mxbai-edge-colbert-v0-32m

# uv
uv add pylate
# uv + pip
uv pip install pylate

# pip
pip install -U pylate

from pylate import indexes, models, retrieve

# Step 1: Load the model
model = models.ColBERT(
    model_name_or_path="mixedbread-ai/mxbai-edge-colbert-v0-32m",
)


# Step 2: Initialize an index (here, PLAID, for larger document collections)
index = indexes.PLAID(
    index_folder="pylate-index",
    index_name="index",
    override=True,  # This overwrites the existing index if any
)

# Step 3: Encode your documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]

documents_embeddings = model.encode(
    documents,
    batch_size=32,
    is_query=False,  # Ensure that it is set to False to indicate that these are documents, not queries
    show_progress_bar=True,
)

# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
    documents_ids=documents_ids,
    documents_embeddings=documents_embeddings,
)