ddi-fw 0.0.258__tar.gz → 0.0.259__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (49) hide show
  1. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/PKG-INFO +1 -1
  2. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/pyproject.toml +1 -1
  3. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/faiss_storage.py +5 -1
  4. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/kaggle.py +2 -1
  5. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw.egg-info/PKG-INFO +1 -1
  6. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/README.md +0 -0
  7. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/setup.cfg +0 -0
  8. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/datasets/__init__.py +0 -0
  9. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/datasets/core.py +0 -0
  10. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/datasets/dataset_splitter.py +0 -0
  11. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/datasets/db_utils.py +0 -0
  12. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/datasets/setup_._py +0 -0
  13. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/__init__.py +0 -0
  14. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/chroma_storage.py +0 -0
  15. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/embeddings.py +0 -0
  16. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/sentence_splitter.py +0 -0
  17. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/langchain/storage.py +0 -0
  18. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/__init__.py +0 -0
  19. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/evaluation_helper.py +0 -0
  20. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/ml_helper.py +0 -0
  21. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/model_wrapper.py +0 -0
  22. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/pytorch_wrapper.py +0 -0
  23. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/tensorflow_wrapper.py +0 -0
  24. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ml/tracking_service.py +0 -0
  25. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ner/__init__.py +0 -0
  26. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ner/mmlrestclient.py +0 -0
  27. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/ner/ner.py +0 -0
  28. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/__init__.py +0 -0
  29. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/multi_modal_combination_strategy.py +0 -0
  30. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/multi_pipeline.py +0 -0
  31. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/multi_pipeline_org.py +0 -0
  32. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/ner_pipeline.py +0 -0
  33. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/pipeline/pipeline.py +0 -0
  34. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/__init__.py +0 -0
  35. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/categorical_data_encoding_checker.py +0 -0
  36. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/enums.py +0 -0
  37. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/json_helper.py +0 -0
  38. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/numpy_utils.py +0 -0
  39. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/package_helper.py +0 -0
  40. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/py7zr_helper.py +0 -0
  41. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/utils.py +0 -0
  42. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/utils/zip_helper.py +0 -0
  43. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/vectorization/__init__.py +0 -0
  44. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/vectorization/feature_vector_generation.py +0 -0
  45. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw/vectorization/idf_helper.py +0 -0
  46. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw.egg-info/SOURCES.txt +0 -0
  47. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw.egg-info/dependency_links.txt +0 -0
  48. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw.egg-info/requires.txt +0 -0
  49. {ddi_fw-0.0.258 → ddi_fw-0.0.259}/src/ddi_fw.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: ddi_fw
3
- Version: 0.0.258
3
+ Version: 0.0.259
4
4
  Summary: Do not use :)
5
5
  Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
6
6
  Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
@@ -6,7 +6,7 @@ build-backend = "setuptools.build_meta"
6
6
 
7
7
  [project]
8
8
  name = "ddi_fw"
9
- version = "0.0.258"
9
+ version = "0.0.259"
10
10
  description = "Do not use :)"
11
11
  readme = "README.md"
12
12
  authors = [
@@ -1,4 +1,5 @@
1
1
  import faiss
2
+ from langchain_text_splitters import TextSplitter
2
3
  import pandas as pd
3
4
  from uuid import uuid4
4
5
  from langchain_community.vectorstores.faiss import FAISS
@@ -45,6 +46,7 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
45
46
  persist_directory: str = Field(default="./embeddings/faiss")
46
47
  index: Any = None
47
48
  vector_store: Optional[FAISS] | None = None
49
+ text_splitter: Optional[TextSplitter] = None
48
50
  class Config:
49
51
  arbitrary_types_allowed = True
50
52
  # def generate_vector_store(self, docs):
@@ -111,7 +113,9 @@ class FaissVectorStoreManager(BaseVectorStoreManager):
111
113
 
112
114
  valid_docs = []
113
115
  valid_ids = []
114
-
116
+ if self.text_splitter:
117
+ docs = self.text_splitter.split_documents(docs)
118
+
115
119
  for doc in docs:
116
120
  content = doc.page_content if hasattr(doc, 'page_content') else ""
117
121
  if content and content.strip():
@@ -22,7 +22,8 @@ def create_kaggle_dataset(base_path: str, collections: list):
22
22
  # Step 2: Get metadata for the current folder
23
23
  model_info = next((c for c in collections if c['id'] == folder_name), None)
24
24
  if model_info is None:
25
- continue # Skip if model info is not found
25
+ raise FileNotFoundError(f"Model info for {folder_name} not exists")
26
+ # continue # Skip if model info is not found
26
27
 
27
28
  title = model_info['kaggle_title']
28
29
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: ddi_fw
3
- Version: 0.0.258
3
+ Version: 0.0.259
4
4
  Summary: Do not use :)
5
5
  Author-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
6
6
  Maintainer-email: Kıvanç Bayraktar <bayraktarkivanc@gmail.com>
File without changes
File without changes
File without changes