ddi-fw 0.0.101__tar.gz → 0.0.103__tar.gz

{ddi_fw-0.0.101 → ddi_fw-0.0.103}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.101
+Version: 0.0.103
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>

{ddi_fw-0.0.101 → ddi_fw-0.0.103}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ddi_fw"
-version = "0.0.101"
+version = "0.0.103"
 description = "Do not use :)"
 readme = "README.md"
 authors = [

{ddi_fw-0.0.101 → ddi_fw-0.0.103}/src/ddi_fw/langchain/embeddings.py

@@ -92,6 +92,7 @@ class SBertEmbeddings(BaseModel, Embeddings):
     #     arbitrary_types_allowed = True
 
     model_config = ConfigDict(
+        extra="allow",
         arbitrary_types_allowed = True,
         protected_namespaces=()
     )

{ddi_fw-0.0.101 → ddi_fw-0.0.103}/src/ddi_fw/langchain/storage.py

@@ -12,6 +12,7 @@ from langchain.document_loaders import DataFrameLoader
 from langchain.text_splitter import TextSplitter
 
 # from langchain_community.document_loaders.hugging_face_dataset import HuggingFaceDatasetLoader
+from ddi_fw.langchain.embeddings import SBertEmbeddings
 from ddi_fw.utils import get_import
 
 
@@ -122,7 +123,7 @@ def generate_embeddings(df, config_file, new_model_names, collections=None, pers
         #     print(f"Configuration for collection {id} not found.")
         #     continue
 
-        embedding_model_type = collection_config['embedding_model_tpe']
+        embedding_model_type = collection_config['embedding_model_type']
         text_splitters_types = collection_config['text_splitters_types']
         batch_size = collection_config['batch_size']
         columns = collection_config['columns']
@@ -134,8 +135,10 @@ def generate_embeddings(df, config_file, new_model_names, collections=None, pers
 
         # Assuming the classes for the embeddings and splitters are available
         try:
+            model_kwargs = collection_config['model_kwargs']
+            SBertEmbeddings(model_name="a", model_config={})
             model = get_import(embedding_model_type)(
-                model_name=name, model_kwargs=c['model_kwargs'])
+                model_name=name, **model_kwargs)
         except:
             # print(f"Unknown embedding model: {embedding_model_type}")
             raise Exception(f"Unknown embedding model: {embedding_model_type}")
@@ -145,11 +148,11 @@ def generate_embeddings(df, config_file, new_model_names, collections=None, pers
         for text_splitter_type in text_splitters_types:
             try:
                 type_of_text_splitter = get_import(text_splitter_type)
-                text_splitter_params = text_splitter.get("params")
+                kwargs = text_splitter.get("params")
                 suffix = text_splitter.get("suffix")
-                if text_splitter_params:
+                if kwargs:
                     text_splitter = type_of_text_splitter(
-                        **text_splitter_params)
+                        **kwargs)
                 else:
                     text_splitter = type_of_text_splitter()
                 text_splitters.append(text_splitter)

{ddi_fw-0.0.101 → ddi_fw-0.0.103}/src/ddi_fw.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ddi_fw
-Version: 0.0.101
+Version: 0.0.103
 Summary: Do not use :)
 Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
 Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>