luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge a77c4f0415 into 2a2ccc86aa

Browse source
This commit is contained in:
Casper da Costa-Luis 2025-03-11 11:31:34 +09:00 committed by GitHub
commit dba32ef21d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 100 additions and 97 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
README.md
View file

@ -146,6 +146,13 @@ result = md.convert("example.jpg")
print(result.text_content)
```
Or from the CLI:
```bash
pip install markitdown
markitdown --llm-model gpt-4o example.jpg
```
### Docker
```sh

144
packages/markitdown/src/markitdown/__main__.py
View file

@ -8,101 +8,89 @@ from importlib.metadata import entry_points
from .__about__ import __version__
from ._markitdown import MarkItDown, DocumentConverterResult
def main():
parser = argparse.ArgumentParser(
parser = argparse.ArgumentParser(
description="Convert various file formats to markdown.",
prog="markitdown",
formatter_class=argparse.RawDescriptionHelpFormatter,
usage=dedent(
"""
SYNTAX:
markitdown <OPTIONAL: FILENAME>
If FILENAME is empty, markitdown reads from stdin.
EXAMPLE:
epilog=dedent(
"""\
examples:
markitdown example.pdf
OR
cat example.pdf | markitdown
OR
markitdown < example.pdf
OR to save to a file use
markitdown example.pdf -o example.md
OR
markitdown example.pdf > example.md
"""
).strip(),
)
parser.add_argument(
markitdown -o example.md example.pdf
cat example.pdf | markitdown > example.md"""
),
)
parser.add_argument(
"-v",
"--version",
action="version",
version=f"%(prog)s {__version__}",
help="show the version number and exit",
)
parser.add_argument(
)
parser.add_argument(
"-o",
"--output",
help="Output file name. If not provided, output is written to stdout.",
)
parser.add_argument(
metavar="OUTFILENAME",
help="if unspecified, defaults to stdout",
)
parser.add_argument(
"-d",
"--use-docintel",
action="store_true",
help="Use Document Intelligence to extract text instead of offline conversion. Requires a valid Document Intelligence Endpoint.",
)
parser.add_argument(
help="use online Document Intelligence to extract text (requires a valid `--endpoint`)",
)
parser.add_argument(
"-e",
"--endpoint",
type=str,
help="Document Intelligence Endpoint. Required if using Document Intelligence.",
)
parser.add_argument(
help="required for `--use-docintel`",
)
parser.add_argument(
"-p",
"--use-plugins",
action="store_true",
help="Use 3rd-party plugins to convert files. Use --list-plugins to see installed plugins.",
)
parser.add_argument(
help="use 3rd-party plugins to convert files (see `--list-plugins`)",
)
parser.add_argument(
"--list-plugins",
action="store_true",
help="List installed 3rd-party plugins. Plugins are loaded when using the -p or --use-plugin option.",
)
help="list installed 3rd-party plugins (loaded with `--use-plugin`)",
)
parser.add_argument("--llm-model", metavar="MODEL", help="e.g. gpt-4o")
parser.add_argument(
"--llm-client-url", metavar="URL", help="base URL for OpenAI LLM client"
)
parser.add_argument(
"-H",
"--llm-client-header",
metavar="HEADER",
nargs="*",
default=[],
help="may be specified multiple times",
)
parser.add_argument(
"filename", metavar="FILENAME", nargs="?", help="if unspecified, defaults to stdin"
)
parser.add_argument("filename", nargs="?")
args = parser.parse_args()
def main(args=None):
args = parser.parse_args(args)
if args.list_plugins:
# List installed plugins, then exit
print("Installed MarkItDown 3rd-party Plugins:\n")
plugin_entry_points = list(entry_points(group="markitdown.plugin"))
if len(plugin_entry_points) == 0:
print(" * No 3rd-party plugins installed.")
print(
"\nFind plugins by searching for the hashtag #markitdown-plugin on GitHub.\n"
)
else:
if plugin_entry_points:
for entry_point in plugin_entry_points:
print(f" * {entry_point.name:<16}\t(package: {entry_point.value})")
print(
"\nUse the -p (or --use-plugins) option to enable 3rd-party plugins.\n"
)
else:
print("No 3rd-party plugins installed.")
print(
"\nFind plugins by searching for the hashtag #markitdown-plugin on GitHub.\n"
)
sys.exit(0)
if args.use_docintel:
@ -112,25 +100,33 @@ def main():
)
elif args.filename is None:
raise ValueError("Filename is required when using Document Intelligence.")
if args.llm_model:
from openai import OpenAI
headers = {}
for header in args.llm_client_header:
key, value = header.split(":", 1)
headers[key] = value.lstrip()
llm_client = OpenAI(base_url=args.llm_client_url, default_headers=headers)
else:
llm_client = None
markitdown = MarkItDown(
enable_plugins=args.use_plugins, docintel_endpoint=args.endpoint
enable_plugins=args.use_plugins,
docintel_endpoint=args.endpoint if args.use_docintel else None,
llm_client=llm_client,
llm_model=args.llm_model,
)
else:
markitdown = MarkItDown(enable_plugins=args.use_plugins)
if args.filename is None:
result = markitdown.convert_stream(sys.stdin.buffer)
else:
if args.filename:
result = markitdown.convert(args.filename)
else:
result = markitdown.convert_stream(sys.stdin.buffer)
_handle_output(args, result)
def _handle_output(args, result: DocumentConverterResult):
"""Handle output to stdout or file"""
if args.output:
with open(args.output, "w", encoding="utf-8") as f:
f.write(result.text_content)
print(result.text_content, file=f)
else:
print(result.text_content)

2
packages/markitdown/tests/test_cli.py
View file

@ -33,7 +33,7 @@ def test_invalid_flag(shared_tmp_dir) -> None:
assert (
"unrecognized arguments" in result.stderr
), f"Expected 'unrecognized arguments' to appear in STDERR"
assert "SYNTAX" in result.stderr, f"Expected 'SYNTAX' to appear in STDERR"
assert "usage" in result.stderr, f"Expected 'usage' to appear in STDERR"
def test_output_to_stdout(shared_tmp_dir) -> None: