Skip to content

Python tool for converting files and office documents to Markdown.

Merge branch 'main' into patch-2

gagb60c495d60940
diff --cc README.md
index 851611ee,15cc6220..62ee178a
--- a/README.md
+++ b/README.md
@@@ -15,6 -13,22 +15,21 @@@ It presently supports
- HTML (special handling of Wikipedia, etc.)
- Various other text-based formats (csv, json, xml, etc.)
+ # Installation
+
+ You can install `markitdown` using pip:
+
+ ```python
+ pip install markitdown
+ ```
+
+ or from the source
+
+ ```sh
+ pip install -e .
+ ```
+
-
+ # Usage
The API is simple:
```python
@@@ -25,20 -39,18 +40,37 @@@ result = markitdown.convert("test.xlsx"
print(result.text_content)
```
+To use this as a command-line utility, install it and then run it like this:
+
+```bash
+markitdown path-to-file.pdf
+```
++
+This will output Markdown to standard output. You can save it like this:
++
+```bash
+markitdown path-to-file.pdf > document.md
+```
++
+You can pipe content to standard input by omitting the argument:
++
+```bash
+cat path-to-file.pdf | markitdown
+```
+
++
+ You can also configure markitdown to use Large Language Models to describe images. To do so you must provide mlm_client and mlm_model parameters to MarkItDown object, according to your specific client.
+
+ ```python
+ from markitdown import MarkItDown
+ from openai import OpenAI
+
+ client = OpenAI()
+ md = MarkItDown(mlm_client=client, mlm_model="gpt-4o")
+ result = md.convert("example.jpg")
+ print(result.text_content)
+ ```
+
## Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a