ddi-fw 0.0.259__py3-none-any.whl → 0.0.261__py3-none-any.whl

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/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.dist-info → ddi_fw-0.0.261.dist-info}/METADATA

@@ -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.dist-info → ddi_fw-0.0.261.dist-info}/RECORD

@@ -4,9 +4,9 @@ ddi_fw/datasets/dataset_splitter.py,sha256=8H8uZTAf8N9LUZeSeHOMawtJFJhnDgUUqFcnl
 ddi_fw/datasets/db_utils.py,sha256=xRj28U_uXTRPHcz3yIICczFUHXUPiAOZtAj5BM6kH44,6465
 ddi_fw/datasets/setup_._py,sha256=khYVJuW5PlOY_i_A16F3UbSZ6s6o_ljw33Byw3C-A8E,1047
 ddi_fw/langchain/__init__.py,sha256=Kk2Yr7vemjy9MNB_ImAWET808zt1JkLsWqsgEXpVPJk,421
-ddi_fw/langchain/chroma_storage.py,sha256=Xh0p2d8bI9U-NYkhuu7fLtsgbExP7phkqPE17PBYWd4,15634
+ddi_fw/langchain/chroma_storage.py,sha256=63_UojxGLbytgm4g2BZWdo2hvnWiVjrs4mZjxNxdkV8,15837
 ddi_fw/langchain/embeddings.py,sha256=eEWy4okcjdhUJHi4N48Wd8XauPXyeaQVLUdNWEvtEcY,6754
-ddi_fw/langchain/faiss_storage.py,sha256=VCKvBB50t3krO5isqRMSPT5yFB9d9s1jQUWiWsmOiak,18481
+ddi_fw/langchain/faiss_storage.py,sha256=1G_lJ4_pKGEp5SlKBYUZWxEnGHuq3JGmvKeDaEztX8w,18646
 ddi_fw/langchain/sentence_splitter.py,sha256=h_bYElx4Ud1mwDNJfL7mUwvgadwKX3GKlSzu5L2PXzg,280
 ddi_fw/langchain/storage.py,sha256=OizKyWm74Js7T6Q9kez-ulUoBGzIMFo4R46h4kjUyIM,11200
 ddi_fw/ml/__init__.py,sha256=FteYEawCkVQOaK-cTv2VrHZ2ZnfeFr31BD6VucO7_DQ,268
@@ -38,7 +38,7 @@ ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,55
 ddi_fw/vectorization/__init__.py,sha256=LcJOpLVoLvHPDw9phGFlUQGeNcST_zKV-Oi1Pm5h_nE,110
 ddi_fw/vectorization/feature_vector_generation.py,sha256=92bhZw4Qxh0hqPK-bPHm9bUO7pg2p4cStQYtVrOtetE,7919
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.259.dist-info/METADATA,sha256=PJfj1EQLb65en5lYWyhYA7izycUHXLEF_MlCllV6qwg,2623
-ddi_fw-0.0.259.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ddi_fw-0.0.259.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.259.dist-info/RECORD,,
+ddi_fw-0.0.261.dist-info/METADATA,sha256=P0xexzVAJfggUMTjYeClVcqkap4mhjRzzLJCfDR86II,2623
+ddi_fw-0.0.261.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ddi_fw-0.0.261.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.261.dist-info/RECORD,,