Agent-Skills.md

Agent Skills: Zvec

Zvec in-process vector database. Covers collections, embedding, reranking, persistence. Use when embedding Zvec as an in-process vector database, managing collections, configuring embedding/reranking, or running approximate nearest-neighbor searches. Keywords: Zvec, vector DB, ANN, SQLite for vectors.

UncategorizedID: itechmeat/llm-code/zvec

Repository

itechmeat/llm-code
itechmeatLicense: MIT
11

Install this agent skill to your local

pnpm dlx add-skill https://github.com/itechmeat/llm-code/tree/HEAD/skills/zvec

Skill Files

Browse the full folder contents for zvec.

Download Skill

Loading file tree…

skills/zvec/SKILL.md

Skill Metadata

Name
zvec
Description
"Zvec in-process vector database. Covers collections, embedding, reranking, persistence. Use when embedding Zvec as an in-process vector database, managing collections, configuring embedding/reranking, or running approximate nearest-neighbor searches. Keywords: Zvec, vector DB, ANN, SQLite for vectors."

Zvec

Zvec is a lightweight, in-process vector database meant to be embedded into applications ("SQLite for vectors").

Quick navigation

  • Overview: references/overview.md
  • Concepts: references/concepts.md
  • Quickstart (first operations): references/quickstart.md
  • Installation (only if needed): references/installation.md
  • Embedding pipelines: references/embedding.md
  • Reranking pipelines: references/reranker.md
  • Data modeling & collections: references/collections.md
  • CRUD / search operations: references/data-operations.md
  • Configuration & persistence: references/configuration.md

Operator recipes (high signal)

  • Minimal “embed Zvec” checklist

    • (Optional) Configure globals once at startup via zvec.init(...) (logging, query_threads).
    • Create a collection on disk with create_and_open(path=..., schema=..., option=...).
    • Ingest documents as Doc(id=..., fields=..., vectors=...) via insert() or upsert().
    • Query via collection.query(vectors=VectorQuery(...), topk=...).
    • Call collection.optimize() periodically after heavy ingestion.

  • Bulk ingest + keep query latency stable

    • Prefer batched insert() / upsert().
    • Monitor collection.stats and run optimize() when flat buffers grow.

  • Hybrid retrieval patterns

    • Filter-only: collection.query(filter=..., topk=...).
    • Vector + filter: pass both vectors=... and filter=....
    • Multi-vector fusion: pass multiple VectorQuery items and rerank using WeightedReRanker or RRF.

  • Safe evolution of live collections

    • Add/drop/alter scalar columns via add_column(), drop_column(), alter_column().
    • Manage indexes via create_index() / drop_index() (scalar). Vector indexes cannot be dropped.

Critical prohibitions

  • Do not mirror vendor docs verbatim; summarize in your own words.
  • Do not assume a client/server deployment model: Zvec is in-process.
  • Do not add project-specific paths, secrets, or environment assumptions.

Links

  • Documentation: https://zvec.org/en/docs/
  • GitHub: https://github.com/alibaba/zvec
  • Releases: https://github.com/alibaba/zvec/releases
  • Issues: https://github.com/alibaba/zvec/issues
Zvec Skill | Agent Skills