ParseDoc

Document → AI → Markdown. A local-first CLI that converts documents into clean, structured, AI-ready Markdown.

ParseDoc turns PDFs, Word docs, PowerPoint decks, HTML pages, plain text, and images into well-structured Markdown. Libraries extract the raw facts, an optional AI model understands the structure, and a deterministic renderer produces the final output. It works fully offline (local rule-based structuring) and can optionally use an AI provider for smarter structuring.

---

Demo

Your browser does not support the video tag. You can download the demo here.

---

Screenshots / Proofs

---

Features

• Local-first: conversion works with no AI provider configured (deterministic fallback).
• Multi-format input: PDF, DOCX, PPTX, HTML, TXT/MD, and images (PNG/JPG) via OCR.
• AI structuring (optional): local, ai, or hybrid modes.
• Pluggable AI providers: OpenAI-compatible (vLLM/LM Studio/OpenRouter), OpenAI, Google Gemini, Ollama (native), and LM Studio.
• Document fidelity: preserves headings, bold/italic, lists, and keeps tables in their original position.
• Image extraction: pull embedded images from DOCX into an assets folder.
• OCR: Tesseract-backed text extraction for scanned PDFs and images.
• Multiple output formats: markdown (default), json, html, text.

---

Installation

pip install docpilot-ai

The PyPI package is named docpilot-ai; the import name and CLI command are both parsedoc.

Full setup, configuration, and provider instructions are in setup.md.

---

Quick start

# Convert a single document
parsedoc convert input.docx -o output.md --mode hybrid

# Convert a whole folder (creates ./batch_out in the current directory)
parsedoc batch . -p "*.docx"

# Inspect a document's structure
parsedoc inspect input.pdf --format summary

# Show configuration
parsedoc config list

# Banner + version
parsedoc version

Modes

Mode	Behavior
local	Pure rule-based structuring. No network calls. Fast and private.
ai	Structures content using the configured AI provider.
hybrid	Uses AI when available, falls back to local structuring on failure.

---

Supported input formats

Format	Extensions
PDF	.pdf
Word	.docx
PowerPoint	.pptx
HTML	.html, .htm
Text / Markdown	.txt, .md, .markdown
Images	.png, .jpg, .jpeg (OCR)

---

Configuring your API

ParseDoc supports several AI providers. Configure via parsedoc config, environment variables, or the TOML file. Examples:

# OpenAI-compatible (e.g. xkiro)
parsedoc config set --key ai_provider --value openai-compatible
parsedoc config set --key base_url --value "https://api.xkiro.com/v1"
parsedoc config set --key model --value "stealth/ox-alpha-free"
parsedoc config set --key api_key --value "sk-xt-..."

# LM Studio (local, defaults to http://localhost:1234/v1)
parsedoc config set --key ai_provider --value lm-studio
parsedoc config set --key model --value local-model

# Ollama (local)
parsedoc config set --key ai_provider --value ollama
parsedoc config set --key model --value qwen3

See setup.md for the complete list of providers (openai-compatible, openai, gemini, ollama, lm-studio), all config keys, environment-variable overrides, and troubleshooting.

---

Using ParseDoc as a library

from parsedoc.core.config import Config
from parsedoc.core.pipeline import Pipeline

config = Config().load_from_file()
pipeline = Pipeline(config)

markdown = pipeline.process(
    "report.docx",
    output_format="markdown",
    mode="hybrid",
    extract_images=True,
    output_path="report.md",
)

---

License

MIT — see LICENSE.