LLM/docling-serve
1
0
Fork 0
mirror of https://github.com/docling-project/docling-serve.git synced 2025-12-02 01:53:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: avoid missing specialized keys in the options hash (#166)

Browse Source 
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2025-04-30 13:14:34 +02:00
committed by GitHub
parent 509f4889f8
commit 36787bc061
2 changed files with 57 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docling_serve/docling_conversion.py
View File

@@ -42,15 +42,12 @@ _log = logging.getLogger(__name__)
# Custom serializer for PdfFormatOption
# (model_dump_json does not work with some classes)
def _hash_pdf_format_option(pdf_format_option: PdfFormatOption) -> bytes:
data = pdf_format_option.model_dump()
data = pdf_format_option.model_dump(serialize_as_any=True)
# pipeline_options are not fully serialized by model_dump, dedicated pass
if pdf_format_option.pipeline_options:
data["pipeline_options"] = pdf_format_option.pipeline_options.model_dump()
# Replace `artifacts_path` with a string representation
data["pipeline_options"]["artifacts_path"] = repr(
data["pipeline_options"]["artifacts_path"]
data["pipeline_options"] = pdf_format_option.pipeline_options.model_dump(
serialize_as_any=True, mode="json"
)
# Replace `pipeline_cls` with a string representation
@@ -59,12 +56,6 @@ def _hash_pdf_format_option(pdf_format_option: PdfFormatOption) -> bytes:
# Replace `backend` with a string representation
data["backend"] = repr(data["backend"])
# Handle `device` in `accelerator_options`
if "accelerator_options" in data and "device" in data["accelerator_options"]:
data["accelerator_options"]["device"] = repr(
data["accelerator_options"]["device"]
)
# Serialize the dictionary to JSON with sorted keys to have consistent hashes
serialized_data = json.dumps(data, sort_keys=True)
options_hash = hashlib.sha1(serialized_data.encode()).digest()