vector-search SKILL.md skillA
vector-search from sparq-org/sparq is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sparq-org/sparq/vector-search@git:20261026.6e0be1dPins git:20261026.6e0be1d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sparq-org/sparq
- Path
skills/vector-search/SKILL.md- Versions recorded
- 10
- Latest version
- git:20261026.6e0be1d, committed Oct 26, 2026
- First version recorded
- Jul 17, 2026
- Size
- 128,174 bytes
- Repository stars
- 13
- License
- MIT
Semantic / ANN vector search over a sparq RDF graph: build a memory-mapped per-term-id embedding store (.spqv), then run cosine top-k with an in-RAM HNSW, a persistent on-disk DiskANN/Vamana graph (.spqg), or an exact brute-force baseline; verbalize entities (label+type+description) for embedding, scalar/product quantize (SQ/PQ) for large stores, fuse with another ranked signal (RRF / score blend) for hybrid retrieval, run predicate-constrained (filtered) ANN over a BGP-selected dict-id mask…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# sparq-vector-search
`sparq-vectors` is an **opt-in** crate that adds embedding storage + nearest-neighbour
(ANN) search to the sparq RDF engine. You store one f32 embedding per dictionary **term
id** in a flat memory-mapped `.spqv` file, then query top-`k` by **cosine** with an exact
scan, an in-RAM HNSW index, or a persistent on-disk DiskANN/Vamana graph — all
cosine-identical so their scores are directly comparable. Embeddings are produced
**out-of-process** (you supply the `Embedder`); the crate never runs a model and the
default engine build does not even compile it.
Query rewrites and pre-binding retain VERSION announcements and their
[version-pinned EBV rules](../sparql-query/ebv-dialects.md). Unknown labels follow
the surface's existing query/ill-formed-input error policy.
## Quickstart
`crates/sparq-vectors/Cargo.toml` (it consumes `sparq-core`; no features needed for the
core flow):
```toml
[dependencies]
sparq-core = { path = "../sparq-core" }
sparq-vectors = { path = "../sparq-vectors" }
oxrdf = "*" # for oxrdf::{NamedNode, Term} in term-keyed queries
```
Embed entity labels, finalize the store, query the nearest neighbours of a term:
```rust
…Read the whole file at its exact version.
How to install
mdr add sparq-org/sparq/vector-search@sha256:2772ac4b34986c07The line at the top of this page pins the label git:20261026.6e0be1d, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2stvh4hyjj7orspc)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 10 versions of this file, between Jul 17, 2026 and Oct 26, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.6e0be1d latest | 2026-10-26 | 6e0be1d | 128,174 B | A | view · diff |
| git:20261014.012ebfd | 2026-10-14 | 012ebfd | 128,172 B | A | view · diff |
| git:20261009.21f6380 | 2026-10-09 | 21f6380 | 127,928 B | A | view · diff |
| git:20261009.f0b870d | 2026-10-09 | f0b870d | 127,356 B | A | view · diff |
| git:20261006.392a1d5 | 2026-10-06 | 392a1d5 | 127,899 B | A | view · diff |
| git:20260731.ce0affc | 2026-07-31 | ce0affc | 127,691 B | A | view · diff |
| git:20260728.1a69807 | 2026-07-28 | 1a69807 | 127,015 B | A | view · diff |
| git:20260728.be75669 | 2026-07-28 | be75669 | 121,496 B | A | view · diff |
| git:20260718.4bad8bc | 2026-07-18 | 4bad8bc | 116,046 B | A | view · diff |
| git:20260717.3527f96 | 2026-07-17 | 3527f96 | 113,092 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (128174 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sparq-org/sparq · 13 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2stvh4hyjj7orspc GET https://markdownregistry.com/api/v1/resolve?ref=sparq-org/sparq/vector-search GET https://markdownregistry.com/api/v1/blob/2772ac4b34986c07182dda826365161d87d75359d9a28c95086b5bcffbcedfd8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.