granite-embedding-30m-sparse

pip install pymilvus[model]

from pymilvus import model
from pymilvus import MilvusClient, DataType

client = MilvusClient("./milvus_demo.db")

client.drop_collection(collection_name="my_sparse_collection")

schema = client.create_schema(
    auto_id=True,
    enable_dynamic_fields=True,
)

schema.add_field(field_name="pk", datatype=DataType.VARCHAR, is_primary=True, max_length=100)
schema.add_field(field_name="id", datatype=DataType.VARCHAR, is_primary=False, max_length=100)
schema.add_field(field_name="embeddings", datatype=DataType.SPARSE_FLOAT_VECTOR)

index_params = client.prepare_index_params()

index_params.add_index(field_name="embeddings",
                               index_name="sparse_inverted_index",
                               index_type="SPARSE_INVERTED_INDEX",
                               metric_type="IP",
                               params={"drop_ratio_build": 0.2})
client.create_collection(
    collection_name="my_sparse_collection",
    schema=schema,
    index_params=index_params
)

embeddings_model = model.sparse.SpladeEmbeddingFunction(
    model_name="ibm-granite/granite-embedding-30m-sparse", 
    device="cpu",
    batch_size=2,
    k_tokens_query=50,
    k_tokens_document=192
)

# Prepare documents to be ingested
docs = [
    "Artificial intelligence was founded as an academic discipline in 1956.",
    "Alan Turing was the first person to conduct substantial research in AI.",
    "Born in Maida Vale, London, Turing was raised in southern England.",
]

# SpladeEmbeddingFunction.encode_documents returns sparse matrix or sparse array depending
# on the milvus-model version. reshape(1,-1) ensures the format is correct for ingestion.
doc_vector = [{"embeddings": doc_emb.reshape(1,-1), "id": f"item_{i}"} for i, doc_emb in enumerate(embeddings_model.encode_documents(docs))]


client.insert(
    collection_name="my_sparse_collection",
    data=doc_vector
)

# Prepare search parameters
search_params = {
    "params": {"drop_ratio_search": 0.2},  # Additional optional search parameters
}

# Prepare the query vector

queries = [
      "When was artificial intelligence founded", 
      "Where was Turing born?"
]
query_vector = embeddings_model.encode_documents(queries)

res = client.search(
    collection_name="my_sparse_collection",
    data=query_vector,
    limit=1, #top k documents to return
    output_fields=["id"],
    search_params=search_params,
)

for r in res:
    print(r)

pip install -U sentence-transformers

from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("ibm-granite/granite-embedding-30m-sparse")

# Run inference
docs = [
    "Artificial intelligence was founded as an academic discipline in 1956.",
    "Alan Turing was the first person to conduct substantial research in AI.",
    "Born in Maida Vale, London, Turing was raised in southern England.",
]
docs_embeddings = model.encode_document(docs, max_active_dims=192)
print(docs_embeddings.shape)
# [3, 50265]

queries = ["When was artificial intelligence founded", "Where was Turing born?"]
queries_embeddings = model.encode_query(queries, max_active_dims=50)
print(queries_embeddings.shape)
# [2, 50265]

# Get the similarity scores for the embeddings
similarities = model.similarity(queries_embeddings, docs_embeddings)
print(similarities.shape)
# [2, 3]

for i, query in enumerate(queries):
    best_doc_index = similarities[i].argmax().item()

    print(f"Query: {query}")
    print(f"Best doc associate: Similarity: {similarities[i][best_doc_index]:.4f}, Doc: {docs[best_doc_index]}")
    intersection = model.intersection(queries_embeddings[i], docs_embeddings[best_doc_index])
    decoded_intersection = model.decode(intersection, top_k=10)
    print("Top 10 tokens influencing the similarity:")
    for token, score in decoded_intersection:
        print(f"Token: {token}, Score: {score:.4f}")

# Query: When was artificial intelligence founded
# Best doc associate: Similarity: 12.3641, Doc: Artificial intelligence was founded as an academic discipline in 1956.
# Top 10 tokens influencing the similarity:
# Token: ĠAI, Score: 2.7591
# Token: Ġintelligence, Score: 2.2971
# Token: Ġartificial, Score: 1.7654
# Token: Ġfounded, Score: 1.3254
# Token: Ġinvention, Score: 0.9808
# Token: Ġlearning, Score: 0.4847
# Token: Ġcomputer, Score: 0.4789
# Token: Ġrobot, Score: 0.3466
# Token: Ġestablishment, Score: 0.3371
# Token: Ġscientific, Score: 0.2804
# Query: Where was Turing born?
# Best doc associate: Similarity: 17.1359, Doc: Born in Maida Vale, London, Turing was raised in southern England.
# Top 10 tokens influencing the similarity:
# Token: uring, Score: 2.9761
# Token: ĠTuring, Score: 2.4544
# Token: Ġborn, Score: 2.4314
# Token: ing, Score: 1.7760
# Token: ure, Score: 1.7626
# Token: Ġcomput, Score: 1.3356
# Token: Ġraised, Score: 1.3285
# Token: able, Score: 1.1940
# Token: Ġphilosopher, Score: 0.4118
# Token: Ġmachine, Score: 0.3977

@misc{awasthy2025graniteembeddingmodels,
      title={Granite Embedding Models}, 
      author={Parul Awasthy and Aashka Trivedi and Yulong Li and Mihaela Bornea and David Cox and Abraham Daniels and Martin Franz and Gabe Goodhart and Bhavani Iyer and Vishwajeet Kumar and Luis Lastras and Scott McCarley and Rudra Murthy and Vignesh P and Sara Rosenthal and Salim Roukos and Jaydeep Sen and Sukriti Sharma and Avirup Sil and Kate Soule and Arafat Sultan and Radu Florian},
      year={2025},
      eprint={2502.20204},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2502.20204}, 
}