ddi-fw 0.0.259__tar.gz → 0.0.261__tar.gz

{ddi_fw-0.0.259 → ddi_fw-0.0.261}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.259
+Version: 0.0.261
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.259 → ddi_fw-0.0.261}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.259"
+version = "0.0.261"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.259 → ddi_fw-0.0.261}/src/ddi_fw/langchain/chroma_storage.py

@@ -267,7 +267,13 @@ class ChromaVectorStoreManager(BaseVectorStoreManager):
         # Ensure all lists are not None and have the same length
         docs = results.get('documents', []) or []
         metadatas = results.get('metadatas', []) or []
-        embeddings = results.get('embeddings', []) or []
+        # embeddings = results.get('embeddings', []) or []
+        
+        embeddings = results.get('embeddings')
+        if isinstance(embeddings, np.ndarray):
+            pass  # Keep as-is
+        elif embeddings is None:
+            embeddings = []
 
         # Check if all lists have the same length
         if not (len(docs) == len(metadatas) == len(embeddings)):

{ddi_fw-0.0.259 → ddi_fw-0.0.261}/src/ddi_fw/langchain/faiss_storage.py

@@ -14,6 +14,7 @@ from langchain_core.embeddings import Embeddings
 from langchain_core.vectorstores import VectorStore
 from ddi_fw.utils import get_import
 from langchain.document_loaders import DataFrameLoader
+from collections import defaultdict
 
 class BaseVectorStoreManager(BaseModel):
     embeddings: Optional[Embeddings] = None
@@ -77,10 +78,15 @@ 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'):
-            type_dict[drug_type] = dict(zip(group['id'], group['embedding'].apply(lambda x: [x])))
+        type_dict = defaultdict(lambda: defaultdict(list))
+
+        grouped = df.groupby(['type', 'id'])['embedding'].apply(list)
+
+        for (drug_type, id), embeddings in grouped.items():
+            type_dict[drug_type][id] = embeddings
+
         return type_dict
     
     def generate_vector_store(self, docs, handle_empty='zero'):
@@ -258,7 +264,7 @@ 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-0.0.259 → ddi_fw-0.0.261}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.259
+Version: 0.0.261
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>