ddi-fw 0.0.255__tar.gz → 0.0.257__tar.gz

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.255
+Version: 0.0.257
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.255"
+version = "0.0.257"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/src/ddi_fw/datasets/core.py

@@ -379,7 +379,7 @@ class TextDatasetMixin(BaseModel):
             if self.vector_store_manager is not None:
                 self.embedding_dict = self.vector_store_manager.initialize_embedding_dict()
             # self.embedding_dict = self.__initialize_embedding_dict()    
-            self.__calculate_embedding_size()
+        self.__calculate_embedding_size()
          
 
 

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/src/ddi_fw/langchain/chroma_storage.py

@@ -86,7 +86,7 @@ def split_dataframe_indices(df, min_size=512):
 
 class ChromaVectorStoreManager(BaseVectorStoreManager):
     collection_name: str = Field(default="default")
-    persist_directory: str = Field(default="./chroma_db")
+    persist_directory: str = Field(default=".embeddings/chroma_db")
     text_splitter: Optional[TextSplitter] = None
     batch_size: int = Field(default=1024)
     vector_store: Optional[Chroma] | None = None
@@ -152,7 +152,9 @@ class ChromaVectorStoreManager(BaseVectorStoreManager):
     #                 self.vector_store.persist()
     #                 print(f"{page_content_column}, size:{len(split_docs_chunk)}")
 
-
+    @staticmethod
+    def get_persist_dir(base_dir, suffix, config=None):
+        return f"{base_dir}"
 
     def generate_vector_store(self, docs: List[Document]):
         self.vector_store = Chroma(

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/src/ddi_fw/langchain/faiss_storage.py

@@ -35,9 +35,14 @@ class BaseVectorStoreManager(BaseModel):
     
     def as_dataframe(self, formatter_fn: Optional[Callable[[Document, np.ndarray], Dict[str, Any]]] = None) -> pd.DataFrame:
         raise NotImplementedError("This method should be implemented by subclasses.")
+    
+    @staticmethod
+    def get_persist_dir(base_dir, suffix, config=None):
+        raise NotImplementedError("Subclasses must implement get_persist_dir.")
+     
 
 class FaissVectorStoreManager(BaseVectorStoreManager):
-    persist_directory: str = Field(default="./embeddings")
+    persist_directory: str = Field(default="./embeddings/faiss")
     index: Any = None
     vector_store: Optional[FAISS] | None = None
     class Config:
@@ -57,6 +62,10 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
     #     uuids = [str(uuid4()) for _ in range(len(docs))]
     #     self.vector_store.add_documents(documents=docs, ids=uuids)
     
+    @staticmethod
+    def get_persist_dir(base_dir, suffix, config=None):
+        return f"{base_dir}/{suffix}"
+    
     def initialize_embedding_dict(self, **kwargs):
         """
         Initializes a dictionary where keys are types (e.g., 'description', 'indication'),
@@ -353,14 +362,14 @@ def load_configuration(config_file):
 #             # Optionally persist/save
 #             vector_store_manager.save(persist_dir)
 
-
+# persist_directory config'den alınsın
 def generate_embeddings(
     docs,
     vector_store_manager_type:Type[BaseVectorStoreManager],
     config_file:Optional[str],
     new_model_names:Optional[List],
     collections:Optional[Dict],
-    persist_directory="embeddings",
+    persist_directory="./embeddings",
 ):
     """
     Generate embeddings for collections based on a configuration file.
@@ -420,7 +429,10 @@ def generate_embeddings(
         
         for text_splitter, suffix in zip(text_splitters, text_splitters_suffixes):
             print(f"{id}_{suffix}")
-            persist_dir = f'{persist_directory}/{id}/{suffix}'
+            # persist_dir = f'{persist_directory}/{id}/{suffix}'
+            # persist_dir = f'{persist_directory}/{suffix}'
+            persist_dir = vector_store_manager_type.get_persist_dir(persist_directory, suffix, collection_config)
+
             # Prepare manager parameters
             manager_params = {
                 "collection_name": f"{id}_{suffix}",

{ddi_fw-0.0.255 → ddi_fw-0.0.257}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.255
+Version: 0.0.257
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>