fix: referenced paths relative to zip root (#289)

Signed-off-by: Michele Dolfi <[email protected]>

Author: dolfim-ibm

docling_serve/response_preparation.py

@@ -91,6 +91,8 @@ def _export_documents_as_files(
     # Default failure in case results is empty
     conv_result = ConversionStatus.FAILURE
 
+    artifacts_dir = Path("artifacts/")  # will be relative to the fname
+
     for conv_res in conv_results:
         conv_result = conv_res.status
         if conv_res.status == ConversionStatus.SUCCESS:
@@ -102,15 +104,19 @@ def _export_documents_as_files(
                 fname = output_dir / f"{doc_filename}.json"
                 _log.info(f"writing JSON output to {fname}")
                 conv_res.document.save_as_json(
-                    filename=fname, image_mode=image_export_mode
+                    filename=fname,
+                    image_mode=image_export_mode,
+                    artifacts_dir=artifacts_dir,
                 )
 
             # Export HTML format:
             if export_html:
                 fname = output_dir / f"{doc_filename}.html"
                 _log.info(f"writing HTML output to {fname}")
                 conv_res.document.save_as_html(
-                    filename=fname, image_mode=image_export_mode
+                    filename=fname,
+                    image_mode=image_export_mode,
+                    artifacts_dir=artifacts_dir,
                 )
 
             # Export Text format:
@@ -129,6 +135,7 @@ def _export_documents_as_files(
                 _log.info(f"writing Markdown output to {fname}")
                 conv_res.document.save_as_markdown(
                     filename=fname,
+                    artifacts_dir=artifacts_dir,
                     image_mode=image_export_mode,
                     page_break_placeholder=md_page_break_placeholder or None,
                 )

pyproject.toml

@@ -35,7 +35,7 @@ classifiers = [
 requires-python = ">=3.10"
 dependencies = [
     "docling~=2.38",
-    "docling-core>=2.32.0",
+    "docling-core>=2.44.1",
     "docling-jobkit[kfp,vlm]~=1.2",
     "fastapi[standard]~=0.115",
     "httpx~=0.28",

tests/test_fastapi_endpoints.py

@@ -1,13 +1,17 @@
 import asyncio
+import io
 import json
 import os
+import zipfile
 
 import pytest
 import pytest_asyncio
 from asgi_lifespan import LifespanManager
 from httpx import ASGITransport, AsyncClient
 from pytest_check import check
 
+from docling_core.types.doc import DoclingDocument, PictureItem
+
 from docling_serve.app import create_app
 
 
@@ -153,3 +157,37 @@ def safe_slice(value, length=100):
             data["document"]["doctags_content"],
             msg=f"DocTags document should contain '<doctag><page_header>'. Received: {safe_slice(data['document']['doctags_content'])}",
         )
+
+
+@pytest.mark.asyncio
+async def test_referenced_artifacts(client: AsyncClient):
+    """Test that paths in the zip file are relative to the zip file root."""
+
+    endpoint = "/v1/convert/file"
+    options = {
+        "to_formats": ["json"],
+        "image_export_mode": "referenced",
+        "target_type": "zip",
+        "ocr": False,
+    }
+
+    current_dir = os.path.dirname(__file__)
+    file_path = os.path.join(current_dir, "2206.01062v1.pdf")
+
+    files = {
+        "files": ("2206.01062v1.pdf", open(file_path, "rb"), "application/pdf"),
+    }
+
+    response = await client.post(endpoint, files=files, data=options)
+    assert response.status_code == 200, "Response should be 200 OK"
+
+    with zipfile.ZipFile(io.BytesIO(response.content)) as zip_file:
+        namelist = zip_file.namelist()
+        for file in namelist:
+            if file.endswith(".json"):
+                doc = DoclingDocument.model_validate(json.loads(zip_file.read(file)))
+                for item, _level in doc.iterate_items():
+                    if isinstance(item, PictureItem):
+                        assert item.image is not None
+                        print(f"{item.image.uri}=")
+                        assert str(item.image.uri) in namelist