Merge branch 'main' into main

tests/test_markitdown.py

@@ -6,11 +6,23 @@ import shutil
 import pytest
 import requests
 
+from warnings import catch_warnings, resetwarnings
+
 from markitdown import MarkItDown
 
 skip_remote = (
     True if os.environ.get("GITHUB_ACTIONS") else False
 )  # Don't run these tests in CI
+
+
+# Don't run the llm tests without a key and the client library
+skip_llm = False if os.environ.get("OPENAI_API_KEY") else True
+try:
+    import openai
+except ModuleNotFoundError:
+    skip_llm = True
+
+# Skip exiftool tests if not installed
 skip_exiftool = shutil.which("exiftool") is None
 
 TEST_FILES_DIR = os.path.join(os.path.dirname(__file__), "test_files")
@@ -114,6 +126,10 @@ CSV_CP932_TEST_STRINGS = [
     "髙橋淳,35,名古屋",
 ]
 
+LLM_TEST_STRINGS = [
+    "5bda1dd6",
+]
+
 
 @pytest.mark.skipif(
     skip_remote,
@@ -242,8 +258,63 @@ def test_markitdown_exiftool() -> None:
         assert target in result.text_content
 
 
+def test_markitdown_deprecation() -> None:
+    try:
+        with catch_warnings(record=True) as w:
+            test_client = object()
+            markitdown = MarkItDown(mlm_client=test_client)
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert markitdown._llm_client == test_client
+    finally:
+        resetwarnings()
+
+    try:
+        with catch_warnings(record=True) as w:
+            markitdown = MarkItDown(mlm_model="gpt-4o")
+            assert len(w) == 1
+            assert w[0].category is DeprecationWarning
+            assert markitdown._llm_model == "gpt-4o"
+    finally:
+        resetwarnings()
+
+    try:
+        test_client = object()
+        markitdown = MarkItDown(mlm_client=test_client, llm_client=test_client)
+        assert False
+    except ValueError:
+        pass
+
+    try:
+        markitdown = MarkItDown(mlm_model="gpt-4o", llm_model="gpt-4o")
+        assert False
+    except ValueError:
+        pass
+
+
+@pytest.mark.skipif(
+    skip_llm,
+    reason="do not run llm tests without a key",
+)
+def test_markitdown_llm() -> None:
+    client = openai.OpenAI()
+    markitdown = MarkItDown(llm_client=client, llm_model="gpt-4o")
+
+    result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test_llm.jpg"))
+
+    for test_string in LLM_TEST_STRINGS:
+        assert test_string in result.text_content
+
+    # This is not super precise. It would also accept "red square", "blue circle",
+    # "the square is not blue", etc. But it's sufficient for this test.
+    for test_string in ["red", "circle", "blue", "square"]:
+        assert test_string in result.text_content.lower()
+
+
 if __name__ == "__main__":
     """Runs this file's tests from the command line."""
     test_markitdown_remote()
     test_markitdown_local()
     test_markitdown_exiftool()
+    test_markitdown_deprecation()
+    test_markitdown_llm()