Merge branch 'sparse_search' into dev

Author: khoroshevskyi

.github/workflows/black.yml

@@ -8,4 +8,4 @@ jobs:
     steps:
       - uses: actions/checkout@v6
       - uses: actions/setup-python@v6
-      - uses: psf/black@@stable
+      - uses: psf/black@stable

bbconf/config_parser/bedbaseconfig.py

@@ -75,7 +75,7 @@ def __init__(self, config: Union[Path, str], init_ml: bool = True):
         if init_ml:
 
             self.dense_encoder: TextEmbedding = self._init_dense_encoder()
-            self.sparce_encoder: Union[SparseEncoder, None] = self._init_sparce_model()
+            self.sparse_encoder: Union[SparseEncoder, None] = self._init_sparce_model()
             self._umap_encoder: Union[UMAP, None] = self._init_umap_model()
             self.r2v_encoder: Union[Region2VecExModel, None] = self._init_r2v_encoder()
 
@@ -112,7 +112,7 @@ def __init__(self, config: Union[Path, str], init_ml: bool = True):
             self.b2b_search_interface = None
             self.bivec_search_interface = None
             self._umap_encoder: Union[UMAP, None] = None
-            self.sparce_encoder = None
+            self.sparse_encoder = None
 
         self._phc = self._init_pephubclient()
         self._boto3_client = self._init_boto3_client()
@@ -288,7 +288,7 @@ def _init_qdrant_text_backend(
             return None
         if not isinstance(dense_encoder, TextEmbedding):
             _LOGGER.error(
-                f"Unable to create Qdrant bivec text collection,, dense encoder is None."
+                f"Unable to create Qdrant bivec text collection, dense encoder is None."
             )
             return None
 

bbconf/modules/bedfiles.py

@@ -1627,13 +1627,12 @@ def add_tokenized(
 
             if self.exist_tokenized(bed_id, universe_id):
                 if not overwrite:
-                    if not overwrite:
-                        raise TokenizeFileExistsError(
-                            "Tokenized file already exists in the database. "
-                            "Set overwrite to True to overwrite it."
-                        )
-                    else:
-                        self.delete_tokenized(bed_id, universe_id)
+                    raise TokenizeFileExistsError(
+                        "Tokenized file already exists in the database. "
+                        "Set overwrite to True to overwrite it."
+                    )
+                else:
+                    self.delete_tokenized(bed_id, universe_id)
 
             path = self._add_zarr_s3(
                 bed_id=bed_id,
@@ -2138,8 +2137,8 @@ def reindex_hybrid_search(self, batch: int = 1000, purge: bool = False) -> None:
 
                     embeddings_list = list(self.config.dense_encoder.embed(text))
 
-                    if self.config.sparce_encoder:
-                        sparse_result = self.config.sparce_encoder.encode(
+                    if self.config.sparse_encoder:
+                        sparse_result = self.config.sparse_encoder.encode(
                             text
                         ).coalesce()
 
@@ -2336,8 +2335,8 @@ def hybrid_search(
             )
 
         dense_query = list(list(self.config.dense_encoder.embed(query))[0])
-        if self.config.sparce_encoder:
-            sparse_result = self.config.sparce_encoder.encode(query).coalesce()
+        if self.config.sparse_encoder:
+            sparse_result = self.config.sparse_encoder.encode(query).coalesce()
             sparse_embeddings = models.SparseVector(
                 indices=sparse_result.indices().tolist()[0],
                 values=sparse_result.values().tolist(),

docs/changelog.md

@@ -2,6 +2,20 @@
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
 
+
+### [0.14.0] - 2025-12-18
+### Fixed:
+- Insertion of tokenized files
+
+### Changed:
+- Updated qdrant and encoder model initialization. (One connection for qdrant and one initialized object per model)
+
+### Added:
+- Hybrid semantic search: dense + sparse search
+
+### Added:
+- Added hybrid semantic search.(dense + sparse search)
+
 ### [0.13.0] - 2025-11-24
 ### Added:
 - Conversion of bedfile to umap from predefined model

requirements/requirements-all.txt

@@ -1,7 +1,7 @@
 yacman >= 0.9.1
 sqlalchemy >= 2.0.0
 gtars >= 0.4.0
-geniml[ml] >= 0.8.2
+geniml[ml] >= 0.8.3
 psycopg >= 3.1.15
 coloredlogs
 pydantic >= 2.9.0

setup.py

@@ -41,9 +41,10 @@
     classifiers=[
         "Development Status :: 4 - Beta",
         "License :: OSI Approved :: BSD License",
-        "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
         "Topic :: Scientific/Engineering :: Bio-Informatics",
     ],
     keywords="",