---
id: colpali-engine
version: "0.3.17"
license: unclear
license_treatment: permissive
maintenance: active
---

# colpali-engine — The code used to train and run inference with the ColPali architecture.

License: permissive · Maintenance: active · Downloads: 154.3K/mo

## What it is and what it does

ColPali-engine is a PyTorch-based library for training and running inference with vision-language document retrieval models. It implements the ColPali architecture and variants (ColQwen, ColSmol, etc.) that convert document images into multi-vector embeddings using visual transformers, enabling efficient semantic search over documents without requiring separate OCR or layout recognition pipelines. The library depends on numpy, scipy, torch, torchvision, transformers, pillow, peft, and requests.

The package is designed for developers and researchers building document retrieval systems. It supports multiple pre-trained model variants with different performance-efficiency tradeoffs, from small models (256M parameters) to larger ones (4.5B+). The core approach follows ColBERT's late-interaction ranking method adapted to the visual domain, allowing both the textual and visual content (layout, charts, images) of documents to influence retrieval scoring.

Use it for:

- Build a document search engine that retrieves pages from PDFs or scanned documents based on natural language queries without OCR
- Index and retrieve technical documentation, research papers, or forms where layout and visual structure matter for understanding
- Create a multilingual document retrieval system using models with support across multiple languages
- Fine-tune a pre-trained model on domain-specific documents using the training utilities and LoRA support
- Deploy efficient document ranking in production with optional fused MaxSim kernels for reduced memory usage

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

ColPali-engine provides training and inference code for vision-language document retrieval models that create multi-vector embeddings from document images using visual transformers, enabling efficient document search without OCR.

Yes. Active maintenance, permissive MIT license, low install friction, no known vulnerabilities, and a focused scope for vision-based document retrieval make it a solid choice. Install if you need to search documents visually without OCR pipelines; skip if you only work with plain text or have existing OCR infrastructure.

## Install

pip install colpali-engine
uv add colpali-engine
poetry add colpali-engine

## Installing colpali-engine

Before you install: Low friction install with a pure Python wheel. Active maintenance with recent commits; last release 67 days ago. Requires PyTorch and related deep learning dependencies, which are substantial but standard for this domain.

License in practice: MIT license (permissive) allows commercial and private use with minimal restrictions, making it suitable for both research and production deployment.

Quickstart:

pip install colpali-engine

from colpali_engine.models import ColPali
from colpali_engine.utils import process_documents

model = ColPali.from_pretrained('vidore/colqwen2-v1.0')
embeddings = model.encode_documents(documents)

Requires Python >=3.10,<3.15 and PyTorch; Mac users with MPS and torch 2.6.0 should downgrade to torch 2.5.1 for ColQwen models.

Verify before relying:

- Whether the package includes full training utilities or primarily inference code
- Performance characteristics (throughput, latency) for typical document batch sizes
- GPU memory requirements for different model variants listed in the description

## Package facts

- License: not declared (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 154.3K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

document retrieval vision language models, visual document search embeddings, multi-vector document ranking, vision transformer document indexing, ColBERT visual retrieval, document image embedding, layout-aware document search, document-retrieval, vision-language-models, information-retrieval

[View on SkillFed](https://skillfed.io/packages/colpali-engine) · [View on PyPI](https://pypi.org/project/colpali-engine/)