ddi-fw 0.0.242__py3-none-any.whl → 0.0.243__py3-none-any.whl

ddi_fw/langchain/chroma_storage.py

@@ -89,12 +89,12 @@ class ChromaVectorStoreManager(BaseVectorStoreManager):
     persist_directory: str = Field(default="./chroma_db")
     text_splitter: Optional[TextSplitter] = None
     batch_size: int = Field(default=1024)
+    vector_store: Optional[Chroma] | None = None
 
     class Config:
         arbitrary_types_allowed = True
         
 
-
     # def __split_docs(self, documents):
     #     docs = self.text_splitter.split_documents(documents)
     #     return docs
@@ -225,8 +225,8 @@ class ChromaVectorStoreManager(BaseVectorStoreManager):
             
     def initialize_embedding_dict(self, **kwargs):
         column_embedding_configs = kwargs.get("column_embedding_configs")
-        vector_db_persist_directory = kwargs.get("vector_db_persist_directory")
-        vector_db_collection_name = kwargs.get("vector_db_collection_name")
+        # vector_db_persist_directory = kwargs.get("vector_db_persist_directory")
+        # vector_db_collection_name = kwargs.get("vector_db_collection_name")
         embedding_dict = defaultdict(lambda: defaultdict(list))
         if column_embedding_configs:
             for item in column_embedding_configs:
@@ -234,8 +234,8 @@ class ChromaVectorStoreManager(BaseVectorStoreManager):
                 col_db_dir = item["vector_db_persist_directory"]
                 col_db_collection = item["vector_db_collection_name"]
                 self.__create_or_update_embeddings__(embedding_dict, col_db_dir, col_db_collection, col)
-        elif vector_db_persist_directory:
-            self.__create_or_update_embeddings__(embedding_dict, vector_db_persist_directory, vector_db_collection_name)
+        elif self.persist_directory:
+            self.__create_or_update_embeddings__(embedding_dict, self.persist_directory, self.collection_name)
         else:
             logging.warning("There is no configuration of Embeddings")
             raise ValueError(

ddi_fw/langchain/faiss_storage.py

@@ -10,9 +10,11 @@ from langchain_core.embeddings import Embeddings
 
 from pydantic import BaseModel, Field
 from langchain_core.embeddings import Embeddings
+from langchain_core.vectorstores import VectorStore
 
 class BaseVectorStoreManager(BaseModel):
-    embeddings: Embeddings
+    embeddings: Optional[Embeddings] = None
+    vector_store: Optional[VectorStore]|None = None
 
     class Config:
         arbitrary_types_allowed = True
@@ -34,8 +36,7 @@ class BaseVectorStoreManager(BaseModel):
 
 class FaissVectorStoreManager(BaseVectorStoreManager):
     index: Any = None
-    vector_store: Any = None
-
+    vector_store: Optional[FAISS] | None = None
     class Config:
         arbitrary_types_allowed = True
     # def generate_vector_store(self, docs):
@@ -73,7 +74,8 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
                 - 'skip': skip the document
                 - 'error': raise ValueError
         """
-
+        if self.embeddings is None:
+            raise ValueError("Embeddings must be initialized before generating vector store.")
         # Step 1: Get embedding dimension from a sample input
         sample_embedding = self.embeddings.embed_query("hello world")
         dimension = len(sample_embedding)
@@ -126,6 +128,7 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
             raise ValueError("No vector store to save.")
 
     def load(self, path):
+        #self.embeddings
         self.vector_store = FAISS.load_local(
             path, self.embeddings, allow_dangerous_deserialization=True
         )

{ddi_fw-0.0.242.dist-info → ddi_fw-0.0.243.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.242
+Version: 0.0.243
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.242.dist-info → ddi_fw-0.0.243.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=xGNaTEZCUxyc_aT1zvzVWGRfsj-9VXqMvPKtV_G7ChA,399
-ddi_fw/langchain/chroma_storage.py,sha256=I8xoqlc2K4gJdOUn5b33mGGMPFKYG3UiptY2HeM34_c,15483
+ddi_fw/langchain/chroma_storage.py,sha256=7LSUhdiPdQHZvKC_NapOeVbHtS71iE5ABZVTrI0YQ-A,15520
 ddi_fw/langchain/embeddings.py,sha256=eEWy4okcjdhUJHi4N48Wd8XauPXyeaQVLUdNWEvtEcY,6754
-ddi_fw/langchain/faiss_storage.py,sha256=H--yYOmHX7nr34THNojqP_qhGXd-kMkhzzWDbMMeoqo,8923
+ddi_fw/langchain/faiss_storage.py,sha256=b-PStwJHeRl9ZYGC7ql5p5ak1Xk2-A6TTEL1UqmhxVI,9220
 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=QQQGhCti653BdU343Ag1bH_g1fzi2hlic7dgNy7otjE,7694
 ddi_fw/vectorization/idf_helper.py,sha256=_Gd1dtDSLaw8o-o0JugzSKMt9FpeXewTh4wGEaUd4VQ,2571
-ddi_fw-0.0.242.dist-info/METADATA,sha256=jq8Op7HG_u5PE0DjELixnPMKwEl6mUkNtPTyQ5uBWU8,2632
-ddi_fw-0.0.242.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ddi_fw-0.0.242.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.242.dist-info/RECORD,,
+ddi_fw-0.0.243.dist-info/METADATA,sha256=li6Qy_fruHkWcTEbIx2-htRPwPOQOe6Ip4tGhFYJorg,2632
+ddi_fw-0.0.243.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ddi_fw-0.0.243.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.243.dist-info/RECORD,,