Results for “embedding-search”

Plan, debug, tune, evaluate, export, or deploy public Nemotron embedding and reranking retrieval recipes using the current checkout.

Embeds target and source image parquets, then mines nearest-neighbour source images for augmentation in VCN AOI workflows.

Analyze and improve the internal link structure of an AEM Edge Delivery Services site by building a link graph from the query index and page content, identifying orphan pages, hub pages, and content silos, and generating specific linking recommendations with suggested anchor text and placement.

基于 anchor 论文、topic 关键词或当前 wiki 状态，产出一份排好序的候选论文 shortlist，供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发；`/ingest --discover` 也会内部调用本 skill。本身不 ingest，只提出候选。

Use when searching NCBI Entrez databases (pubmed, gene, protein, nuccore, snp, geoprofiles) with query strings and field qualifiers to retrieve record UIDs for downstream processing.

HNSW vector search for pattern similarity retrieval and knowledge graph maintenance with PageRank scoring, community detection, and 3-tier memory management.

Integrate Elasticsearch and implement search index Sync patterns in NestJS. Use when integrating Elasticsearch or implementing search index sync in NestJS.

Augments nearest-neighbour search with graph Laplacian features to retrieve items based on both semantic similarity and structural role.

Build production-ready LLM applications, RAG systems, and intelligent agents with architecture design, model selection, and cost controls.