Markdown note proofreading with OpenAI LLMs
Project description
notecheck
A utility for identifying grammatical and conceptual errors in Markdown notes using OpenAI's language models.
Installation
Clone the repository and install the package:
pip install .
Then, create a .env file containing your OpenAI API key:
OPENAI_API_KEY=your-key-here
Usage
To run the checker:
notecheck path/to/notes/root
By default, the path is set to ~/obsidian/notes, but this may vary depending on your system.
The tool will:
- Automatically correct basic grammatical and spelling issues.
- Annotate more complex or conceptual issues with comments for review.
Example
Below is a sample input containing a conceptual error:
You can represent the internal energy and enthalpy of a gas from its constituent gases using the mole fractions:
$$\bar u = \sum_i y_i\bar u_i \quad \text{and} \quad \bar h = \sum_i y_i \bar h_i$$
This also carries over to specific heats:
$$\bar c_v = \sum_i y_i \bar c_{v,i} \quad \text{and} \quad \bar c_p = \sum_i y_i \bar c_{p,i}$$
Remember that:
$$\bar c_v = \bar c_p + \bar R $$
🤖 (notecheck comment) — For an ideal gas, the correct relationship is $c_p = c_v + R$, not $c_v = c_p + R$.
The comment highlights the error, allowing you to review and correct the note accordingly.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file notecheck-0.1.0.tar.gz.
File metadata
- Download URL: notecheck-0.1.0.tar.gz
- Upload date:
- Size: 4.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.22
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cb974673681c388d7e89b215a6ce0b6f06ed27adf2ebb5df19cfcec45491e079
|
|
| MD5 |
9efebd234fc1c8602dc90780e03c2c36
|
|
| BLAKE2b-256 |
d8f794bf3459a3c38a9324f3299281f1b7e3f6699abad7ec27a353db7604bbca
|
File details
Details for the file notecheck-0.1.0-py3-none-any.whl.
File metadata
- Download URL: notecheck-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.22
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8d22216cebee1a9740497341c6fe6f9ed3c5d29a45f9cc1e062ae30c9674a63f
|
|
| MD5 |
ce8755bca948e861e56c9f852a08b17c
|
|
| BLAKE2b-256 |
bbd0548ccc22fedc70cd254902e401333219108600e6c3c7306d50c23aae051e
|