layernext-beta 2.4.0b2__tar.gz → 2.4.0b3__tar.gz

{layernext-beta-2.4.0b2/layernext_beta.egg-info → layernext-beta-2.4.0b3}/PKG-INFO

@@ -1,10 +1,13 @@
 Metadata-Version: 2.1
 Name: layernext-beta
-Version: 2.4.0b2
+Version: 2.4.0b3
 Summary: LayerNext Python SDK
+Home-page: UNKNOWN
 Author: LayerNext
 Author-email: <support@layernext.ai>
+License: UNKNOWN
 Keywords: python,datalake,datasetsync,ai,annotation,layernext,layernext,machine learning
+Platform: UNKNOWN
 Classifier: Development Status :: 1 - Planning
 Classifier: Intended Audience :: Developers
 Classifier: Programming Language :: Python :: 3
@@ -37,3 +40,5 @@ url = 'https://api.xxxx.layernext.ai'
 client = layernext.LayerNextClient(api_key, secret, url)
 
 ```
+
+

{layernext-beta-2.4.0b2 → layernext-beta-2.4.0b3}/layernext/__init__.py

@@ -8,7 +8,7 @@ from layernext.datalake.constants import (AnnotationUploadType, ItemType, JobSta
                                           SortFieldName, SortOrder, AnnotationShapeType)
 from deprecated import deprecated
 
-__version__ = '2.4.0b2'
+__version__ = '2.4.0b3'
 
 
 class LayerNextClient:
@@ -784,6 +784,8 @@ class LayerNextClient:
                 modified_sort["sortByField"] = SortField.SIZE.value
             elif field == SortFieldName.VIDEO_INDEX.value:
                 modified_sort["sortByField"] = SortField.VIDEO_INDEX.value
+            elif field == SortFieldName.TEXT_SCORE.value:
+                modified_sort["sortByField"] = SortField.TEXT_SCORE.value
             else:
                 valid_fields: list = self.get_valid_sort_fields()
                 raise Exception(
@@ -802,7 +804,9 @@ class LayerNextClient:
             "date": {},
             "tags": [],
             "labels": [],
-            "metadata": {}
+            "metadata": {},
+            "keywords": [],
+            "categories": []
         }
         if "annotation_types" in filter:
             if "human" in filter["annotation_types"]:
@@ -815,6 +819,10 @@ class LayerNextClient:
             return_filter["date"]["toDate"] = filter["to_date"]
         if "from_date" in filter:
             return_filter["date"]["fromDate"] = filter["from_date"]
+        if "keywords" in filter:
+            return_filter["keywords"] = filter["keywords"]
+        if "categories" in filter:
+            return_filter["categories"] = filter["categories"]
         return return_filter
 
     """
@@ -2239,7 +2247,7 @@ class LayerNextClient:
     @filter: {date: {fromDate: "", toDate: ""}, "annotation_types": ["human", "raw", "machine"]}
     @page_index - index of the page
     @page_size - size of the page, maximum = 1000
-    @sort_order: {sort_by_field:"date_modified"/"date_created"/"name"/"size"/"video_index", sort_order: "ASC/DESC"}
+    @sort_order: {sort_by_field:"date_modified"/"date_created"/"name"/"size"/"video_index"/"text_score", sort_order: "ASC/DESC"}
     """
 
     def get_item_list_from_datalake(
@@ -2756,7 +2764,15 @@ class LayerNextClient:
             unique_names,
             model_name
         ) 
-    
+    """ 
+    Use to create or update job in metalake
+    @session_id :  string - session id
+    @job_name   :  string - job name 
+    @job_type   :  enum   - type of job (enum)
+    @progress   :  int    - progress of created or update job
+    @status     :  enum   - complete, in_progress.. (enum)
+    @job_detail :  dict   - job specific details
+    """
     def create_or_update_job(
         self, 
         session_id:str, 
@@ -2782,6 +2798,31 @@ class LayerNextClient:
             status, 
             job_detail
         )
+
+    """
+    Use to find documents matching for given keywords and categories
+    @unique_name:  List[str] - unique name of the required embeddings
+    @model_name: List[str] - model name of the required embeddings
+    @page_index: int - index of the page
+    @page_size: int - size of the page, maximum = 1000
+    """
+    def find_documents(
+        self,
+        keywords: List[str],
+        categories: List[str],
+        page_index=0,
+        page_size=1,
+    ):
+        return self.get_item_list_from_datalake(
+            item_type='other',
+            filter={
+                "keywords": keywords,
+                "categories": categories
+            },
+            page_index=page_index,
+            page_size=page_size,
+            sort_order={"sort_by_field": "text_score", "sort_order": "DESC"}
+        )
     
 
     """
@@ -2858,4 +2899,56 @@ class LayerNextClient:
             return {
                 "isSuccess": False,
                 "error": "Failed to get selection id"
-            }
+            }
+    
+
+    """
+    find chunk by search keys from text
+    @param search_key_list - list of search keys
+    @param unique_name_list - list of unique names
+    return array of chunks
+    example search_key_list - ["tax", "discount"]
+    example unique_name_list - ["abc.pdf", "def.pdf"]
+    example response - [
+        '# 000009752 Description Date Credited Amount Deposit Ref Nbr: 130012345 05-15 $3,615.08 Total Deposits & Other Credits $3,615.08 ATM Withdrawals & Debits Account # 000009752 Description Tran Date Date Paid Amount ATM', 
+        'Debits $20.00 ChecksPaid Account # 000009752 Date Paid Check Number Amount Reference Number 05-12 1001 75.00 00012576589 05-18 1002 30.00 00036547854 05-24 1003 200.00 00094613547 Total Checks Paid', 
+        'Purchases & Debits -0.00 Withdrawals & Other Debits -0.00 Checks Paid -200.00 Ending Balance on June 5, 2003 $10,521.19 Deposits & Other Credits Account # 000009752 Description Date Credited Amount Deposit Ref'
+    ]
+    """
+    def find_chunk(
+            self,
+            search_key_list: [str],
+            unique_name_list: List[str],
+        ):
+        print(f'find chunk - search_key_list: {search_key_list}, unique_name_list: {unique_name_list}')
+
+        _datalake_client = datalake.DatalakeClient(
+            self.encoded_key_secret, self.layernext_url)
+
+        response = _datalake_client.find_chunk(
+            search_key_list, unique_name_list)
+        
+        return response 
+    
+
+    """ 
+    Use to get data dictionary
+    """
+    def get_data_dictionary(self):
+        _datalake_client = datalake.DatalakeClient(
+            self.encoded_key_secret, self.layernext_url)
+
+        return _datalake_client.get_data_dictionary()
+    
+    
+    """ 
+    Use to execute mongo db query
+    @function     :  This can be 'aggregate', 'find', 'updateMany', etc.
+    @input_data   :  The input parameters for the MongoDB function, provided as a JSON-like dictionary or list 
+    @collection   :  The name of the MongoDB collection on which the query is to be run
+    """
+    def execute_mongo_query(self, function, input_data, collection):
+        _datalake_client = datalake.DatalakeClient(
+            self.encoded_key_secret, self.layernext_url)
+
+        return _datalake_client.execute_mongo_query(function, input_data, collection)

{layernext-beta-2.4.0b2 → layernext-beta-2.4.0b3}/layernext/datalake/__init__.py

@@ -576,6 +576,9 @@ class DatalakeClient:
 
         return res
     
+    """
+    update or create virtual collection
+    """
     def update_virtual_collection(self, virtual_collection_name: str = None,
             virtual_collection_id: str = None,
             selection_id: str = None):
@@ -592,3 +595,53 @@ class DatalakeClient:
         res = self.datalake_interface.update_virtual_collection(payload)
 
         return res
+
+    """
+    find chunk by search keys from text
+    """
+    def find_chunk(self, search_key_list: [str],
+            unique_name_list: List[str]):
+        payload = {
+            "searchKeys": search_key_list,
+            "uniqueNames": unique_name_list
+        }
+
+        res = self.datalake_interface.find_chunk(payload)
+
+        return res
+    """
+    Use to get data dictionary
+    """
+    def get_data_dictionary(self):
+        res = self.datalake_interface.get_data_dictionary()
+        if "isSuccess" in res and res["isSuccess"] == False:
+            raise Exception(res["message"])
+        if 'isSuccess' in res:
+            if res["isSuccess"] == False:
+                message = res['message']
+                print(f'Success false with. message: {message}')
+                raise Exception(message)
+            else:
+                print('Successfully extract the dictionary data')
+                return res['data']
+        else:
+            print('Request return with unexpected results')
+            raise Exception('Request return with unexpected results')
+        
+    """ 
+    Use to execute mongo db query
+    @function     :  This can be 'aggregate', 'find', 'updateMany', etc.
+    @input_data   :  The input parameters for the MongoDB function, provided as a JSON-like dictionary or list 
+    @collection   :  The name of the MongoDB collection on which the query is to be run
+    """
+    def execute_mongo_query(self, function, input_data, collection):
+
+        payload = {
+            'function': function,
+            'query': input_data,
+            'collection': collection
+        }
+        res = self.datalake_interface.execute_mongo_query(payload)
+        return res
+
+        

{layernext-beta-2.4.0b2 → layernext-beta-2.4.0b3}/layernext/datalake/constants.py

@@ -85,7 +85,8 @@ class SortFieldName(Enum):
     DATE_CREATED = "date_created"
     NAME = "name"
     SIZE = "size"
-    VIDEO_INDEX = "video_index"
+    VIDEO_INDEX = "video_index",
+    TEXT_SCORE = "text_score"
 
 
 class SortField(Enum):
@@ -93,7 +94,8 @@ class SortField(Enum):
     DATE_CREATED = 2
     NAME = 3
     SIZE = 4
-    VIDEO_INDEX = 6
+    VIDEO_INDEX = 6,
+    TEXT_SCORE = 7
 
 
 class SortOrder(Enum):