Skip to content
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

Jump to bottom

fix error in log message #2719

Merged
merged 5 commits into from
Jun 24, 2022
Merged

fix error in log message #2719

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
c83ddd4
fix error in log message
anakin87 Jun 23, 2022
15228c2
Update Documentation & Code Style
github-actions[bot] Jun 23, 2022
1a240c8
pass index to _drop_duplicate_documents
anakin87 Jun 24, 2022
c9163c4
make the use of index in logging more explicit
anakin87 Jun 24, 2022
c202191
Update Documentation & Code Style
github-actions[bot] Jun 24, 2022
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
9 changes: 6 additions & 3 deletions haystack/document_stores/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -607,11 +607,12 @@ def get_documents_by_id(
) -> List[Document]:
pass

def _drop_duplicate_documents(self, documents: List[Document]) -> List[Document]:
def _drop_duplicate_documents(self, documents: List[Document], index: Optional[str] = None) -> List[Document]:
"""
Drop duplicates documents based on same hash ID

:param documents: A list of Haystack Document objects.
:param index: name of the index
:return: A list of Haystack Document objects.
"""
_hash_ids: Set = set([])
Expand All @@ -620,7 +621,8 @@ def _drop_duplicate_documents(self, documents: List[Document]) -> List[Document]
for document in documents:
if document.id in _hash_ids:
logger.info(
f"Duplicate Documents: Document with id '{document.id}' already exists in index " f"'{self.index}'"
f"Duplicate Documents: Document with id '{document.id}' already exists in index "
f"'{index or self.index}'"
)
continue
_documents.append(document)
Expand All @@ -640,6 +642,7 @@ def _handle_duplicate_documents(
documents that are not in the index yet.

:param documents: A list of Haystack Document objects.
:param index: name of the index
:param duplicate_documents: Handle duplicates document based on parameter options.
Parameter options : ( 'skip','overwrite','fail')
skip (default option): Ignore the duplicates documents
Expand All @@ -652,7 +655,7 @@ def _handle_duplicate_documents(

index = index or self.index
if duplicate_documents in ("skip", "fail"):
documents = self._drop_duplicate_documents(documents)
documents = self._drop_duplicate_documents(documents, index)
documents_found = self.get_documents_by_id(ids=[doc.id for doc in documents], index=index, headers=headers)
ids_exist_in_db: List[str] = [doc.id for doc in documents_found]

Expand Down