OpenAIReview

OpenAIReview

[](https://pypi.org/project/openaireview/)

Our goal is provide thorough and detailed reviews to help researchers conduct the best research. See more examples [here](https://openaireview.github.io/).


Installation

uv venv && uv pip install openaireview
# or: pip install openaireview

For fast PDF processing (requires `MISTRAL_API_KEY`):

uv pip install "openaireview[mistral]"

For development:

git clone https://github.com/ChicagoHAI/OpenAIReview.git
cd OpenAIReview
uv venv && uv pip install -e .
# or: pip install -e .

Updates

• --max-pages and --max-tokens to limit input size and save OCR cost
• Mistral OCR and DeepSeek OCR as optional PDF engines (pip install "openaireview[mistral]")
• openaireview extract subcommand for two-stage OCR + review workflow
• Multi-provider routing: OpenRouter, OpenAI, Anthropic, Gemini, Mistral (--provider)
• Table and figure extraction from arXiv HTML (tables as markdown)
• pymupdf4llm + GNN layout as default PDF fallback (replaces raw PyMuPDF)
• Mobile-responsive visualization UI
• Collapsible resolved comments in viz
• Claude Code skill (/openaireview) with multi-agent pipeline

PDF parsing engines (optional)

PDF extraction quality matters — math symbols, tables, and reading order all affect review quality. Four engines are supported, tried in order:

Engine	Install	Best for	Notes
Mistral OCR	pip install "openaireview[mistral]" + set MISTRAL_API_KEY	Best overall quality, math, tables	Cloud API, ~$0.001/page
DeepSeek OCR	pip install "openaireview[deepseek]" + local backend	Privacy-sensitive docs	Local model via Ollama/vLLM
Marker	uv tool install marker-pdf --with psutil	Math-heavy PDFs (offline)	Slow without GPU
pymupdf4llm	(included)	Fallback, always avail