Skip to content

Python tool for converting files and office documents to Markdown.

Added llm tests to the local test set.

Adam Fourney248d64edd0ce
diff --git a/pyproject.toml b/pyproject.toml
index 756380a5..c5bd58ba 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -39,6 +39,7 @@ dependencies = [
"SpeechRecognition",
"pathvalidate",
"charset-normalizer",
+ "openai",
]
[project.urls]
@@ -77,3 +78,6 @@ exclude_lines = [
"if __name__ == .__main__.:",
"if TYPE_CHECKING:",
]
+
+[tool.hatch.build.targets.sdist]
+only-include = ["src/markitdown"]
diff --git a/src/markitdown/__about__.py b/src/markitdown/__about__.py
index d1621f54..fa67ccbb 100644
--- a/src/markitdown/__about__.py
+++ b/src/markitdown/__about__.py
@@ -1,4 +1,4 @@
# SPDX-FileCopyrightText: 2024-present Adam Fourney <[email protected]>
#
# SPDX-License-Identifier: MIT
-__version__ = "0.0.1a1"
+__version__ = "0.0.1a2"
diff --git a/src/markitdown/_markitdown.py b/src/markitdown/_markitdown.py
index a7fb28a1..ff9a7b13 100644
--- a/src/markitdown/_markitdown.py
+++ b/src/markitdown/_markitdown.py
@@ -847,8 +847,6 @@ class ImageConverter(MediaConverter):
if prompt is None or prompt.strip() == "":
prompt = "Write a detailed caption for this image."
- sys.stderr.write(f"llm Prompt:\n{prompt}\n")
-
data_uri = ""
with open(local_path, "rb") as image_file:
content_type, encoding = mimetypes.guess_type("_dummy" + extension)
diff --git a/tests/test_files/test.docx b/tests/test_files/test.docx
old mode 100755
new mode 100644
diff --git a/tests/test_files/test.jpg b/tests/test_files/test.jpg
old mode 100755
new mode 100644
diff --git a/tests/test_files/test.xlsx b/tests/test_files/test.xlsx
old mode 100755
new mode 100644
diff --git a/tests/test_files/test_llm.jpg b/tests/test_files/test_llm.jpg
new file mode 100644
index 00000000..1f358fed
Binary files /dev/null and b/tests/test_files/test_llm.jpg differ
diff --git a/tests/test_files/test_with_comment.docx b/tests/test_files/test_with_comment.docx
old mode 100755
new mode 100644
diff --git a/tests/test_markitdown.py b/tests/test_markitdown.py
index 76bd3026..bfc316cc 100644
--- a/tests/test_markitdown.py
+++ b/tests/test_markitdown.py
@@ -11,6 +11,16 @@ 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")
@@ -107,6 +117,10 @@ CSV_CP932_TEST_STRINGS = [
"髙橋淳,35,名古屋",
]
+LLM_TEST_STRINGS = [
+ "5bda1dd6",
+]
+
@pytest.mark.skipif(
skip_remote,
@@ -229,8 +243,28 @@ def test_markitdown_exiftool() -> None:
assert target in result.text_content
+ 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_llm()