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

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

docling_serve/docling_conversion.py

@@ -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()

tests/test_options_serialization.py

@@ -0,0 +1,54 @@
+from docling_serve.datamodel.convert import (
+    ConvertDocumentsOptions,
+    PictureDescriptionApi,
+)
+from docling_serve.docling_conversion import (
+    _hash_pdf_format_option,
+    get_pdf_pipeline_opts,
+)
+
+
+def test_options_cache_key():
+    hashes = set()
+
+    opts = ConvertDocumentsOptions()
+    pipeline_opts = get_pdf_pipeline_opts(opts)
+    hash = _hash_pdf_format_option(pipeline_opts)
+    assert hash not in hashes
+    hashes.add(hash)
+
+    opts.do_picture_description = True
+    pipeline_opts = get_pdf_pipeline_opts(opts)
+    hash = _hash_pdf_format_option(pipeline_opts)
+    # pprint(pipeline_opts.pipeline_options.model_dump(serialize_as_any=True))
+    assert hash not in hashes
+    hashes.add(hash)
+
+    opts.picture_description_api = PictureDescriptionApi(
+        url="http://localhost",
+        params={"model": "mymodel"},
+        prompt="Hello 1",
+    )
+    pipeline_opts = get_pdf_pipeline_opts(opts)
+    hash = _hash_pdf_format_option(pipeline_opts)
+    # pprint(pipeline_opts.pipeline_options.model_dump(serialize_as_any=True))
+    assert hash not in hashes
+    hashes.add(hash)
+
+    opts.picture_description_api = PictureDescriptionApi(
+        url="http://localhost",
+        params={"model": "your-model"},
+        prompt="Hello 1",
+    )
+    pipeline_opts = get_pdf_pipeline_opts(opts)
+    hash = _hash_pdf_format_option(pipeline_opts)
+    # pprint(pipeline_opts.pipeline_options.model_dump(serialize_as_any=True))
+    assert hash not in hashes
+    hashes.add(hash)
+
+    opts.picture_description_api.prompt = "World"
+    pipeline_opts = get_pdf_pipeline_opts(opts)
+    hash = _hash_pdf_format_option(pipeline_opts)
+    # pprint(pipeline_opts.pipeline_options.model_dump(serialize_as_any=True))
+    assert hash not in hashes
+    hashes.add(hash)