ddi-fw 0.0.105__tar.gz → 0.0.107__tar.gz

{ddi_fw-0.0.105 → ddi_fw-0.0.107}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.105
+Version: 0.0.107
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.105 → ddi_fw-0.0.107}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.105"
+version = "0.0.107"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.105 → ddi_fw-0.0.107}/src/ddi_fw/langchain/storage.py

@@ -10,6 +10,7 @@ from langchain.docstore.document import Document
 from langchain.document_loaders import DataFrameLoader
 
 from langchain.text_splitter import TextSplitter
+import numpy as np
 
 # from langchain_community.document_loaders.hugging_face_dataset import HuggingFaceDatasetLoader
 from ddi_fw.langchain.embeddings import SBertEmbeddings
@@ -24,6 +25,34 @@ def load_configuration(config_file):
         config = json.load(f)
     return config
 
+def split_dataframe(df, min_size=512, max_size=1024):
+    # Ensure the total size of the DataFrame is larger than the desired split size
+    total_size = len(df)
+    
+    # Check if the dataframe is large enough
+    if total_size <= min_size:
+       return df
+    
+    # List to store partial DataFrames
+    partial_dfs = []
+
+    # Start splitting the DataFrame
+    start_idx = 0
+    
+    while start_idx < total_size:
+        # Calculate the size of the next chunk: it should be between min_size and max_size
+        chunk_size = np.random.randint(min_size, max_size + 1)
+        
+        # Ensure that the chunk size does not exceed the remaining data
+        chunk_size = min(chunk_size, total_size - start_idx)
+        
+        # Create the partial DataFrame and append to the list
+        partial_dfs.append(df.iloc[start_idx:start_idx + chunk_size])
+        
+        # Update the start index for the next chunk
+        start_idx += chunk_size
+    
+    return partial_dfs
 
 class DataFrameToVectorDB:
     def __init__(self,
@@ -83,11 +112,15 @@ class DataFrameToVectorDB:
         Store function to handle both full and partial dataframe processing.
         """
         if partial_df_size:
-            # Process the dataframe in chunks if partial_df_size is provided
-            for i in range(0, len(df), partial_df_size):
-                batch = df[i: i + partial_df_size]
-                self.store_documents(df=batch, columns=columns,
+            partial_dfs  = split_dataframe(df, min_size = partial_df_size)
+            for partial_df in partial_dfs:
+                self.store_documents(df=partial_df, columns=columns,
                                      page_content_columns=page_content_columns)
+            # Process the dataframe in chunks if partial_df_size is provided
+            # for i in range(0, len(df), partial_df_size):
+            #     batch = df[i: i + partial_df_size]
+            #     self.store_documents(df=batch, columns=columns,
+            #                          page_content_columns=page_content_columns)
         else:
             # Process the entire dataframe if no partial_df_size is specified
             self.store_documents(df=df, columns=columns,

{ddi_fw-0.0.105 → ddi_fw-0.0.107}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.105
+Version: 0.0.107
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>