ddi-fw 0.0.47__tar.gz → 0.0.49__tar.gz

{ddi_fw-0.0.47 → ddi_fw-0.0.49}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.47
+Version: 0.0.49
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.47 → ddi_fw-0.0.49}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.47"
+version = "0.0.49"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.47 → ddi_fw-0.0.49}/src/ddi_fw/datasets/core.py

@@ -379,13 +379,13 @@ class BaseDataset(ABC):
                 # return np.hstack(
                 #     (value[row['id1']], value[row['id2']]), dtype=np.float16)
 
-        def x_fnc(row, embedding_column, embeddings_after_pooling):
-            if row['id1'] in self.embedding_dict[embedding_column]:
-                v1 = embeddings_after_pooling[embedding_column][row['id1']]
+        def x_fnc(row, embeddings_after_pooling):
+            if row['id1'] in embeddings_after_pooling:
+                v1 = embeddings_after_pooling[row['id1']]
             else:
                 v1 = np.zeros(self.embedding_size)
-            if row['id2'] in self.embedding_dict[embedding_column]:
-                v2 = embeddings_after_pooling[embedding_column][row['id2']]
+            if row['id2'] in embeddings_after_pooling:
+                v2 = embeddings_after_pooling[row['id2']]
             else:
                 v2 = np.zeros(self.embedding_size)
             return np.float16(np.hstack(
@@ -404,7 +404,7 @@ class BaseDataset(ABC):
                 v) for k, v in self.embedding_dict[embedding_column].items()}
             # column_embeddings_dict = embedding_values[embedding_column]
             self.ddis_df[embedding_column+'_embedding'] = self.ddis_df.apply(
-                x_fnc, args=(embedding_column, embeddings_after_pooling), axis=1)
+                x_fnc, args=(embeddings_after_pooling,), axis=1)
 
         self.dataframe = self.ddis_df.copy()
         self.dataframe['class'] = list(classes)

{ddi_fw-0.0.47 → ddi_fw-0.0.49}/src/ddi_fw/datasets/embedding_generator_new.py

@@ -17,7 +17,7 @@ from sentence_transformers import SentenceTransformer, util
 
 from typing import Any, Dict, List, Optional
 from langchain_core.embeddings import Embeddings
-from pydantic import BaseModel, ConfigDict, Field, SecretStr
+from pydantic import BaseModel, ConfigDict, Field, SecretStr, computed_field
 from langchain.embeddings import SentenceTransformerEmbeddings
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
@@ -56,7 +56,7 @@ class SumPoolingStrategy(PoolingStrategy):
         return np.sum(embeddings, axis=0)
 
 
-class SentenceTransformerDecorator(BaseModel, Embeddings):
+class SentenceTransformerDecorator(Embeddings):
     def __init__(self, model_name="all-MiniLM-L6-v2", **kwargs: Any):
         self.embeddings = SentenceTransformerEmbeddings(model_name=model_name)
 
@@ -67,7 +67,7 @@ class SentenceTransformerDecorator(BaseModel, Embeddings):
         return self.embeddings.embed_query(text)
 
 
-class PretrainedEmbeddings(BaseModel, Embeddings):
+class PretrainedEmbeddings( Embeddings):
     def __init__(self, model_name):
         self.mmodel_name = model_name
         self.model = AutoModel.from_pretrained(model_name)
@@ -88,11 +88,23 @@ class PretrainedEmbeddings(BaseModel, Embeddings):
 
 
 class SBertEmbeddings(BaseModel, Embeddings):
-    def __init__(self, model_name):
-        self.model = SentenceTransformer(model_name)
+    # class Config:
+    #     arbitrary_types_allowed = True
+
+    model_config = ConfigDict(
+        arbitrary_types_allowed = True,
+        protected_namespaces=()
+    )
+
+    model_name:str
+
+    @computed_field
+    @property
+    def model(self) -> SentenceTransformer:
+        return SentenceTransformer(self.model_name)
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]:
-        return self.model.encode(texts)
+        return self.model.encode(texts).tolist()
 
     def embed_query(self, text: str) -> List[float]:
         return self.embed_documents([text])[0]

{ddi_fw-0.0.47 → ddi_fw-0.0.49}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.47
+Version: 0.0.49
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>