Skip to main content

docs2llm

A command-line tool to extract documentation from local directories and GitHub repositories, formatting it for use as context with Large Language Models (LLMs).

Purpose

docs2llm helps you capture documentation from codebases to use as context for AI assistants and large language models. It searches for documentation files (markdown, text, etc.), processes them, and creates a single consolidated file that can be used as reference material for LLMs.

Features

  • Extract documentation from local directories or GitHub repositories
  • Automatically identify and process common documentation files
  • Prioritize README files and important documentation
  • Support for multiple file formats (Markdown, RST, TXT)
  • Format output for optimal LLM context
  • Control scan depth to manage output size
  • Clone specific branches from Git repositories
  • Detailed logging with configurable verbosity

Installation

# Install from PyPI
pip install docs2llm

Usage

Command Line Interface

# Extract docs from a local directory
docs2llm /path/to/project --output context.txt

# Extract docs from a GitHub repository
docs2llm --git owner/repo --output context.txt

# Specify a branch
docs2llm --git owner/repo --branch develop

# Control scan depth
docs2llm /path/to/project --max-depth 2

# Enable verbose logging
docs2llm /path/to/project -v

# Write logs to a file
docs2llm /path/to/project --log-file extraction.log

Options

  • PATH: Local directory containing documentation files
  • --git: GitHub repository URL or owner/repo format
  • --output: Output file name (default: llm_context.txt)
  • --max-depth: Maximum directory depth to search (default: 3)
  • --branch: Specific branch to clone (only used with --git)
  • --verbose, -v: Enable verbose logging
  • --log-file: Log to this file in addition to console

Python API

from docs2llm import extract_documentation

# Extract from local directory
success = extract_documentation(
    local_path="/path/to/project",
    output_file="context.txt",
    max_depth=3,
    verbose=True
)

# Extract from GitHub repository
success = extract_documentation(
    git_repo="owner/repo",
    output_file="context.txt",
    branch="main",
    verbose=True
)

Metadata

Release files for docs2llm 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for docs2llm 0.1.0
File Size Uploaded
docs2llm-0.1.0.tar.gz 22.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for docs2llm 0.1.0
File Interpreter ABI Platform
docs2llm-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 31.6 kB

Release files / docs2llm-0.1.0.tar.gz

Download URL docs2llm-0.1.0.tar.gz
Size 22.8 kB
Tags Source
SHA-256 checksum
How to use checksums
904b479f5f425c5d03381af0904ada252ad4c08dad04345ecce86fd84ecac42c
BLAKE2b-256 checksum
How to use checksums
3cecb5419cc88dc748c591e365e97847b24bca138c97705d4594865f17985aea
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 14, 2025.

Transparency log

Release files / docs2llm-0.1.0-py3-none-any.whl

Download URL docs2llm-0.1.0-py3-none-any.whl
Size 8.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
64ede59f2556eda6ff110fa305e2babf8aeed6fcd5149ff6945590628ef3c62a
BLAKE2b-256 checksum
How to use checksums
375bdc2c53e1ff1ae0bdcb08aecdc0a9618e0212cb1119e1d78ca2d185aa16e6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 14, 2025.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page