ddi-fw 0.0.253__tar.gz → 0.0.255__tar.gz

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.253
+Version: 0.0.255
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/pyproject.toml

@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.253"
+version = "0.0.255"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/src/ddi_fw/langchain/__init__.py

@@ -1,5 +1,5 @@
 from ..langchain.embeddings import PoolingStrategy,SumPoolingStrategy,MeanPoolingStrategy,SentenceTransformerDecorator,PretrainedEmbeddings,SBertEmbeddings
 from .sentence_splitter import SentenceSplitter
-from .storage import DataFrameToVectorDB, generate_embeddings
-from .faiss_storage import BaseVectorStoreManager, FaissVectorStoreManager
+# from .storage import DataFrameToVectorDB, generate_embeddings
+from .faiss_storage import BaseVectorStoreManager, FaissVectorStoreManager,generate_embeddings
 from .chroma_storage import ChromaVectorStoreManager

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/src/ddi_fw/langchain/faiss_storage.py

@@ -390,7 +390,7 @@ def generate_embeddings(
         partial_df_size = collection_config.get('partial_dataframe_size')
         columns = collection_config.get('columns')
         page_content_columns = collection_config.get('page_content_columns')
-        persist_dir = f'{persist_directory}/{id}'
+        
 
         # Load embedding model
         try:
@@ -417,10 +417,10 @@ def generate_embeddings(
                 text_splitters_suffixes.append(suffix)
             except Exception as e:
                 raise Exception(f"Unknown text splitter: {text_splitter_type}") from e
-
+        
         for text_splitter, suffix in zip(text_splitters, text_splitters_suffixes):
             print(f"{id}_{suffix}")
-
+            persist_dir = f'{persist_directory}/{id}/{suffix}'
             # Prepare manager parameters
             manager_params = {
                 "collection_name": f"{id}_{suffix}",

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/src/ddi_fw/vectorization/feature_vector_generation.py

@@ -3,7 +3,6 @@ import numpy as np
 import pandas as pd
 from scipy.spatial.distance import pdist, squareform
 from sklearn.preprocessing import MultiLabelBinarizer
-import cupy as cp
 
 # todo pd.unique kullan
 def find_distinct_elements(frame):
@@ -97,6 +96,12 @@ class SimilarityMatrixGenerator:
         Returns:
         cp.ndarray: A 2D CuPy array containing the pairwise Jaccard similarity.
         """
+        try:
+            import cupy as cp
+        except ImportError:
+            raise ImportError("cupy is required for GPU Jaccard similarity computation. Please install it with 'pip install cupy'.")
+                
+                
         if not ((matrix == 0) | (matrix == 1)).all():
             raise ValueError("Input matrix must be binary (contain only 0s and 1s).")
         matrix = cp.asarray(matrix)

{ddi_fw-0.0.253 → ddi_fw-0.0.255}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ddi_fw
-Version: 0.0.253
+Version: 0.0.255
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>