Docling-serve cassettes

tests/cassettes/test_converters/TestDoclingServeConverterIntegration.test_convert_code_file_real_service.yaml

@@ -0,0 +1,100 @@
+interactions:
+- request:
+    body: "--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data; name=\"to_formats\"\r\n\r\njson\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition:
+      form-data; name=\"do_ocr\"\r\n\r\ntrue\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data; name=\"force_ocr\"\r\n\r\nfalse\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition:
+      form-data; name=\"do_table_structure\"\r\n\r\ntrue\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data;
+      name=\"table_mode\"\r\n\r\naccurate\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data; name=\"table_cell_matching\"\r\n\r\ntrue\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition:
+      form-data; name=\"images_scale\"\r\n\r\n2.0\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data;
+      name=\"generate_picture_images\"\r\n\r\nfalse\r\n--4379b32700c5b8d95062406eb16d4651\r\nContent-Disposition: form-data;
+      name=\"files\"; filename=\"tmpeojgnbxt.md\"\r\nContent-Type: text/markdown\r\n\r\n```python\ndef test():\n    return
+      42\n```\r\n--4379b32700c5b8d95062406eb16d4651--\r\n"
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1011'
+      content-type:
+      - multipart/form-data; boundary=4379b32700c5b8d95062406eb16d4651
+      host:
+      - localhost:5001
+    method: POST
+    uri: http://localhost:5001/v1/convert/file
+  response:
+    headers:
+      content-length:
+      - '1114'
+      content-type:
+      - application/json
+    parsed_body:
+      document:
+        doctags_content: null
+        filename: tmpeojgnbxt.md
+        html_content: null
+        json_content:
+          body:
+            children:
+            - $ref: '#/texts/0'
+            content_layer: body
+            label: unspecified
+            meta: null
+            name: _root_
+            parent: null
+            self_ref: '#/body'
+          form_items: []
+          furniture:
+            children: []
+            content_layer: furniture
+            label: unspecified
+            meta: null
+            name: _root_
+            parent: null
+            self_ref: '#/furniture'
+          groups: []
+          key_value_items: []
+          name: tmpeojgnbxt
+          origin:
+            binary_hash: 9008975733065065710
+            filename: tmpeojgnbxt.md
+            mimetype: text/markdown
+            uri: null
+          pages: {}
+          pictures: []
+          schema_name: DoclingDocument
+          tables: []
+          texts:
+          - captions: []
+            children: []
+            code_language: unknown
+            content_layer: body
+            footnotes: []
+            formatting: null
+            hyperlink: null
+            image: null
+            label: code
+            meta: null
+            orig: |-
+              def test():
+                  return 42
+            parent:
+              $ref: '#/body'
+            prov: []
+            references: []
+            self_ref: '#/texts/0'
+            text: |-
+              def test():
+                  return 42
+          version: 1.8.0
+        md_content: null
+        text_content: null
+      errors: []
+      processing_time: 0.0017275830000471615
+      status: success
+      timings: {}
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_converters/TestDoclingServeConverterIntegration.test_convert_text_real_service.yaml

@@ -0,0 +1,103 @@
+interactions:
+- request:
+    body: "--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data; name=\"to_formats\"\r\n\r\njson\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition:
+      form-data; name=\"do_ocr\"\r\n\r\ntrue\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data; name=\"force_ocr\"\r\n\r\nfalse\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition:
+      form-data; name=\"do_table_structure\"\r\n\r\ntrue\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data;
+      name=\"table_mode\"\r\n\r\naccurate\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data; name=\"table_cell_matching\"\r\n\r\ntrue\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition:
+      form-data; name=\"images_scale\"\r\n\r\n2.0\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data;
+      name=\"generate_picture_images\"\r\n\r\nfalse\r\n--798e57b119ed24827326455c645311ae\r\nContent-Disposition: form-data;
+      name=\"files\"; filename=\"content.md\"\r\nContent-Type: text/markdown\r\n\r\n# Test Document\n\nThis is a test.\r\n--798e57b119ed24827326455c645311ae--\r\n"
+    headers:
+      accept:
+      - '*/*'
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '1000'
+      content-type:
+      - multipart/form-data; boundary=798e57b119ed24827326455c645311ae
+      host:
+      - localhost:5001
+    method: POST
+    uri: http://localhost:5001/v1/convert/file
+  response:
+    headers:
+      content-length:
+      - '1225'
+      content-type:
+      - application/json
+    parsed_body:
+      document:
+        doctags_content: null
+        filename: content.md
+        html_content: null
+        json_content:
+          body:
+            children:
+            - $ref: '#/texts/0'
+            - $ref: '#/texts/1'
+            content_layer: body
+            label: unspecified
+            meta: null
+            name: _root_
+            parent: null
+            self_ref: '#/body'
+          form_items: []
+          furniture:
+            children: []
+            content_layer: furniture
+            label: unspecified
+            meta: null
+            name: _root_
+            parent: null
+            self_ref: '#/furniture'
+          groups: []
+          key_value_items: []
+          name: content
+          origin:
+            binary_hash: 18149311266811077188
+            filename: content.md
+            mimetype: text/markdown
+            uri: null
+          pages: {}
+          pictures: []
+          schema_name: DoclingDocument
+          tables: []
+          texts:
+          - children: []
+            content_layer: body
+            formatting: null
+            hyperlink: null
+            label: title
+            meta: null
+            orig: Test Document
+            parent:
+              $ref: '#/body'
+            prov: []
+            self_ref: '#/texts/0'
+            text: Test Document
+          - children: []
+            content_layer: body
+            formatting: null
+            hyperlink: null
+            label: text
+            meta: null
+            orig: This is a test.
+            parent:
+              $ref: '#/body'
+            prov: []
+            self_ref: '#/texts/1'
+            text: This is a test.
+          version: 1.8.0
+        md_content: null
+        text_content: null
+      errors: []
+      processing_time: 0.002875374999803171
+      status: success
+      timings: {}
+    status:
+      code: 200
+      message: OK
+version: 1

tests/test_chunker.py

@@ -1,3 +1,4 @@
+from pathlib import Path
 from unittest.mock import AsyncMock, Mock, patch
 
 import pytest
@@ -11,6 +12,11 @@ from haiku.rag.config import AppConfig, Config
 from haiku.rag.converters import get_converter
 
 
+@pytest.fixture(scope="module")
+def vcr_cassette_dir():
+    return str(Path(__file__).parent / "cassettes" / "test_chunker")
+
+
 @pytest.mark.asyncio
 async def test_local_chunker(qa_corpus: Dataset):
     """Test DoclingLocalChunker with real document."""
@@ -479,28 +485,11 @@ This is content.
         assert meta1.page_numbers == [1, 2]
 
 
-def is_docling_serve_available(base_url: str = "http://localhost:5001") -> bool:
-    """Check if docling-serve is running and accessible."""
-    import requests
-
-    try:
-        response = requests.get(f"{base_url}/health", timeout=2)
-        return response.status_code == 200
-    except Exception:
-        return False
-
-
-@pytest.mark.skipif(
-    not is_docling_serve_available(),
-    reason="docling-serve not available at http://localhost:5001",
-)
-@pytest.mark.integration
+@pytest.mark.vcr()
 @pytest.mark.asyncio
 async def test_local_and_serve_chunkers_produce_same_output():
     """Test that local and serve chunkers produce identical output for the same document.
 
-    This integration test requires docling-serve to be running on localhost:5001.
-
     Note: Labels are resolved from the DoclingDocument since docling-serve API
     only returns ref strings, not labels. See:
     https://github.com/docling-project/docling-serve/issues/448

tests/test_converters.py

@@ -6,7 +6,6 @@ from unittest.mock import AsyncMock, Mock, patch
 
 import httpx
 import pytest
-import requests
 from docling_core.types.doc.document import DoclingDocument
 
 from haiku.rag.config import AppConfig
@@ -16,13 +15,9 @@ from haiku.rag.converters.docling_serve import DoclingServeConverter
 from haiku.rag.converters.text_utils import TextFileHandler
 
 
-def is_docling_serve_available(base_url: str = "http://localhost:5001") -> bool:
-    """Check if docling-serve is running and accessible."""
-    try:
-        response = requests.get(f"{base_url}/health", timeout=2)
-        return response.status_code == 200
-    except Exception:
-        return False
+@pytest.fixture(scope="module")
+def vcr_cassette_dir():
+    return str(Path(__file__).parent / "cassettes" / "test_converters")
 
 
 def create_mock_docling_document_json(name: str = "test") -> dict:
@@ -560,13 +555,8 @@ class TestDoclingServeConverter:
             assert "files" in call_kwargs
 
 
-@pytest.mark.integration
-@pytest.mark.skipif(
-    not is_docling_serve_available(),
-    reason="docling-serve not available at http://localhost:5001",
-)
 class TestDoclingServeConverterIntegration:
-    """Integration tests with real docling-serve (requires service running)."""
+    """Integration tests with real docling-serve recorded via VCR."""
 
     @pytest.fixture
     def config(self):
@@ -580,22 +570,23 @@ class TestDoclingServeConverterIntegration:
         """Create converter for integration tests."""
         return DoclingServeConverter(config)
 
+    @pytest.mark.vcr()
     @pytest.mark.asyncio
     async def test_convert_text_real_service(self, converter):
-        """Test text conversion with real docling-serve (integration)."""
+        """Test text conversion with real docling-serve."""
         doc = await converter.convert_text("# Test Document\n\nThis is a test.")
         assert isinstance(doc, DoclingDocument)
-        assert doc.version == "1.8.0"
 
+    @pytest.mark.vcr()
     @pytest.mark.asyncio
     async def test_convert_code_file_real_service(self, converter):
-        """Test code file conversion with real docling-serve (integration)."""
+        """Test code file conversion with real docling-serve."""
         code = "def test():\n    return 42"
-        with tempfile.NamedTemporaryFile(mode="w", suffix=".py") as f:
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".py", delete=False) as f:
             f.write(code)
-            f.flush()
             temp_path = Path(f.name)
-            doc = await converter.convert_file(temp_path)
+        doc = await converter.convert_file(temp_path)
+        temp_path.unlink()
 
         assert isinstance(doc, DoclingDocument)
         result = doc.export_to_markdown()