Merge branch 'main' into feature/fix-code-comments
This commit is contained in:
@@ -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"]
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
# SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
|
||||
#
|
||||
# SPDX-License-Identifier: MIT
|
||||
__version__ = "0.0.1a1"
|
||||
__version__ = "0.0.1a3"
|
||||
|
||||
@@ -15,7 +15,7 @@ import traceback
|
||||
import zipfile
|
||||
from typing import Any, Dict, List, Optional, Union
|
||||
from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
|
||||
from warnings import catch_warnings
|
||||
from warnings import warn, resetwarnings, catch_warnings
|
||||
|
||||
import mammoth
|
||||
import markdownify
|
||||
@@ -44,6 +44,8 @@ try:
|
||||
IS_AUDIO_TRANSCRIPTION_CAPABLE = True
|
||||
except ModuleNotFoundError:
|
||||
pass
|
||||
finally:
|
||||
resetwarnings()
|
||||
|
||||
# Optional YouTube transcription support
|
||||
try:
|
||||
@@ -847,8 +849,6 @@ 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)
|
||||
@@ -1010,14 +1010,46 @@ class MarkItDown:
|
||||
self,
|
||||
requests_session: Optional[requests.Session] = None,
|
||||
llm_client: Optional[Any] = None,
|
||||
llm_model: Optional[Any] = None,
|
||||
llm_model: Optional[str] = None,
|
||||
style_map: Optional[str] = None,
|
||||
# Deprecated
|
||||
mlm_client: Optional[Any] = None,
|
||||
mlm_model: Optional[str] = None,
|
||||
):
|
||||
if requests_session is None:
|
||||
self._requests_session = requests.Session()
|
||||
else:
|
||||
self._requests_session = requests_session
|
||||
|
||||
# Handle deprecation notices
|
||||
#############################
|
||||
if mlm_client is not None:
|
||||
if llm_client is None:
|
||||
warn(
|
||||
"'mlm_client' is deprecated, and was renamed 'llm_client'.",
|
||||
DeprecationWarning,
|
||||
)
|
||||
llm_client = mlm_client
|
||||
mlm_client = None
|
||||
else:
|
||||
raise ValueError(
|
||||
"'mlm_client' is deprecated, and was renamed 'llm_client'. Do not use both at the same time. Just use 'llm_client' instead."
|
||||
)
|
||||
|
||||
if mlm_model is not None:
|
||||
if llm_model is None:
|
||||
warn(
|
||||
"'mlm_model' is deprecated, and was renamed 'llm_model'.",
|
||||
DeprecationWarning,
|
||||
)
|
||||
llm_model = mlm_model
|
||||
mlm_model = None
|
||||
else:
|
||||
raise ValueError(
|
||||
"'mlm_model' is deprecated, and was renamed 'llm_model'. Do not use both at the same time. Just use 'llm_model' instead."
|
||||
)
|
||||
#############################
|
||||
|
||||
self._llm_client = llm_client
|
||||
self._llm_model = llm_model
|
||||
self._style_map = style_map
|
||||
|
||||
0
tests/test_files/test.docx
vendored
Executable file → Normal file
0
tests/test_files/test.docx
vendored
Executable file → Normal file
0
tests/test_files/test.jpg
vendored
Executable file → Normal file
0
tests/test_files/test.jpg
vendored
Executable file → Normal file
|
Before Width: | Height: | Size: 463 KiB After Width: | Height: | Size: 463 KiB |
0
tests/test_files/test.xlsx
vendored
Executable file → Normal file
0
tests/test_files/test.xlsx
vendored
Executable file → Normal file
BIN
tests/test_files/test_llm.jpg
vendored
Normal file
BIN
tests/test_files/test_llm.jpg
vendored
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 145 KiB |
0
tests/test_files/test_with_comment.docx
vendored
Executable file → Normal file
0
tests/test_files/test_with_comment.docx
vendored
Executable file → Normal file
@@ -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")
|
||||
@@ -107,6 +119,10 @@ CSV_CP932_TEST_STRINGS = [
|
||||
"髙橋淳,35,名古屋",
|
||||
]
|
||||
|
||||
LLM_TEST_STRINGS = [
|
||||
"5bda1dd6",
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.skipif(
|
||||
skip_remote,
|
||||
@@ -229,8 +245,63 @@ 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()
|
||||
|
||||
Reference in New Issue
Block a user