Merge to prod.

aixplain/enums/data_type.py

@@ -35,4 +35,4 @@ class DataType(Enum):
     VIDEO = "video"
 
     def __str__(self):
-        return self._value_
+        return self._value_

aixplain/factories/pipeline_factory.py

@@ -22,6 +22,7 @@
 """
 import json
 import logging
+import os
 from typing import Dict, List, Optional, Text, Union
 from aixplain.enums.data_type import DataType
 from aixplain.enums.function import Function
@@ -207,7 +208,7 @@ def list(
                 output_data_types = [output_data_types]
             payload["inputDataTypes"] = [data_type.value for data_type in output_data_types]
 
-        logging.info(f"Start service for POST List Dataset - {url} - {headers} - {json.dumps(payload)}")
+        logging.info(f"Start service for POST List Pipeline - {url} - {headers} - {json.dumps(payload)}")
         r = _request_with_retry("post", url, headers=headers, json=payload)
         resp = r.json()
 
@@ -220,3 +221,40 @@ def list(
             for pipeline in results:
                 pipelines.append(cls.__from_response(pipeline))
         return {"results": pipelines, "page_total": page_total, "page_number": page_number, "total": total}
+
+    @classmethod
+    def create(cls, name: Text, pipeline: Union[Text, Dict], status: Text = "draft") -> Pipeline:
+        """Pipeline Creation
+
+        Args:
+            name (Text): Pipeline Name
+            pipeline (Union[Text, Dict]): Pipeline as a Python dictionary or in a JSON file
+            status (Text, optional): Status of the pipeline. Currently only draft pipelines can be saved. Defaults to "draft".
+
+        Raises:
+            Exception: Currently just the creation of draft pipelines are supported
+
+        Returns:
+            Pipeline: instance of the new pipeline
+        """
+        try:
+            assert status == "draft", "Pipeline Creation Error: Currently just the creation of draft pipelines are supported."
+            if isinstance(pipeline, str) is True:
+                _, ext = os.path.splitext(pipeline)
+                assert (
+                    os.path.exists(pipeline) and ext == ".json"
+                ), "Pipeline Creation Error: Make sure the pipeline to be save is in a JSON file."
+                with open(pipeline) as f:
+                    pipeline = json.load(f)
+
+            # prepare payload
+            payload = {"name": name, "status": "draft", "architecture": pipeline}
+            url = urljoin(cls.backend_url, "sdk/pipelines")
+            headers = {"Authorization": f"Token {config.TEAM_API_KEY}", "Content-Type": "application/json"}
+            logging.info(f"Start service for POST Create Pipeline - {url} - {headers} - {json.dumps(payload)}")
+            r = _request_with_retry("post", url, headers=headers, json=payload)
+            response = r.json()
+
+            return Pipeline(response["id"], name, config.TEAM_API_KEY)
+        except Exception as e:
+            raise Exception(e)

aixplain/modules/metadata.py

@@ -43,6 +43,7 @@ def __init__(
         file_extension: Optional[FileType] = None,
         languages: List[Language] = [],
         dsubtype: DataSubtype = DataSubtype.OTHER,
+        id: Optional[Text] = None,
         **kwargs
     ) -> None:
         """MetaData Class
@@ -62,6 +63,7 @@ def __init__(
             file_extension (Optional[FileType], optional): File extension (e.g. CSV, TXT, etc.). Defaults to None.
             languages (List[Language], optional): List of languages which the data consists of. Defaults to [].
             dsubtype (DataSubtype, optional): Data subtype (e.g., age, topic, race, split, etc.), used in datasets metadata. Defaults to Other.
+            id (Optional[Text], optional): Data ID. Defaults to None.
         """
         self.name = name
         if isinstance(dtype, str):
@@ -91,4 +93,5 @@ def __init__(
                 language = Language(language)
             self.languages.append(language)
         self.dsubtype = dsubtype
+        self.id = id
         self.kwargs = kwargs

aixplain/modules/pipeline.py

@@ -23,11 +23,13 @@
 
 import time
 import json
+import os
 import logging
 from aixplain.modules.asset import Asset
 from aixplain.utils import config
 from aixplain.utils.file_utils import _request_with_retry
 from typing import Dict, Optional, Text, Union
+from urllib.parse import urljoin
 
 
 class Pipeline(Asset):
@@ -306,3 +308,32 @@ def run_async(
             if resp is not None:
                 response["error"] = resp
         return response
+
+    def update(self, pipeline: Union[Text, Dict]):
+        """Update Pipeline
+
+        Args:
+            pipeline (Union[Text, Dict]): Pipeline as a Python dictionary or in a JSON file
+
+        Raises:
+            Exception: Make sure the pipeline to be save is in a JSON file.
+        """
+        try:
+            if isinstance(pipeline, str) is True:
+                _, ext = os.path.splitext(pipeline)
+                assert (
+                    os.path.exists(pipeline) and ext == ".json"
+                ), "Pipeline Update Error: Make sure the pipeline to be save is in a JSON file."
+                with open(pipeline) as f:
+                    pipeline = json.load(f)
+
+            # prepare payload
+            payload = {"name": self.name, "status": "draft", "architecture": pipeline}
+            url = urljoin(config.BACKEND_URL, f"sdk/pipelines/{self.id}")
+            headers = {"Authorization": f"Token {config.TEAM_API_KEY}", "Content-Type": "application/json"}
+            logging.info(f"Start service for PUT Update Pipeline - {url} - {headers} - {json.dumps(payload)}")
+            r = _request_with_retry("put", url, headers=headers, json=payload)
+            response = r.json()
+            logging.info(f"Pipeline {response['id']} Updated.")
+        except Exception as e:
+            raise Exception(e)

aixplain/processes/data_onboarding/onboard_functions.py

@@ -97,11 +97,11 @@ def process_data_files(
         -1,
         0,
     )
-    if metadata.dtype in [DataType.AUDIO, DataType.IMAGE] or metadata.dsubtype == DataSubtype.INTERVAL:
+    if metadata.dtype in [DataType.AUDIO, DataType.IMAGE, DataType.LABEL] or metadata.dsubtype == DataSubtype.INTERVAL:
         files, data_column_idx, start_column_idx, end_column_idx, nrows = process_media_files.run(
             metadata=metadata, paths=paths, folder=folder
         )
-    elif metadata.dtype in [DataType.TEXT, DataType.LABEL]:
+    elif metadata.dtype in [DataType.TEXT]:
         files, data_column_idx, nrows = process_text_files.run(metadata=metadata, paths=paths, folder=folder)
     return files, data_column_idx, start_column_idx, end_column_idx, nrows
 

aixplain/processes/data_onboarding/process_media_files.py

@@ -16,6 +16,7 @@
 from pathlib import Path
 from tqdm import tqdm
 from typing import List, Tuple
+from urllib.parse import urlparse
 
 AUDIO_MAX_SIZE = 50000000
 IMAGE_TEXT_MAX_SIZE = 25000000
@@ -45,6 +46,15 @@ def run(metadata: MetaData, paths: List, folder: Path, batch_size: int = 100) ->
     Returns:
         Tuple[List[File], int, int, int]: list of s3 links; data, start and end columns index, and number of rows
     """
+    if metadata.dtype == DataType.LABEL:
+        assert (
+            metadata.storage_type != StorageType.TEXT
+        ), f'Data Asset Onboarding Error: Column "{metadata.name}" of type "{metadata.dtype}" can not be stored in text. Label data should be stored in a JSON file.'
+    else:
+        assert (
+            metadata.storage_type != StorageType.TEXT
+        ), f'Data Asset Onboarding Error: Column "{metadata.name}" of type "{metadata.dtype}" can not be stored in text.'
+
     # if files are stored locally, create a folder to store it
     media_folder = Path(".")
     if metadata.storage_type == StorageType.FILE:
@@ -95,6 +105,14 @@ def run(metadata: MetaData, paths: List, folder: Path, batch_size: int = 100) ->
                     assert (
                         os.path.getsize(media_path) <= AUDIO_MAX_SIZE
                     ), f'Data Asset Onboarding Error: Local audio file "{media_path}" exceeds the size limit of 50 MB.'
+                elif metadata.dtype == DataType.LABEL:
+                    assert (
+                        os.path.getsize(media_path) <= IMAGE_TEXT_MAX_SIZE
+                    ), f'Data Asset Onboarding Error: JSON file with labels "{media_path}" exceeds the size limit of 25 MB.'
+                    _, extension = os.path.splitext(media_path)
+                    assert (
+                        extension == ".json"
+                    ), f'Data Asset Onboarding Error: Label data should be stored in a JSON file and "{media_path}" is not one.'
                 else:
                     assert (
                         os.path.getsize(media_path) <= IMAGE_TEXT_MAX_SIZE
@@ -105,6 +123,12 @@ def run(metadata: MetaData, paths: List, folder: Path, batch_size: int = 100) ->
                     shutil.copy2(media_path, new_path)
                 batch.append(fname)
             else:
+                if metadata.dtype == DataType.LABEL:
+                    path = urlparse(media_path).path
+                    _, extension = os.path.splitext(path)
+                    assert (
+                        extension == ".json"
+                    ), f'Data Asset Onboarding Error: Label data should be stored in a JSON file and "{media_path}" is not one.'
                 batch.append(media_path)
 
             # crop intervals can not be used with interval data types

aixplain/processes/data_onboarding/process_text_files.py

@@ -26,7 +26,7 @@ def process_text(content: str, storage_type: StorageType) -> Text:
         Text: textual content
     """
     if storage_type == StorageType.FILE:
-        # Check the size of file and assert a limit of 50 MB
+        # Check the size of file and assert a limit of 25 MB
         assert (
             os.path.getsize(content) <= 25000000
         ), f'Data Asset Onboarding Error: Local text file "{content}" exceeds the size limit of 25 MB.'

docs/samples/label_dataset_onboarding/corpus/index.csv

@@ -0,0 +1,3 @@
+,images,labels
+0,corpus/images/1.jpg,corpus/labels/1.json
+1,corpus/images/2.png,corpus/labels/2.json

docs/samples/label_dataset_onboarding/corpus/labels/1.json

@@ -0,0 +1,9 @@
+{
+    "data": "arcade",
+    "boundingBox": {
+        "top": 0,
+        "bottom": 0,
+        "left": 0,
+        "right": 0
+    }
+}

docs/samples/label_dataset_onboarding/corpus/labels/2.json

@@ -0,0 +1,9 @@
+{
+    "data": "building",
+    "boundingBox": {
+        "top": 0,
+        "bottom": 0,
+        "left": 0,
+        "right": 0
+    }
+}