neurobyte 0.2.0

Export Jupyter notebooks into narrated, cell-labeled text.

Neurobyte

Export Jupyter notebooks into narrated, cell-labeled text for LLM contexts.

Features

• Clean Export: Extracts code cells from .ipynb files.
• Narrative Summary: Generates a header paragraph summarizing the code's intent.
• Neurobyte Outline: Adds a structured outline with markdown headers.
• Redaction: Automatically redacts sensitive patterns (API keys, BQ table IDs).
• JSON Output: Machine-readable format for indexing and search.
• Markdown Cells: Include # headers in the outline.
• Custom Redaction: Add your own regex patterns.
• Cell Selection: Export specific cell ranges.

Installation

pip install neurobyte

Usage

CLI

# Basic export
python -m neurobyte export notebook.ipynb

# Specify output file
python -m neurobyte export notebook.ipynb -o summary.txt

# JSON output
python -m neurobyte export notebook.ipynb --json

# Include markdown cells
python -m neurobyte export notebook.ipynb --include-markdown

# Custom redaction pattern
python -m neurobyte export notebook.ipynb --redact-pattern 'client_id=\d+'

# Export specific cells
python -m neurobyte export notebook.ipynb --cells 1-5

# Disable redaction
python -m neurobyte export notebook.ipynb --no-redact

Python API

import neurobyte as nb
from neurobyte.export import ExportOptions

# Basic export
nb.export_notebook("notebook.ipynb", "export.txt")

# With options
opts = ExportOptions(
    output_format="json",
    include_markdown=True,
    redact_secrets=True,
    extra_redact_patterns=["client_id=\\d+"],
    cell_indices=[1, 2, 3],
)
nb.export_notebook("notebook.ipynb", "export.json", options=opts)

# Export from live session (requires IPython)
nb.export_here("session.txt")

Development

This project uses make for common development tasks.

# Install dependencies
make install

# Run tests (Pytest)
make test

# Linting & Formatting (Ruff, Black, Mypy)
make lint
make format