mirror of
https://github.com/qdrant/qdrant.git
synced 2026-07-26 04:31:02 -05:00
ecae89ef4d
* Fix edge sparse vector search panic on score postprocessing The distance lookup for score postprocessing only checked dense vector configs, causing a panic when searching sparse vectors. Fall back to Distance::Dot for sparse vectors, matching the full server behavior. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Fix formatting Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * Address PR review: return error instead of panic, fix example - Replace panic! with OperationError::service_error for unknown vector names in edge search, avoiding process crash on bad client input - Update stale "panics" comments and add assertions in sparse-search example Made-with: Cursor --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Cursor Agent <agent@cursor.com>
41 lines
1.6 KiB
Python
41 lines
1.6 KiB
Python
import os, shutil
|
|
from pathlib import Path
|
|
|
|
from qdrant_edge import (
|
|
EdgeShard, EdgeConfig, EdgeVectorParams, EdgeSparseVectorParams,
|
|
Distance, Modifier, Query, QueryRequest,
|
|
Point, SparseVector, UpdateOperation,
|
|
)
|
|
|
|
|
|
DATA_DIR = Path(__file__).parent.parent.parent / "data"
|
|
TMP_DIR = DATA_DIR / "tmp"
|
|
|
|
path = TMP_DIR / "qdrant_edge_sparse_bug"
|
|
shutil.rmtree(path, ignore_errors=True)
|
|
os.makedirs(path)
|
|
|
|
config = EdgeConfig(
|
|
vectors=EdgeVectorParams(size=4, distance=Distance.Cosine),
|
|
sparse_vectors={"sparse": EdgeSparseVectorParams(modifier=Modifier.Idf)},
|
|
)
|
|
shard = EdgeShard.create(path, config)
|
|
|
|
shard.update(UpdateOperation.upsert_points([
|
|
Point(1, {"": [0.5, 0.5, 0.3, 0.1], "sparse": SparseVector(indices=[1, 2], values=[1.0, 0.5])}, {"text": "doc 1"}),
|
|
Point(2, {"": [0.1, 0.9, 0.3, 0.1], "sparse": SparseVector(indices=[2, 3], values=[1.0, 0.5])}, {"text": "doc 2"}),
|
|
Point(3, {"": [0.9, 0.1, 0.3, 0.1], "sparse": SparseVector(indices=[1, 3], values=[1.0, 0.5])}, {"text": "doc 3"}),
|
|
]))
|
|
shard.optimize()
|
|
print(f"Info: {shard.info()}") # Shows indexed_vectors_count=3
|
|
|
|
# Dense search
|
|
r = shard.query(QueryRequest(limit=3, query=Query.Nearest([0.5, 0.5, 0.3, 0.1]), with_payload=True))
|
|
print(f"Dense: {len(r)} results")
|
|
assert len(r) == 3, f"Dense query should return 3 results, got {len(r)}"
|
|
|
|
# Sparse search
|
|
sv = SparseVector(indices=[1, 2], values=[1.0, 0.5])
|
|
r = shard.query(QueryRequest(limit=3, query=Query.Nearest(sv, using="sparse"), with_payload=True))
|
|
print(f"Sparse: {len(r)} results")
|
|
assert len(r) == 3, f"Sparse query should return 3 results, got {len(r)}" |