-        """Validate synapse-backend collection exists."""
-        action = info.context['action']
-        client = action.client
-        try:
-            client.get_data_collection(value)
-        except ClientError:
-            raise PydanticCustomError('client_error', 'Error occurred while checking data collection exists.')
-        return value
-
-    @field_validator('project', mode='before')
-    @classmethod
-    def check_project_exists(cls, value: str, info) -> str:
-        """Validate synapse-backend project exists."""
-        if not value:
-            return value
-
-        action = info.context['action']
-        client = action.client
-        try:
-            client.get_project(value)
-        except ClientError:
-            raise PydanticCustomError('client_error', 'Error occurred while checking project exists.')
-        return value
-
-
-@register_action
-class TaskPreAnnotationAction(Action):
-    """TaskPreAnnotation action class.
-
-    * Annotate data to tasks.
-    """
-
-    name = 'task_pre_annotation'
-    category = PluginCategory.UPLOAD
-    method = RunMethod.JOB
-    run_class = TaskPreAnnotationRun
-    progress_categories = {
-        'generate_tasks': {
-            'proportion': 10,
-        },
-        'annotate_task_data': {
-            'proportion': 90,
-        },
-    }
-
-    def start(self):
-        """Start task_pre_annotation action.
-
-        * Generate tasks.
-        * Annotate data to tasks.
-        """
-        task_pre_annotation = self.get_task_pre_annotation()
-        task_pre_annotation.handle_annotate_data_from_files()
-        return {}
-
-    def get_task_pre_annotation(self):
-        """Get task pre annotation entrypoint."""
-        return self.entrypoint()

synapse_sdk/plugins/categories/upload/templates/plugin/task_pre_annotation.py

@@ -1,14 +0,0 @@
-class TaskPreAnnotation:
-    def __init__(self, run, *args, **kwargs):
-        """Initialize the plugin task pre annotation action class.
-
-        Args:
-            run: Plugin run object.
-        """
-        self.run = run
-
-    def handle_annotate_data_from_files(self):
-        pass
-
-    def handle_annotate_data_with_inference(self):
-        pass