Instructions to use vidore/colpali with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ColPali
How to use vidore/colpali with ColPali:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sentence-transformers
How to use vidore/colpali with sentence-transformers:
from sentence_transformers import MultiVectorEncoder model = MultiVectorEncoder("vidore/colpali") queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Notebooks
- Google Colab
- Kaggle
how generate the visualization that we have in the paper?
#7
by marcoaleixo - opened
first of all, awesome work, congrats!
but I'm here to ask something haha
can you share the code that you used to create the Figure 1 in the paper?
I'm testing the model in portuguese and really wan't to see this visualization as well :)
Hi @marcoaleixo , thanks for your interest in our model ππΌ
You can generate the similarity maps for ColPali using our vidore-benchmark tool. You should find all the information you need at: https://github.com/illuin-tech/vidore-benchmark.
tonywu71 changed discussion status to closed