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
Remove convert_to_tensor=True in MultiVectorEncoder, this parameter was removed
#16
by tomaarsen HF Staff - opened
Hello!
This simple PR removes convert_to_tensor=True in the MultiVectorEncoder encode_query/encode_document/encode calls, as I removed this parameter and made a Tensor output the default just prior to the release. I didn't realize these snippets still used this parameter, my apologies!
- Tom Aarsen
QuentinJG changed pull request status to merged