ddi-fw 0.0.258__tar.gz → 0.0.260__tar.gz

{ddi_fw-0.0.258 → ddi_fw-0.0.260}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.258
+Version: 0.0.260
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.258 → ddi_fw-0.0.260}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.258"
+version = "0.0.260"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.258 → ddi_fw-0.0.260}/src/ddi_fw/langchain/faiss_storage.py

@@ -1,4 +1,5 @@
 import faiss
+from langchain_text_splitters import TextSplitter
 import pandas as pd
 from uuid import uuid4
 from langchain_community.vectorstores.faiss import FAISS
@@ -45,6 +46,7 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
     persist_directory: str = Field(default="./embeddings/faiss")
     index: Any = None
     vector_store: Optional[FAISS] | None = None
+    text_splitter: Optional[TextSplitter] = None
     class Config:
         arbitrary_types_allowed = True
     # def generate_vector_store(self, docs):
@@ -75,6 +77,7 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
             dict: A dictionary with the structure {type: {drugbank_id: [embedding]}}.
         """
         self.load(self.persist_directory)
+        # df = self.as_dataframe(formatter_fn=custom_formatter)
         df = self.as_dataframe(formatter_fn=custom_formatter)
         type_dict = {}
         for drug_type, group in df.groupby('type'):
@@ -111,7 +114,9 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
 
         valid_docs = []
         valid_ids = []
-
+        if self.text_splitter:
+            docs = self.text_splitter.split_documents(docs)
+            
         for doc in docs:
             content = doc.page_content if hasattr(doc, 'page_content') else ""
             if content and content.strip():
@@ -254,7 +259,7 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
 
 def custom_formatter(document: Document, vector: np.ndarray) -> Dict[str, Any]:
     return {
-        "id": document.metadata.get("drugbank_id", None),
+        "id": document.metadata.get("id", None),
         "type": document.metadata.get("type", None),
         "embedding": vector
     }

{ddi_fw-0.0.258 → ddi_fw-0.0.260}/src/ddi_fw/utils/kaggle.py

@@ -22,7 +22,8 @@ def create_kaggle_dataset(base_path: str, collections: list):
         # Step 2: Get metadata for the current folder
         model_info = next((c for c in collections if c['id'] == folder_name), None)
         if model_info is None:
-            continue  # Skip if model info is not found
+            raise FileNotFoundError(f"Model info for {folder_name} not exists")
+            # continue  # Skip if model info is not found
         
         title = model_info['kaggle_title']
         

{ddi_fw-0.0.258 → ddi_fw-0.0.260}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.258
+Version: 0.0.260
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>