ddi-fw 0.0.151__tar.gz → 0.0.152__tar.gz

{ddi_fw-0.0.151 → ddi_fw-0.0.152}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.151
+Version: 0.0.152
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.151 → ddi_fw-0.0.152}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.151"
+version = "0.0.152"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.151 → ddi_fw-0.0.152}/src/ddi_fw/pipeline/pipeline.py

@@ -35,20 +35,18 @@ class Pipeline(BaseModel):
     model: Optional[Any] = None
     multi_modal:  Optional[Any] = None
     use_mlflow: bool = True
-    _items: List = []
-    _train_idx_arr: List | None = []
-    _val_idx_arr: List | None = []
-
+    _items:List=[]
+    _train_idx_arr:List|None=[]
+    _val_idx_arr:List|None=[]
+    
     @property
     def items(self) -> List:
         return self._items
-
     @property
-    def train_idx_arr(self) -> List | None:
+    def train_idx_arr(self) -> List|None:
         return self._train_idx_arr
-
     @property
-    def val_idx_arr(self) -> List | None:
+    def val_idx_arr(self) -> List|None:
         return self._val_idx_arr
 
     class Config:
@@ -127,15 +125,12 @@ class Pipeline(BaseModel):
                 print(
                     f"Embeddings of {column} are calculated from {vector_db_collection_name}")
 
-            # if metadatas == None or embeddings == None:
-            if 'embeddings' not in dictionary or 'metadatas' not in dictionary or not dictionary['embeddings'] or not dictionary['metadatas']:
-                raise ValueError(
-                    "The collection does not contain embeddings or metadatas.")
-
             # Populate the embedding dictionary with embeddings from the vector database
             metadatas = dictionary["metadatas"]
             embeddings = dictionary["embeddings"]
-
+            if metadatas is None or embeddings is None:
+                raise ValueError(
+                    "The collection does not contain embeddings or metadatas.")
             for metadata, embedding in zip(metadatas, embeddings):
                 embedding_dict[metadata["type"]
                                ][metadata["id"]].append(embedding)
@@ -189,8 +184,7 @@ class Pipeline(BaseModel):
         if issubclass(self.dataset_type, TextDatasetMixin):
             key, value = next(iter(embedding_dict.items()))
             embedding_size = value[next(iter(value))][0].shape[0]
-            pooling_strategy = self.embedding_pooling_strategy_type(
-            ) if self.embedding_pooling_strategy_type else None
+            pooling_strategy = self.embedding_pooling_strategy_type() if self.embedding_pooling_strategy_type  else None
 
             dataset = self.dataset_type(
                 embedding_dict=embedding_dict,

{ddi_fw-0.0.151 → ddi_fw-0.0.152}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.151
+Version: 0.0.152
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>