Skip to content

fix: resolve batch inference crash by handling non-serializable objects in GCS cache #352

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

Open
SalimMessaad1 wants to merge 3 commits into
base: main
Choose a base branch
from
Open

fix: resolve batch inference crash by handling non-serializable objects in GCS cache #352

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0acd625
fix: resolve TypeError in batch cache hashing by adding custom JSON s…
SalimMessaad1 Feb 10, 2026
7ebc534
fix: resolve TypeError in batch cache hashing by adding custom JSON s…
SalimMessaad1 Feb 10, 2026
1783371
Merge branch 'main' into fix-serialization-bug
SalimMessaad1 Feb 26, 2026
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
13 changes: 11 additions & 2 deletions langextract/providers/gemini_batch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,13 @@
_KEY_IDX = "idx-"
_CACHE_PREFIX = "cache"
_UNSET = object()

def _json_serializer(obj: Any) -> Any:
"""JSON serializer for objects not serializable by default json code."""
if dataclasses.is_dataclass(obj):
return dataclasses.asdict(obj)
if isinstance(obj, enum.Enum):
return obj.value
raise TypeError(f"Object of type {type(obj)} is not JSON serializable")

@dataclasses.dataclass(slots=True, frozen=True)
class BatchConfig:
Expand Down Expand Up @@ -386,7 +392,10 @@ def __init__(self, bucket_name: str, project: str | None = None):

def _compute_hash(self, key_data: dict) -> str:
"""Compute SHA256 hash of the canonicalized request data."""
canonical_json = json.dumps(key_data, sort_keys=True, ensure_ascii=False)
# to prevent crash added default=_json_serializer
canonical_json = json.dumps(
key_data, sort_keys=True, ensure_ascii=False, default=_json_serializer
)
return hashlib.sha256(canonical_json.encode("utf-8")).hexdigest()

def _get_single(self, key_hash: str) -> str | None:
Expand Down
Loading