Infinity-Parser2-Pro

# Create a Conda environment (Optional)
conda create -n infinity_parser2 python=3.12
conda activate infinity_parser2

# Install PyTorch (CUDA). Find the proper version at https://pytorch.org/get-started/previous-versions based on your CUDA version.
pip install torch==2.10.0 torchvision==0.25.0 torchaudio==2.10.0 --index-url https://download.pytorch.org/whl/cu128

# Install FlashAttention (FlashAttention-2 is recommended by default)
# Standard install (compiles from source, ~10-30 min):
pip install flash-attn==2.8.3 --no-build-isolation
# Faster install: download wheel from https://github.com/Dao-AILab/flash-attention/releases. Then run: pip install /path/to/<wheel_filename>.whl
# For Hopper GPUs (e.g. H100, H800), we recommend FlashAttention-3 instead. See: https://github.com/Dao-AILab/flash-attention
# NOTE: The code will prioritize detecting FlashAttention-3. If not found, it falls back to FlashAttention-2.

# Install vLLM
# NOTE: you may need to run the command below to resolve triton and numpy conflicts before installing vllm.
# pip uninstall -y pytorch-triton opencv-python opencv-python-headless numpy && rm -rf "$(python -c 'import site; print(site.getsitepackages()[0])')/cv2"
pip install vllm==0.17.1

pip install infinity_parser2

git clone https://github.com/infly-ai/INF-MLLM.git
cd INF-MLLM/Infinity-Parser2
pip install -e .

# NOTE: The Infinity-Parser2 model will be automatically downloaded on the first run.

# Parse a PDF (outputs Markdown by default)
parser demo_data/demo.pdf

# Parse an image
parser demo_data/demo.png

# Batch parse multiple files
parser demo_data/demo.pdf demo_data/demo.png -o ./output

# Parse an entire directory
parser demo_data -o ./output

# Output raw JSON with layout bboxes
parser demo_data/demo.pdf --output-format json

# Convert to Markdown directly
parser demo_data/demo.png --task doc2md