clarifai 10.11.1__tar.gz → 10.11.2rc1__tar.gz

{clarifai-10.11.1/clarifai.egg-info → clarifai-10.11.2rc1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: clarifai
-Version: 10.11.1
+Version: 10.11.2rc1
 Summary: Clarifai Python SDK
 Home-page: https://github.com/Clarifai/clarifai-python
 Author: Clarifai
@@ -19,22 +19,8 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: clarifai-grpc>=10.11.2
-Requires-Dist: clarifai-protocol>=0.0.14
-Requires-Dist: numpy>=1.22.0
-Requires-Dist: tqdm>=4.65.0
-Requires-Dist: tritonclient>=2.34.0
-Requires-Dist: rich>=13.4.2
-Requires-Dist: PyYAML>=6.0.1
-Requires-Dist: schema==0.7.5
-Requires-Dist: Pillow>=9.5.0
-Requires-Dist: inquirerpy==0.3.4
-Requires-Dist: tabulate>=0.9.0
-Requires-Dist: fsspec==2024.6.1
-Requires-Dist: click==8.1.7
 Provides-Extra: all
-Requires-Dist: pycocotools==2.0.6; extra == "all"
+License-File: LICENSE
 
 <h1 align="center">
   <a href="https://www.clarifai.com/"><img alt="Clarifai" title="Clarifai" src="https://github.com/user-attachments/assets/623b883b-7fe5-4b95-bbfa-8691f5779af4"></a>

clarifai-10.11.2rc1/clarifai/__init__.py

@@ -0,0 +1 @@
+__version__ = "10.11.2rc1"

{clarifai-10.11.1 → clarifai-10.11.2rc1}/clarifai/client/dataset.py

@@ -281,9 +281,9 @@ class Dataset(Lister, BaseClient):
       failed_input_ids = list(set(failed_input_ids) - set(duplicate_input_ids))
       duplicate_details = [[
           input_ids[id], id, "Input has a duplicate ID.",
-          dataset_obj.data_generator[input_ids[id]].image_path,
-          dataset_obj.data_generator[input_ids[id]].labels,
-          dataset_obj.data_generator[input_ids[id]].metadata
+          getattr(dataset_obj.data_generator[input_ids[id]], 'image_path', None),
+          getattr(dataset_obj.data_generator[input_ids[id]], 'labels', None),
+          getattr(dataset_obj.data_generator[input_ids[id]], 'metadata', None)
       ] for id in duplicate_input_ids]
       duplicate_table = tabulate(
           duplicate_details,
@@ -386,7 +386,7 @@ class Dataset(Lister, BaseClient):
           tablefmt="grid")
       timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
       self.logger.warning(
-          f"{timestamp}\nFailed to upload {len(failed_retrying_inputs)} inputs in current batch {batch_no}:\n{failed_table}\n\n"
+          f"{timestamp}\nFailed to upload {len(failed_retrying_inputs)} inputs in current batch {batch_no} due to {retry_response}:\n{failed_table}\n\n"
       )
 
   def _data_upload(self,

{clarifai-10.11.1 → clarifai-10.11.2rc1}/clarifai/client/model.py

@@ -503,6 +503,7 @@ class Model(Lister, BaseClient):
                           compute_cluster_id: str = None,
                           nodepool_id: str = None,
                           deployment_id: str = None,
+                          user_id: str = None,
                           inference_params: Dict = {},
                           output_config: Dict = {}):
     """Predicts the model based on the given filepath.
@@ -534,7 +535,7 @@ class Model(Lister, BaseClient):
       file_bytes = f.read()
 
     return self.predict_by_bytes(file_bytes, input_type, compute_cluster_id, nodepool_id,
-                                 deployment_id, inference_params, output_config)
+                                 deployment_id, user_id, inference_params, output_config)
 
   def predict_by_bytes(self,
                        input_bytes: bytes,
@@ -542,6 +543,7 @@ class Model(Lister, BaseClient):
                        compute_cluster_id: str = None,
                        nodepool_id: str = None,
                        deployment_id: str = None,
+                       user_id: str = None,
                        inference_params: Dict = {},
                        output_config: Dict = {}):
     """Predicts the model based on the given bytes.
@@ -581,11 +583,23 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.predict(
         inputs=[input_proto],
@@ -599,6 +613,7 @@ class Model(Lister, BaseClient):
                      compute_cluster_id: str = None,
                      nodepool_id: str = None,
                      deployment_id: str = None,
+                     user_id: str = None,
                      inference_params: Dict = {},
                      output_config: Dict = {}):
     """Predicts the model based on the given URL.
@@ -639,11 +654,23 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.predict(
         inputs=[input_proto],
@@ -712,6 +739,7 @@ class Model(Lister, BaseClient):
                            compute_cluster_id: str = None,
                            nodepool_id: str = None,
                            deployment_id: str = None,
+                           user_id: str = None,
                            inference_params: Dict = {},
                            output_config: Dict = {}):
     """Generate the stream output on model based on the given filepath.
@@ -748,6 +776,7 @@ class Model(Lister, BaseClient):
         compute_cluster_id=compute_cluster_id,
         nodepool_id=nodepool_id,
         deployment_id=deployment_id,
+        user_id=user_id,
         inference_params=inference_params,
         output_config=output_config)
 
@@ -757,6 +786,7 @@ class Model(Lister, BaseClient):
                         compute_cluster_id: str = None,
                         nodepool_id: str = None,
                         deployment_id: str = None,
+                        user_id: str = None,
                         inference_params: Dict = {},
                         output_config: Dict = {}):
     """Generate the stream output on model based on the given bytes.
@@ -798,11 +828,21 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.generate(
         inputs=[input_proto],
@@ -816,6 +856,7 @@ class Model(Lister, BaseClient):
                       compute_cluster_id: str = None,
                       nodepool_id: str = None,
                       deployment_id: str = None,
+                      user_id: str = None,
                       inference_params: Dict = {},
                       output_config: Dict = {}):
     """Generate the stream output on model based on the given URL.
@@ -857,11 +898,23 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.generate(
         inputs=[input_proto],
@@ -930,6 +983,7 @@ class Model(Lister, BaseClient):
                          compute_cluster_id: str = None,
                          nodepool_id: str = None,
                          deployment_id: str = None,
+                         user_id: str = None,
                          inference_params: Dict = {},
                          output_config: Dict = {}):
     """Stream the model output based on the given filepath.
@@ -964,6 +1018,7 @@ class Model(Lister, BaseClient):
         compute_cluster_id=compute_cluster_id,
         nodepool_id=nodepool_id,
         deployment_id=deployment_id,
+        user_id=user_id,
         inference_params=inference_params,
         output_config=output_config)
 
@@ -973,6 +1028,7 @@ class Model(Lister, BaseClient):
                       compute_cluster_id: str = None,
                       nodepool_id: str = None,
                       deployment_id: str = None,
+                      user_id: str = None,
                       inference_params: Dict = {},
                       output_config: Dict = {}):
     """Stream the model output based on the given bytes.
@@ -1016,11 +1072,23 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.stream(
         inputs=input_generator(),
@@ -1034,6 +1102,7 @@ class Model(Lister, BaseClient):
                     compute_cluster_id: str = None,
                     nodepool_id: str = None,
                     deployment_id: str = None,
+                    user_id: str = None,
                     inference_params: Dict = {},
                     output_config: Dict = {}):
     """Stream the model output based on the given URL.
@@ -1075,11 +1144,23 @@ class Model(Lister, BaseClient):
 
     runner_selector = None
     if deployment_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with deployment ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Deployment.get_runner_selector(
-          user_id=self.user_id, deployment_id=deployment_id)
+          user_id=user_id, deployment_id=deployment_id)
     elif compute_cluster_id and nodepool_id:
+      if not user_id and not os.environ.get('CLARIFAI_USER_ID'):
+        raise UserError(
+            "User ID is required for model prediction with compute cluster ID and nodepool ID, please provide user_id in the method call."
+        )
+      if not user_id:
+        user_id = os.environ.get('CLARIFAI_USER_ID')
       runner_selector = Nodepool.get_runner_selector(
-          user_id=self.user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
+          user_id=user_id, compute_cluster_id=compute_cluster_id, nodepool_id=nodepool_id)
 
     return self.stream(
         inputs=input_generator(),

{clarifai-10.11.1 → clarifai-10.11.2rc1}/clarifai/datasets/upload/features.py

@@ -7,7 +7,7 @@ from typing import List, Optional, Union
 class TextFeatures:
   """Text classification datasets preprocessing output features."""
   text: str
-  labels: List[Union[str, int]]  # List[str or int] to cater for multi-class tasks
+  labels: List[Union[str, int]] = None  # List[str or int] to cater for multi-class tasks
   id: Optional[int] = None  # text_id
   metadata: Optional[dict] = None
   label_ids: Optional[List[str]] = None

{clarifai-10.11.1 → clarifai-10.11.2rc1}/clarifai/datasets/upload/multimodal.py

@@ -34,7 +34,8 @@ class MultiModalDataset(ClarifaiDataset):
       metadata = Struct()
       image_bytes = data_item.image_bytes
       text = data_item.text
-      labels = data_item.labels if isinstance(data_item.labels, list) else [data_item.labels]
+      labels = data_item.labels if ((data_item.labels is None) or
+                                    isinstance(data_item.labels, list)) else [data_item.labels]
       input_id = f"{self.dataset_id}-{id}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
       if data_item.metadata is not None:
         metadata.update(data_item.metadata)

{clarifai-10.11.1 → clarifai-10.11.2rc1}/clarifai/datasets/upload/text.py

@@ -34,8 +34,9 @@ class TextClassificationDataset(ClarifaiDataset):
       data_item = self.data_generator[id]
       metadata = Struct()
       text = data_item.text
-      labels = data_item.labels if isinstance(data_item.labels,
-                                              list) else [data_item.labels]  # clarifai concept
+      labels = data_item.labels if ((data_item.labels is None) or
+                                    isinstance(data_item.labels, list)) else [data_item.labels
+                                                                             ]  # clarifai concept
       label_ids = data_item.label_ids
       input_id = f"{self.dataset_id}-{get_uuid(8)}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
       if data_item.metadata is not None: