sie-qdrant

SIE integration for Qdrant.

Installation

pip install sie-qdrant

Dense embeddings

from qdrant_client import QdrantClient
from qdrant_client.models import Distance, VectorParams, PointStruct
from sie_qdrant import SIEVectorizer

vectorizer = SIEVectorizer(base_url="http://localhost:8080", model="BAAI/bge-m3")

qdrant = QdrantClient("http://localhost:6333")
qdrant.create_collection(
    collection_name="documents",
    vectors_config=VectorParams(size=1024, distance=Distance.COSINE),
)

texts = ["first doc", "second doc"]
vectors = vectorizer.embed_documents(texts)
qdrant.upsert(
    collection_name="documents",
    points=[
        PointStruct(id=i, vector=v, payload={"text": t})
        for i, (t, v) in enumerate(zip(texts, vectors))
    ],
)

query_vec = vectorizer.embed_query("search text")
results = qdrant.query_points(
    collection_name="documents", query=query_vec, limit=5
)

Named vectors (dense + sparse)

SIE's multi-output encode produces dense and sparse vectors in one call. Qdrant supports sparse vectors natively via SparseVector(indices, values), so no expansion to full vocabulary length is needed:

from qdrant_client import QdrantClient
from qdrant_client.models import (
    Distance, VectorParams, PointStruct,
    SparseVectorParams, SparseVector,
)
from sie_qdrant import SIENamedVectorizer

vectorizer = SIENamedVectorizer(
    base_url="http://localhost:8080",
    model="BAAI/bge-m3",
    output_types=["dense", "sparse"],
)

qdrant = QdrantClient("http://localhost:6333")
qdrant.create_collection(
    collection_name="documents",
    vectors_config={"dense": VectorParams(size=1024, distance=Distance.COSINE)},
    sparse_vectors_config={"sparse": SparseVectorParams()},
)

named = vectorizer.embed_documents(["hello world"])
qdrant.upsert(
    collection_name="documents",
    points=[
        PointStruct(
            id=0,
            vector={
                "dense": named[0]["dense"],
                "sparse": SparseVector(**named[0]["sparse"]),
            },
            payload={"text": "hello world"},
        )
    ],
)

Storage advantage: Unlike integrations that expand sparse vectors to full vocabulary length (~30K floats), Qdrant stores sparse vectors in their native indices+values form, making hybrid search storage-efficient.

Testing

# Unit tests (no server needed)
pytest

# Integration tests (requires SIE + Qdrant)
pytest -m integration

Metadata

Release files for sie-qdrant 0.8.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sie-qdrant 0.8.2
File	Size	Uploaded
sie_qdrant-0.8.2.tar.gz	10.1 kB	Sep 23, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for sie-qdrant 0.8.2
File	Interpreter	ABI	Platform	Reset
sie_qdrant-0.8.2-py3-none-any.whl 5.1 kB Sep 23, 2026	Python 3	none	any	Details

Total release size: 15.2 kB

Release files / sie_qdrant-0.8.2.tar.gz

Download URL	sie_qdrant-0.8.2.tar.gz
Size	10.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`c7bc886bafce0e1e6143b0df673bf24ad5b3a954f90422b5610d8a182bd44f2c`
BLAKE2b-256 checksum How to use checksums	`ccc3c0da379da6dfa95da12c2c3099af236155ab9d0c5b650dccd5ca1bfe643b`
Upload date	Sep 23, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/superlinked/sie
Publishing commit: github.com/superlinked/sie/tree/66daf371748b463f9f2bbe308ffb83f488f4cd8a

Workflow

Publishing configuration: github.com/superlinked/sie/blob/66daf371748b463f9f2bbe308ffb83f488f4cd8a/.github/workflows/release.yml
Publishing logs: github.com/superlinked/sie/actions/runs/35908401744/attempts/1

Artifact

Subject: sie_qdrant-0.8.2.tar.gz
SHA-256 checksum: c7bc886bafce0e1e6143b0df673bf24ad5b3a954f90422b5610d8a182bd44f2c Verifying attestations

Release files / sie_qdrant-0.8.2-py3-none-any.whl

Download URL	sie_qdrant-0.8.2-py3-none-any.whl
Size	5.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`154c2da92460420ac206abbaed9253496d3b6a17dc417a08c83ba1bda33aef51`
BLAKE2b-256 checksum How to use checksums	`673dd3cf49aa51ef0b7098148ddae29bdb110819425df3f277cbb405c5e0b396`
Upload date	Sep 23, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/superlinked/sie
Publishing commit: github.com/superlinked/sie/tree/66daf371748b463f9f2bbe308ffb83f488f4cd8a

Workflow

Publishing configuration: github.com/superlinked/sie/blob/66daf371748b463f9f2bbe308ffb83f488f4cd8a/.github/workflows/release.yml
Publishing logs: github.com/superlinked/sie/actions/runs/35908401744/attempts/1

Artifact

Subject: sie_qdrant-0.8.2-py3-none-any.whl
SHA-256 checksum: 154c2da92460420ac206abbaed9253496d3b6a17dc417a08c83ba1bda33aef51 Verifying attestations