(Tutorial) Building a Visual Document Retrieval Pipeline with Collateral and Late Interaction Scoring

import subprocess, sys, os, json, hashlib


def pip(cmd):
   subprocess.check_call((sys.executable, "-m", "pip") + cmd)


pip(("uninstall", "-y", "pillow", "PIL", "torchaudio", "colpali-engine"))
pip(("install", "-q", "--upgrade", "pip"))
pip(("install", "-q", "pillow<12", "torchaudio==2.8.0"))
pip(("install", "-q", "colpali-engine", "pypdfium2", "matplotlib", "tqdm", "requests"))