feat: Async api (#60)

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

tests/test_1-file-all-outputs.py

@@ -89,7 +89,7 @@ async def test_convert_file(async_client):
         check.is_in(
             '{"schema_name": "DoclingDocument"',
             json.dumps(data["document"]["json_content"]),
-            msg=f"JSON document should contain '{{\\n  \"schema_name\": \"DoclingDocument'\". Received: {safe_slice(data['document']['json_content'])}",
+            msg=f'JSON document should contain \'{{\\n  "schema_name": "DoclingDocument\'". Received: {safe_slice(data["document"]["json_content"])}',
         )
     # HTML check
     check.is_in(

tests/test_1-url-all-outputs.py

@@ -83,7 +83,7 @@ async def test_convert_url(async_client):
         check.is_in(
             '{"schema_name": "DoclingDocument"',
             json.dumps(data["document"]["json_content"]),
-            msg=f"JSON document should contain '{{\\n  \"schema_name\": \"DoclingDocument'\". Received: {safe_slice(data['document']['json_content'])}",
+            msg=f'JSON document should contain \'{{\\n  "schema_name": "DoclingDocument\'". Received: {safe_slice(data["document"]["json_content"])}',
         )
     # HTML check
     check.is_in(

tests/test_1-url-async-ws.py

@@ -0,0 +1,48 @@
+import base64
+from pathlib import Path
+
+import httpx
+import pytest
+import pytest_asyncio
+from websockets.sync.client import connect
+
+
+@pytest_asyncio.fixture
+async def async_client():
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        yield client
+
+
+@pytest.mark.asyncio
+async def test_convert_url(async_client: httpx.AsyncClient):
+    """Test convert URL to all outputs"""
+
+    doc_filename = Path("tests/2408.09869v5.pdf")
+    encoded_doc = base64.b64encode(doc_filename.read_bytes()).decode()
+
+    base_url = "http://localhost:5001/v1alpha"
+    payload = {
+        "options": {
+            "to_formats": ["md", "json"],
+            "image_export_mode": "placeholder",
+            "ocr": True,
+            "abort_on_error": False,
+            "return_as_file": False,
+        },
+        # "http_sources": [{"url": "https://arxiv.org/pdf/2501.17887"}],
+        "file_sources": [{"base64_string": encoded_doc, "filename": doc_filename.name}],
+    }
+    # print(json.dumps(payload, indent=2))
+
+    for n in range(5):
+        response = await async_client.post(
+            f"{base_url}/convert/source/async", json=payload
+        )
+        assert response.status_code == 200, "Response should be 200 OK"
+
+    task = response.json()
+
+    uri = f"ws://localhost:5001/v1alpha/status/ws/{task['task_id']}"
+    with connect(uri) as websocket:
+        for message in websocket:
+            print(message)

tests/test_1-url-async.py

@@ -0,0 +1,60 @@
+import json
+import random
+import time
+
+import httpx
+import pytest
+import pytest_asyncio
+
+
+@pytest_asyncio.fixture
+async def async_client():
+    async with httpx.AsyncClient(timeout=60.0) as client:
+        yield client
+
+
+@pytest.mark.asyncio
+async def test_convert_url(async_client):
+    """Test convert URL to all outputs"""
+
+    example_docs = [
+        "https://arxiv.org/pdf/2411.19710",
+        "https://arxiv.org/pdf/2501.17887",
+        "https://www.nature.com/articles/s41467-024-50779-y.pdf",
+        "https://arxiv.org/pdf/2306.12802",
+        "https://arxiv.org/pdf/2311.18481",
+    ]
+
+    base_url = "http://localhost:5001/v1alpha"
+    payload = {
+        "options": {
+            "to_formats": ["md", "json"],
+            "image_export_mode": "placeholder",
+            "ocr": True,
+            "abort_on_error": False,
+            "return_as_file": False,
+        },
+        "http_sources": [{"url": random.choice(example_docs)}],
+    }
+    print(json.dumps(payload, indent=2))
+
+    for n in range(5):
+        response = await async_client.post(
+            f"{base_url}/convert/source/async", json=payload
+        )
+        assert response.status_code == 200, "Response should be 200 OK"
+
+    task = response.json()
+
+    print(json.dumps(task, indent=2))
+
+    while task["task_status"] not in ("success", "failure"):
+        response = await async_client.get(f"{base_url}/status/poll/{task['task_id']}")
+        assert response.status_code == 200, "Response should be 200 OK"
+        task = response.json()
+        print(f"{task['task_status']=}")
+        print(f"{task['task_position']=}")
+
+        time.sleep(2)
+
+    assert task["task_status"] == "success"

tests/test_2-files-all-outputs.py

@@ -57,18 +57,18 @@ async def test_convert_file(async_client):
     content_disposition = response.headers.get("content-disposition")
 
     with check:
-        assert (
-            content_disposition is not None
-        ), "Content-Disposition header should be present"
+        assert content_disposition is not None, (
+            "Content-Disposition header should be present"
+        )
     with check:
         assert "attachment" in content_disposition, "Response should be an attachment"
     with check:
-        assert (
-            'filename="converted_docs.zip"' in content_disposition
-        ), "Attachment filename should be 'converted_docs.zip'"
+        assert 'filename="converted_docs.zip"' in content_disposition, (
+            "Attachment filename should be 'converted_docs.zip'"
+        )
 
     content_type = response.headers.get("content-type")
     with check:
-        assert (
-            content_type == "application/zip"
-        ), "Content-Type should be 'application/zip'"
+        assert content_type == "application/zip", (
+            "Content-Type should be 'application/zip'"
+        )

tests/test_2-urls-all-outputs.py

@@ -50,18 +50,18 @@ async def test_convert_url(async_client):
     content_disposition = response.headers.get("content-disposition")
 
     with check:
-        assert (
-            content_disposition is not None
-        ), "Content-Disposition header should be present"
+        assert content_disposition is not None, (
+            "Content-Disposition header should be present"
+        )
     with check:
         assert "attachment" in content_disposition, "Response should be an attachment"
     with check:
-        assert (
-            'filename="converted_docs.zip"' in content_disposition
-        ), "Attachment filename should be 'converted_docs.zip'"
+        assert 'filename="converted_docs.zip"' in content_disposition, (
+            "Attachment filename should be 'converted_docs.zip'"
+        )
 
     content_type = response.headers.get("content-type")
     with check:
-        assert (
-            content_type == "application/zip"
-        ), "Content-Type should be 'application/zip'"
+        assert content_type == "application/zip", (
+            "Content-Type should be 'application/zip'"
+        )