qdrant-sparse
Qdrant sparse vector operations: collection creation with SparseVectorParams, Modifier.IDF for miniCOIL/SPLADE/BM42, upserting SparseVector points, sparse search, hybrid search with prefetch + RRF/DBSF fusion, converting model outputs to SparseVector format, payload filtering, and performance tuning. Covers the sparse vector gap not handled by the official Qdrant MCP (which only supports dense vectors via FastEmbed).
npx skills add majiayu000/claude-skill-registry --skill qdrant-sparse --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Qdrant Sparse Vector Reference This skill covers everything needed to work with Qdrant's sparse vector features using the `qdrant-client` Python SDK. Sparse vectors are essential for lexical/token-level retrieval (miniCOIL, SPLADE, BM42) and hybrid search. ## 1. Collection Creation ### Sparse-Only Collection ```python from qdrant_client import QdrantClient, models client = QdrantClient(url="http://localhost:6333") client.create_collection( collection_name="sparse_only", vectors_config={}, # Empty — no dense vectors sparse_vectors_config={ "text": models.SparseVectorParams( modifier=models.Modifier.IDF, # Critical for miniCOIL/SPLADE/BM42 ) }, ) ``` ### Hybrid Collection (Dense + Sparse) ```python client.create_collection( collection_name="hybrid", vectors_config={ "dense": models.VectorParams( size=384, distance=models.Distance.COSINE, ) }, sparse_vectors_config={ "sparse": models.SparseVectorParams( modifier=models.Modifier.IDF, ) }, ) ``` ### Multiple Sparse Vector Fields A collection can have multiple named sparse vector fields: ```python client.create_collection( collection_name="multi_sparse", vectors_config={}, sparse_vectors_config={ "title": models.SparseVectorParams(modi
- 1. Collection Creation
- Sparse-Only Collection
- Hybrid Collection (Dense + Sparse)
- Multiple Sparse Vector Fields
- 2. Modifier.IDF — When and Why
- 3. Sparse Vector Format
- Converting Model Outputs to SparseVector
- miniCOIL Index Encoding
- 4. Upserting Points
- Single Point
- Batch Upsert
- Hybrid Upsert (Dense + Sparse)
- 5. Searching
- Basic Sparse Search
What does the qdrant-sparse skill do?
Qdrant sparse vector operations: collection creation with SparseVectorParams, Modifier.IDF for miniCOIL/SPLADE/BM42, upserting SparseVector points, sparse search, hybrid search with prefetch + RRF/DBSF fusion, converting model outputs to SparseVector format, payload filtering, and performance tuning. Covers the sparse vector gap not handled by the official Qdrant MCP (which only supports dense vectors via FastEmbed).
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill qdrant-sparse --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.