ddi-fw 0.0.121__py3-none-any.whl → 0.0.123__py3-none-any.whl

ddi_fw/datasets/core.py

@@ -56,7 +56,7 @@ class BaseDataset(ABC):
     def produce_inputs(self):
         items = []
         y_train_label, y_test_label = stack(self.y_train), stack(self.y_test)
-        self.__similarity_related_columns__.append("smile_2") #TODO
+        # self.__similarity_related_columns__.append("smile_2") #TODO
         for column in self.__similarity_related_columns__:
             train_data, test_data = stack(
                 self.X_train[column]), stack(self.X_test[column])

ddi_fw/pipeline/pipeline.py

@@ -67,9 +67,13 @@ class Pipeline:
             if column == None:
                 dictionary = collection.get(
                     include=['embeddings', 'metadatas'])
+                print(
+                    f"Embeddings are calculated from {vector_db_collection_name}")
             else:
                 dictionary = collection.get(include=['embeddings', 'metadatas'], where={
                                             "type": {"$eq": f"{column}"}})
+                print(
+                    f"Embeddings of {column} are calculated from {vector_db_collection_name}")
             # Populate the embedding dictionary with embeddings from the vector database
             for metadata, embedding in zip(dictionary['metadatas'], dictionary['embeddings']):
                 embedding_dict[metadata["type"]
@@ -88,9 +92,7 @@ class Pipeline:
                 kwargs[k] = v
         if self.embedding_dict == None:
             embedding_dict = defaultdict(lambda: defaultdict(list))
-            if self.vector_db_persist_directory:
-                self.__create_or_update_embeddings__(
-                    embedding_dict, self.vector_db_persist_directory, self.vector_db_collection_name)
+            # TODO find more effective solution
 
             if self.column_embedding_configs:
                 for item in self.column_embedding_configs:
@@ -99,8 +101,14 @@ class Pipeline:
                     col_db_collection = item["vector_db_collection_name"]
                     self.__create_or_update_embeddings__(
                         embedding_dict, col_db_dir, col_db_collection, col)
-                    print(
-                        f"Embedings of {col} is calculated from {col_db_collection}")
+                    
+            elif self.vector_db_persist_directory:
+                self.__create_or_update_embeddings__(
+                    embedding_dict, self.vector_db_persist_directory, self.vector_db_collection_name)
+                
+            else:
+                print(
+                    f"There is no configuration of Embeddings")
 
         # if self.embedding_dict == None:
         #     if self.vector_db_persist_directory:

{ddi_fw-0.0.121.dist-info → ddi_fw-0.0.123.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.121
+Version: 0.0.123
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
@@ -46,7 +46,6 @@ Requires-Dist: py7zr==0.22.0
 Requires-Dist: openai>=1.52.2
 Requires-Dist: langchain>=0.3.4
 Requires-Dist: chromadb>=0.5.15
-Requires-Dist: langchain-community==0.3.3
+Requires-Dist: langchain_community==0.3.3
 Requires-Dist: datasets==3.0.2
 Requires-Dist: unstructured==0.16.3
-

{ddi_fw-0.0.121.dist-info → ddi_fw-0.0.123.dist-info}/RECORD

@@ -1,5 +1,5 @@
 ddi_fw/datasets/__init__.py,sha256=HSwQrqnzrEjIG4gif41pwJ_cST3t2XHGDxqFyuEBRwo,351
-ddi_fw/datasets/core.py,sha256=fHceJmzWr5UKQ8PDdn7ehZ2GvBvLZjBpTze85FNK20s,17108
+ddi_fw/datasets/core.py,sha256=z-H-UWIwLjnJVC7QwZQIK4tC8v00XJtjSeA1cYssxAI,17110
 ddi_fw/datasets/db_utils.py,sha256=OTsa3d-Iic7z3HmzSQK9UigedRbHDxYChJk0s4GfLnw,6191
 ddi_fw/datasets/embedding_generator.py,sha256=Jqrlv88RCu0Lg812KsA12X0cSaZuxbckJ4LNRKNy_qw,2173
 ddi_fw/datasets/feature_vector_generation.py,sha256=gvjpEzkgVV8dp4V8NMMv59u0v-1tNAJ7v83R-keWGoA,4748
@@ -72,7 +72,7 @@ ddi_fw/pipeline/__init__.py,sha256=tKDM_rW4vPjlYTeOkNgi9PujDzb4e9O3LK1w5wqnebw,2
 ddi_fw/pipeline/multi_modal_combination_strategy.py,sha256=qIst7vxHaOAhRv4lgozszwa3b1QE4aIrN74t41Xnvr4,1637
 ddi_fw/pipeline/multi_pipeline.py,sha256=t_Z7d7xRfDnhpQTlqCf7c0isZ5hZlyXavKhC7ePsnJY,5903
 ddi_fw/pipeline/ner_pipeline.py,sha256=wB7hz4YCOv7UAz6bGE6sSpPXXIdoOflOVK5UCc1fO-o,5586
-ddi_fw/pipeline/pipeline.py,sha256=VX3GcoTjY7_ehX_rmpa-uh0NyBFoxF24AxbwruEWw4A,8457
+ddi_fw/pipeline/pipeline.py,sha256=WQk9vZOLao6YDpqPK7O7NDMqb5pjcPfUaG6_LZL2Qis,8769
 ddi_fw/test/basic_test.py,sha256=fEOGcZm1ObnsDvMiXNmdmz6YCeUrGc8V0DwlSwGhsq8,376
 ddi_fw/test/combination_test.py,sha256=TWNE8sf-DSh1Q9-yRaRBc774Sn1kSMGXLwQhd2_Qynk,324
 ddi_fw/test/compress_json_test.py,sha256=BGny56YqiG-pzhMoDzLKQBQI1E7o3jU0S7VYWtclAx4,1045
@@ -91,7 +91,7 @@ ddi_fw/utils/package_helper.py,sha256=erl8_onmhK-41zQoaED2qyDUV9GQxmT9sdoyRp9_q5
 ddi_fw/utils/py7zr_helper.py,sha256=gOqaFIyJvTjUM-btO2x9AQ69jZOS8PoKN0wetYIckJw,4747
 ddi_fw/utils/utils.py,sha256=szwnxMTDRrZoeNRyDuf3aCbtzriwtaRk4mHSH3asLdA,4301
 ddi_fw/utils/zip_helper.py,sha256=YRZA4tKZVBJwGQM0_WK6L-y5MoqkKoC-nXuuHK6CU9I,5567
-ddi_fw-0.0.121.dist-info/METADATA,sha256=ApuijQBhiTmWPSBH9Ew_idL99expLzAQ57uUSZDp06c,1967
-ddi_fw-0.0.121.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-ddi_fw-0.0.121.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
-ddi_fw-0.0.121.dist-info/RECORD,,
+ddi_fw-0.0.123.dist-info/METADATA,sha256=aklS2YR-_6JHgDWB2vv_Urdb-bUj975olJHX17x6AhA,1965
+ddi_fw-0.0.123.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+ddi_fw-0.0.123.dist-info/top_level.txt,sha256=PMwHICFZTZtcpzQNPV4UQnfNXYIeLR_Ste-Wfc1h810,7
+ddi_fw-0.0.123.dist-info/RECORD,,

{ddi_fw-0.0.121.dist-info → ddi_fw-0.0.123.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any