Skip to content

fix: drop latin-1 decode in source title and userIds #306

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
kyteinsky merged 1 commit into from
May 28, 2026
Merged

fix: drop latin-1 decode in source title and userIds #306

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
16 changes: 4 additions & 12 deletions context_chat_backend/chain/ingest/injest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -257,7 +257,7 @@ def _sources_to_indocuments(

metadata = {
'source': source.reference,
'title': _decode_latin_1(source.title),
'title': source.title,
'type': source.type,
}
doc = Document(page_content=content, metadata=metadata)
Expand All @@ -271,7 +271,7 @@ def _sources_to_indocuments(

indocuments[db_id] = InDocument(
documents=split_docs,
userIds=list(map(_decode_latin_1, source.userIds)),
userIds=source.userIds,
source_id=source.reference,
provider=source.provider,
modified=source.modified, # pyright: ignore[reportArgumentType]
Expand Down Expand Up @@ -299,7 +299,7 @@ def _increase_access_for_existing_sources(
try:
vectordb.update_access(
UpdateAccessOp.ALLOW,
list(map(_decode_latin_1, source.userIds)),
source.userIds,
source.reference,
)
results[db_id] = None
Expand Down Expand Up @@ -390,22 +390,14 @@ def _process_sources(
return source_proc_results


def _decode_latin_1(s: str) -> str:
try:
return s.encode('latin-1').decode('utf-8')
except UnicodeDecodeError:
logger.error('Failed to decode latin-1: %s', s)
return s


def embed_sources(
vectordb_loader: VectorDBLoader,
config: TConfig,
sources: Mapping[int, SourceItem | ReceivedFileItem]
) -> Mapping[int, IndexingError | None]:
logger.debug('Embedding sources:', extra={
'source_ids': [
f'{source.reference} ({_decode_latin_1(source.title)})'
f'{source.reference} ({source.title})'
for source in sources.values()
],
'len(source_ids)': len(sources),
Expand Down
Loading