Superlinked

pip install sie-lancedb

npm install @superlinked/sie-lancedb @lancedb/lancedb

import tempfile
from pathlib import Path

from lancedb.embeddings import get_registry
from lancedb.pydantic import LanceModel, Vector
import sie_lancedb  # registers "sie" and "sie-multivector"

sie = get_registry().get("sie").create(
    model="BAAI/bge-m3",
    base_url="http://localhost:8080",
)

class Documents(LanceModel):
    id: int
    text: str = sie.SourceField()
    vector: Vector(sie.ndims()) = sie.VectorField()

db = lancedb.connect(str(Path(tempfile.mkdtemp()) / "superlinked-demo"))
table = db.create_table("docs", schema=Documents)

table.add([
    {"id": 1, "text": "Machine learning is a subset of AI."},
    {"id": 2, "text": "Neural networks use multiple layers."},
    {"id": 3, "text": "Python is popular for ML development."},
])

results = table.search("What is deep learning?").limit(3).to_list()

from sie_lancedb import SIEReranker

# Create FTS index for hybrid search
table.create_fts_index("text", replace=True)

results = (
    table.search("What is deep learning?", query_type="hybrid")
    .rerank(SIEReranker(model="jinaai/jina-reranker-v2-base-multilingual"))
    .limit(5)
    .to_list()
)

for r in results:
    print(f"{r['_relevance_score']:.3f}  {r['text']}")

from lancedb.pydantic import MultiVector

sie_colbert = get_registry().get("sie-multivector").create(
    model="jinaai/jina-colbert-v2",
    base_url="http://localhost:8080",
)

class ColBERTDocs(LanceModel):
    text: str = sie_colbert.SourceField()
    vector: MultiVector(sie_colbert.ndims()) = sie_colbert.VectorField()

table = db.create_table("colbert_docs", schema=ColBERTDocs)

# Compute the document multivectors and store them with their text
texts = ["Machine learning is a subset of AI."]
vectors = sie_colbert.compute_source_embeddings(texts)
table.add([{"text": text, "vector": vector} for text, vector in zip(texts, vectors)])

# MaxSim search - query and document multivectors compared token-by-token
results = table.search("What is ML?").limit(5).to_list()

from sie_lancedb import SIEExtractor

extractor = SIEExtractor(
    base_url="http://localhost:8080",
    model="urchade/gliner_multi-v2.1",
)

docs = db.open_table("docs")
extractor.enrich_table(
    docs,
    source_column="text",
    target_column="entities",
    labels=["person", "technology", "organization"],
    id_column="id",
)