Skip to content

Release 0.15.7 #451

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
khoroshevskyi merged 2 commits into from
Dec 15, 2025
Merged

Release 0.15.7 #451

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
83c7063
fixed typos
khoroshevskyi Dec 12, 2025
5d19987
updated sparse encoder default model
khoroshevskyi Dec 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pephub/_version.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
__version__ = "0.15.6"
__version__ = "0.15.7"
2 changes: 1 addition & 1 deletion pephub/const.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,7 @@
# figure 4
# great speed to accuracy tradeoff
DENSE_ENCODER_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
SPARSE_ENCODER_MODEL = "naver/splade-v3"
SPARSE_ENCODER_MODEL = "prithivida/Splade_PP_en_v2"

EIDO_TEMPLATES_DIRNAME = "templates/eido"
EIDO_TEMPLATES_PATH = os.path.join(
Expand Down
18 changes: 10 additions & 8 deletions pephub/dependencies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,14 +107,16 @@ def jwt_encode_user_data(user_data: dict, exp: datetime = None) -> str:
)
# embedding_model = None

token = os.environ.get("HF_TOKEN", None)
# token = os.environ.get("HF_TOKEN", None)
# hf_model_sparse = os.environ.get("HF_MODEL_SPARSE", SPARSE_ENCODER_MODEL)
# if token is None:
# sparse_model = None
# _LOGGER_PEPHUB.warning("No HF_TOKEN provided, sparse model disabled.")
# else:

hf_model_sparse = os.environ.get("HF_MODEL_SPARSE", SPARSE_ENCODER_MODEL)
if token is None:
sparse_model = None
_LOGGER_PEPHUB.warning("No HF_TOKEN provided, sparce model disabled.")
else:
sparse_model = SparseEncoder(hf_model_sparse, token=token)
_LOGGER_PEPHUB.info(f"Sparce model in use: {hf_model_sparse}")
sparse_model = SparseEncoder(hf_model_sparse)
_LOGGER_PEPHUB.info(f"Sparse model in use: {hf_model_sparse}")


## Qdrant connection
Expand Down Expand Up @@ -403,7 +405,7 @@ def get_sentence_transformer() -> Embedding:

def get_sparse_model() -> Union[SparseEncoder, None]:
"""
Return sparce encoder model
Return sparse encoder model
"""
return sparse_model

Expand Down
6 changes: 3 additions & 3 deletions pephub/routers/api/v1/search.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ async def search_for_pep(
query: SearchQuery,
qdrant: QdrantClient = Depends(get_qdrant),
model: Embedding = Depends(get_sentence_transformer),
model_sparce: SparseEncoder = Depends(get_sparse_model),
model_sparse: SparseEncoder = Depends(get_sparse_model),
agent: PEPDatabaseAgent = Depends(get_db),
namespace_access: List[str] = Depends(get_namespace_access_list),
) -> SearchReturnModel:
Expand All @@ -74,8 +74,8 @@ async def search_for_pep(
if qdrant is not None:
dense_query = list(list(model.embed(query.query))[0])

if model_sparce:
sparse_result = model_sparce.encode(query.query).coalesce()
if model_sparse:
sparse_result = model_sparse.encode(query.query).coalesce()
sparse_embeddings = SparseVector(
indices=sparse_result.indices().tolist()[0],
values=sparse_result.values().tolist(),
Expand Down
Loading