ColPali is a model based on a novel model architecture and training strategy based on Vision Language Models (VLMs) to efficiently index documents from their visual features. It is a PaliGemma-3B extension that generates ColBERT- style multi-vector representations of text and images. It was introduced in the paper ColPali: Efficient Document Retrieval with Vision Language Models and first released in this repository

Model Description

This model is built iteratively starting from an off-the-shelf SigLIP model. We finetuned it to create BiSigLIP and fed the patch-embeddings output by SigLIP to an LLM, PaliGemma-3B to create BiPali.

One benefit of inputting image patch embeddings through a language model is that they are natively mapped to a latent space similar to textual input (query). This enables leveraging the ColBERT strategy to compute interactions between text tokens and image patches, which enables a step-change improvement in performance compared to BiPali.

Version specificity

[!NOTE] This version is similar to vidore/colpali-v1.3, except that the LoRA adapter was merged into the base model. Thus, loading ColPali from this checkpoint saves you the trouble of merging the pre-trained adapter yourself.

This can be useful if you want to train a new adpter from scratch.

Model Training

Dataset

Our training dataset of 127,460 query-page pairs is comprised of train sets of openly available academic datasets (63%) and a synthetic dataset made up of pages from web-crawled PDF documents and augmented with VLM-generated (Claude-3 Sonnet) pseudo-questions (37%). Our training set is fully English by design, enabling us to study zero-shot generalization to non-English languages. We explicitly verify no multi-page PDF document is used both ViDoRe and in the train set to prevent evaluation contamination. A validation set is created with 2% of the samples to tune hyperparameters.

Note: Multilingual data is present in the pretraining corpus of the language model (Gemma-2B) and potentially occurs during PaliGemma-3B's multimodal training.

Parameters

All models are trained for 1 epoch on the train set. Unless specified otherwise, we train models in bfloat16 format, use low-rank adapters (LoRA) with alpha=32 and r=32 on the transformer layers from the language model, as well as the final randomly initialized projection layer, and use a paged_adamw_8bit optimizer. We train on an 8 GPU setup with data parallelism, a learning rate of 5e-5 with linear decay with 2.5% warmup steps, and a batch size of 32.

Usage

Sentence Transformers

ColPali can be used as a multi-vector (ColBERT-style late interaction) retriever with Sentence Transformers via the MultiVectorEncoder:

pip install "sentence-transformers[image]>=6.0.0"

python

from sentence_transformers import MultiVectorEncoder

model = MultiVectorEncoder("vidore/colpali-v1.3-merged")

queries = [
    "What is the variable represented on the y-axis of the graph?",
    "Total outlay is maximum in which year?",
]
images = [
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc1.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc2.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc3.jpg",
    "https://huggingface.co/datasets/sentence-transformers/example-documents/resolve/main/doc4.jpg",
]

query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(images)
print(f"Query 0 shape:    {query_embeddings[0].shape}")
print(f"Document 0 shape: {document_embeddings[0].shape}")
"""
Query 0 shape:    torch.Size([28, 128])
Document 0 shape: torch.Size([1030, 128])
"""

scores = model.similarity(query_embeddings, document_embeddings)
print(scores)
"""
tensor([[22.3359, 19.8555, 19.6582, 19.0928],
        [ 5.8828, 13.3398,  6.1621,  6.8135]])
"""

ColPali Engine

[!WARNING] Note: current colpali-engine no longer sends the query prefix and trailing newline that this checkpoint was trained with. The trailing newline went in 0.3.11 (illuin-tech/colpali#280) and the prefix in 0.3.13 (illuin-tech/colpali#339). The Sentence Transformers configuration in this repository reproduces the original training-time format, so its embeddings differ slightly from current colpali-engine output.

The Sentence Transformers configuration also sends token_type_ids to the model, which on transformers 5.x is what makes PaliGemma build an explicit attention mask at all. Without it no mask is materialized and the shorter queries in a batch attend to their own padding.

Install colpali-engine:

pip install colpali-engine>=0.3.0,<0.4.0

Then run the following code:

python

from typing import cast

import torch
from PIL import Image

from colpali_engine.models import ColPali, ColPaliProcessor

model_name = "vidore/colpali-v1.3-merged"

model = ColPali.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="cuda:0",  # or "mps" if on Apple Silicon
).eval()
processor = ColPaliProcessor.from_pretrained(model_name)

# Your inputs
images = [
    Image.new("RGB", (32, 32), color="white"),
    Image.new("RGB", (16, 16), color="black"),
]
queries = [
    "Is attention really all you need?",
    "Are Benjamin, Antoine, Merve, and Jo best friends?",
]

# Process the inputs
batch_images = processor.process_images(images).to(model.device)
batch_queries = processor.process_queries(queries).to(model.device)

# Forward pass
with torch.no_grad():
    image_embeddings = model(**batch_images)
    querry_embeddings = model(**batch_queries)

scores = processor.score_multi_vector(querry_embeddings, image_embeddings)

Limitations

Focus: The model primarily focuses on PDF-type documents and high-ressources languages, potentially limiting its generalization to other document types or less represented languages.
Support: The model relies on multi-vector retreiving derived from the ColBERT late interaction mechanism, which may require engineering efforts to adapt to widely used vector retrieval frameworks that lack native multi-vector support.

License

ColPali's vision language backbone model (PaliGemma) is under gemma license as specified in its model card. Because the pre-trained adapter got merged in this model, the license for these weights are also under the gemma license

Contact

Manuel Faysse: manuel.faysse@illuin.tech
Hugues Sibille: hugues.sibille@illuin.tech
Tony Wu: tony.wu@illuin.tech

Citation

If you use any datasets or models from this organization in your research, please cite the original dataset as follows:

bibtex

@misc{faysse2024colpaliefficientdocumentretrieval,
  title={ColPali: Efficient Document Retrieval with Vision Language Models}, 
  author={Manuel Faysse and Hugues Sibille and Tony Wu and Bilel Omrani and Gautier Viaud and Céline Hudelot and Pierre Colombo},
  year={2024},
  eprint={2407.01449},
  archivePrefix={arXiv},
  primaryClass={cs.IR},
  url={https://arxiv.org/abs/2407.01449}, 
}