clarifai 10.3.0__tar.gz → 10.3.2__tar.gz

{clarifai-10.3.0/clarifai.egg-info → clarifai-10.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: clarifai
-Version: 10.3.0
+Version: 10.3.2
 Summary: Clarifai Python SDK
 Home-page: https://github.com/Clarifai/clarifai-python
 Author: Clarifai
@@ -83,6 +83,7 @@ Give the repo a star ⭐
   * [Smart Image Search](#smart-image-search)
   * [Smart Text Search](#smart-text-search)
   * [Filters](#filters)
+  * [Pagination](#pagination)
 * **[Retrieval Augmented Generation (RAG)](#retrieval-augmented-generation-rag)**
 * **[More Examples](#pushpin-more-examples)**
 
@@ -163,13 +164,13 @@ dataset = app.create_dataset(dataset_id="demo_dataset")
 # execute data upload to Clarifai app dataset
 from clarifai.datasets.upload.laoders.coco_detection import COCODetectionDataLoader
 coco_dataloader = COCODetectionDataLoader("images_dir", "coco_annotation_filepath")
-dataset.upload_dataset(dataloader=coco_dataloader, get_upload_status=True, log_warnings =True)
+dataset.upload_dataset(dataloader=coco_dataloader, get_upload_status=True)
 
 
 #Try upload and record the failed outputs in log file.
 from clarifai.datasets.upload.utils import load_module_dataloader
 cifar_dataloader = load_module_dataloader('./image_classification/cifar10')
-dataset.upload_dataset(dataloader=cifar_dataloader, get_upload_status=True, log_warnings =True)
+dataset.upload_dataset(dataloader=cifar_dataloader, log_warnings =True)
 
 #Retry upload from logs for `upload_dataset`
 dataset.retry_upload_from_logs(dataloader=cifar_dataloader, log_file_path='log_file.log',
@@ -478,6 +479,22 @@ Input filters allows to filter by input_type, status of inputs and by inputs_dat
 results = search.query(filters=[{'input_types': ['image', 'text']}])
 ```
 
+#### Pagination
+
+Below is an example of using Search with Pagination.
+
+```python
+# Note: CLARIFAI_PAT must be set as env variable.
+from clarifai.client.search import Search
+search = Search(user_id="user_id", app_id="app_id", metric="cosine", pagination=True)
+
+# Search by image url
+results = search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}],page_no=2,per_page=5)
+
+for data in results:
+  print(data.hits[0].input.data.image.url)
+```
+
 ## Retrieval Augmented Generation (RAG)
 
 You can setup and start your RAG pipeline in 4 lines of code. The setup method automatically creates a new app and the necessary components under the hood. By default it uses the [mistral-7B-Instruct](https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct) model.

{clarifai-10.3.0 → clarifai-10.3.2}/README.md

@@ -48,6 +48,7 @@ Give the repo a star ⭐
   * [Smart Image Search](#smart-image-search)
   * [Smart Text Search](#smart-text-search)
   * [Filters](#filters)
+  * [Pagination](#pagination)
 * **[Retrieval Augmented Generation (RAG)](#retrieval-augmented-generation-rag)**
 * **[More Examples](#pushpin-more-examples)**
 
@@ -128,13 +129,13 @@ dataset = app.create_dataset(dataset_id="demo_dataset")
 # execute data upload to Clarifai app dataset
 from clarifai.datasets.upload.laoders.coco_detection import COCODetectionDataLoader
 coco_dataloader = COCODetectionDataLoader("images_dir", "coco_annotation_filepath")
-dataset.upload_dataset(dataloader=coco_dataloader, get_upload_status=True, log_warnings =True)
+dataset.upload_dataset(dataloader=coco_dataloader, get_upload_status=True)
 
 
 #Try upload and record the failed outputs in log file.
 from clarifai.datasets.upload.utils import load_module_dataloader
 cifar_dataloader = load_module_dataloader('./image_classification/cifar10')
-dataset.upload_dataset(dataloader=cifar_dataloader, get_upload_status=True, log_warnings =True)
+dataset.upload_dataset(dataloader=cifar_dataloader, log_warnings =True)
 
 #Retry upload from logs for `upload_dataset`
 dataset.retry_upload_from_logs(dataloader=cifar_dataloader, log_file_path='log_file.log',
@@ -443,6 +444,22 @@ Input filters allows to filter by input_type, status of inputs and by inputs_dat
 results = search.query(filters=[{'input_types': ['image', 'text']}])
 ```
 
+#### Pagination
+
+Below is an example of using Search with Pagination.
+
+```python
+# Note: CLARIFAI_PAT must be set as env variable.
+from clarifai.client.search import Search
+search = Search(user_id="user_id", app_id="app_id", metric="cosine", pagination=True)
+
+# Search by image url
+results = search.query(ranks=[{"image_url": "https://samples.clarifai.com/metro-north.jpg"}],page_no=2,per_page=5)
+
+for data in results:
+  print(data.hits[0].input.data.image.url)
+```
+
 ## Retrieval Augmented Generation (RAG)
 
 You can setup and start your RAG pipeline in 4 lines of code. The setup method automatically creates a new app and the necessary components under the hood. By default it uses the [mistral-7B-Instruct](https://clarifai.com/mistralai/completion/models/mistral-7B-Instruct) model.

clarifai-10.3.2/VERSION

@@ -0,0 +1 @@
+10.3.2

{clarifai-10.3.0 → clarifai-10.3.2}/clarifai/client/input.py

@@ -72,6 +72,7 @@ class Inputs(Lister, BaseClient):
                  text_pb: Text = None,
                  geo_info: List = None,
                  labels: List = None,
+                 label_ids: List = None,
                  metadata: Struct = None) -> Input:
     """Create input proto for image data type.
         Args:
@@ -82,7 +83,8 @@ class Inputs(Lister, BaseClient):
             audio_pb (Audio): The audio proto to be used for the input.
             text_pb (Text): The text proto to be used for the input.
             geo_info (list): A list of longitude and latitude for the geo point.
-            labels (list): A list of labels for the input.
+            labels (list): A list of label names for the input.
+            label_ids (list): A list of label ids for the input.
             metadata (Struct): A Struct of metadata for the input.
         Returns:
             Input: An Input object for the specified input ID.
@@ -90,14 +92,26 @@ class Inputs(Lister, BaseClient):
     assert geo_info is None or isinstance(
         geo_info, list), "geo_info must be a list of longitude and latitude"
     assert labels is None or isinstance(labels, list), "labels must be a list of strings"
+    assert label_ids is None or isinstance(label_ids, list), "label_ids must be a list of strings"
     assert metadata is None or isinstance(metadata, Struct), "metadata must be a Struct"
     geo_pb = resources_pb2.Geo(geo_point=resources_pb2.GeoPoint(
         longitude=geo_info[0], latitude=geo_info[1])) if geo_info else None
-    concepts=[
+    if labels:
+      if not label_ids:
+        concepts=[
             resources_pb2.Concept(
             id=f"id-{''.join(_label.split(' '))}", name=_label, value=1.)\
             for _label in labels
-        ]if labels else None
+        ]
+      else:
+        assert len(labels) == len(label_ids), "labels and label_ids must be of the same length"
+        concepts=[
+            resources_pb2.Concept(
+            id=label_id, name=_label, value=1.)\
+            for label_id, _label in zip(label_ids, labels)
+        ]
+    else:
+      concepts = None
 
     if dataset_id:
       return resources_pb2.Input(
@@ -467,13 +481,14 @@ class Inputs(Lister, BaseClient):
     return input_protos
 
   @staticmethod
-  def get_bbox_proto(input_id: str, label: str, bbox: List) -> Annotation:
+  def get_bbox_proto(input_id: str, label: str, bbox: List, label_id: str = None) -> Annotation:
     """Create an annotation proto for each bounding box, label input pair.
 
     Args:
         input_id (str): The input ID for the annotation to create.
-        label (str): annotation label
+        label (str): annotation label name
         bbox (List): a list of a single bbox's coordinates. # bbox ordering: [xmin, ymin, xmax, ymax]
+        label_id (str): annotation label ID
 
     Returns:
         An annotation object for the specified input ID.
@@ -500,19 +515,22 @@ class Inputs(Lister, BaseClient):
                 data=resources_pb2.Data(concepts=[
                     resources_pb2.Concept(
                         id=f"id-{''.join(label.split(' '))}", name=label, value=1.)
+                    if not label_id else resources_pb2.Concept(id=label_id, name=label, value=1.)
                 ]))
         ]))
 
     return input_annot_proto
 
   @staticmethod
-  def get_mask_proto(input_id: str, label: str, polygons: List[List[float]]) -> Annotation:
+  def get_mask_proto(input_id: str, label: str, polygons: List[List[float]],
+                     label_id: str = None) -> Annotation:
     """Create an annotation proto for each polygon box, label input pair.
 
     Args:
         input_id (str): The input ID for the annotation to create.
-        label (str): annotation label
+        label (str): annotation label name
         polygons (List): Polygon x,y points iterable
+        label_id (str): annotation label ID
 
     Returns:
         An annotation object for the specified input ID.
@@ -537,6 +555,7 @@ class Inputs(Lister, BaseClient):
                 data=resources_pb2.Data(concepts=[
                     resources_pb2.Concept(
                         id=f"id-{''.join(label.split(' '))}", name=label, value=1.)
+                    if not label_id else resources_pb2.Concept(id=label_id, name=label, value=1.)
                 ]))
         ]))
 
@@ -726,16 +745,20 @@ class Inputs(Lister, BaseClient):
     request = service_pb2.PostAnnotationsRequest(
         user_app_id=self.user_app_id, annotations=batch_annot)
     response = self._grpc_request(self.STUB.PostAnnotations, request)
+    response_dict = MessageToDict(response)
     if response.status.code != status_code_pb2.SUCCESS:
       try:
-        self.logger.warning(f"Post annotations failed, status: {response.annotations[0].status}")
+        for annot in response_dict["annotations"]:
+          if annot['status']['code'] != status_code_pb2.ANNOTATION_SUCCESS:
+            self.logger.warning(f"Post annotations failed, status: {annot['status']}")
       except Exception:
-        self.logger.warning(f"Post annotations failed, status: {response.status.details}")
+        self.logger.warning(f"Post annotations failed due to {response.status}")
       finally:
         retry_upload.extend(batch_annot)
     else:
       if show_log:
         self.logger.info("\nAnnotations Uploaded\n%s", response.status)
+
     return retry_upload
 
   def _upload_batch(self, inputs: List[Input]) -> List[Input]: