Instructions to use BAAI/BGE-VL-Screenshot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BAAI/BGE-VL-Screenshot with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BAAI/BGE-VL-Screenshot", trust_remote_code=True) sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
About query_embeddings
#1
by lzzw666 - opened
How can I correctly obtain query_embeddings for offline retrieval? The current code for obtaining query_embeddings requires additional loading of images, for example:
query_inputs = model.data_process(
images=['query.png'],
text=[texts],
q_or_c="query",
)
There should be a way to embed text without images.
Thanks!
lzzw666 changed discussion status to closed