605 个 · 按相关度排序
Assess the storage and retrieval layers of RAG systems, which search documents to support AI answers. Test persistent document poisoning, cross-tenant access, source-text leaks, and manipulated search rankings using independently verifiable evidence.
中文简介正在准备中。当前显示英语简介。
Use when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or PAIDF Data Mining nearest-neighbor matching on Curator embeddings. Activate for Make or CLI pipeline config, GPU run preflight, FFmpeg sidecar, SAM3 keys, or Curator-to-TAO handoff. Do not use for generic ETL, vector-database RAG, model training, orchestration, or embeddings outside Cosmos Curator and PAIDF Data Mining.
中文简介正在准备中。当前显示原文说明。
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
中文简介正在准备中。当前显示原文说明。
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starters, revision activities, or low-stakes testing materials.
中文简介正在准备中。当前显示原文说明。
Think and work like an expert Information Retrieval Scientist. Use when a task calls for Information Retrieval Scientist judgment. Reasons from the Probability Ranking Principle, Saracevic's relevance layers, and Cranfield pooling through tuned BM25, SPLADE/ColBERT/dense and LLM reranking, trec_eval/ir_measures with paired topic-level tests, interleaving, and nugget-based RAG evaluation while treating unjudged-as-nonrelevant pools, position-biased clicks, LLM-judge circularity, single-vector embedding limits, and benchmark contamination as first-class failure modes.
中文简介正在准备中。当前显示原文说明。
Designing search engines and vector DBs for full-text, vector, and hybrid retrieval, including permission-aware retrieval for multi-tenant or per-role corpora. Use for search design, index optimization, the RAG retrieval layer, or deciding where ACL filtering belongs in the query path.
中文简介正在准备中。当前显示原文说明。
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starters, revision activities, or low-stakes testing materials.
中文简介正在准备中。当前显示原文说明。
Classify the information-need of a query and dispatch it to the appropriate retrieval or reasoning strategy. Use before read-side memory access, before multi-strategy retrieval, or any time you'd otherwise default to "one retriever for everything". Returns a strategy label, a token budget, and a retrieval depth so downstream handlers can be specialised. Backed by Pre-Route (arxiv 2605.10235v2) and MemFlow (arxiv 2605.03312v1), which together show LLMs possess latent routing ability elicitable via a structured prompt — and that externalising the routing decision improves small-model performance by ~2x. Triggers: "route this", "what strategy", "before retrieving", "intent classification", or any query whose ideal handling depends on what KIND of question it is.
中文简介正在准备中。当前显示原文说明。
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).
中文简介正在准备中。当前显示原文说明。
Self-Retrieval generates relevant passage $p$ using the knowledge embedded within its parameters, which is different from dense retrieval or generativ
中文简介正在准备中。当前显示原文说明。
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
中文简介正在准备中。当前显示原文说明。
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
中文简介正在准备中。当前显示原文说明。
Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.
中文简介正在准备中。当前显示原文说明。
Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).
中文简介正在准备中。当前显示原文说明。
使用DSPy构建问答、文档检索等AI流程，定义输入输出并组合可复用组件。利用训练示例和评估指标自动调整提示词，比较调整前后的输出结果。
使用Pinecone构建按内容含义查找信息的搜索基础设施，支持数据写入、更新与删除、条件筛选，以及语义搜索与关键词搜索的组合。
Generate music through Venice.ai, handling queued requests, completion, and result retrieval. Use it to create short jingles, repeating background music, or provisional scores for prototypes as part of an agent-assisted music workflow.
中文简介正在准备中。当前显示英语简介。
Find stored Ruflo memories by meaning, keywords, or an optional ranking method. Search across storage groups, retrieve past solutions and task context, and see which search method actually ran, including any fallback.
中文简介正在准备中。当前显示英语简介。
Prepare market history for pattern detection and comparison. Import opening, high, low, and closing prices plus volume, validate and normalize the values, then store them by symbol and date for later retrieval. It does not place orders.
中文简介正在准备中。当前显示英语简介。
Extract information from a project or conversation and store it as memories in MemPalace for later retrieval. The skill follows the step-by-step mining instructions returned by the MemPalace command.
中文简介正在准备中。当前显示英语简介。
Design and improve retrieval for RAG, which supplies external knowledge to AI answers. Cover document splitting, semantic and keyword search, combined result ranking, and quality measurements to identify where relevant information is being missed.
中文简介正在准备中。当前显示英语简介。
Build vector search that considers both semantic similarity and patterns in how items connect. Use graph features to explore structure in embeddings, numerical representations of content, and compare retrieval results with conventional similarity search.
中文简介正在准备中。当前显示英语简介。
Plan AI application development by selecting relevant phases and companion skills. The workflow covers language model integration, retrieval from documents, agents, machine learning pipelines, monitoring, and security, with prompts and quality checklists.
中文简介正在准备中。当前显示英语简介。
Plan AI application work across six areas: prompt evaluation, context allocation, retrieval-based answer generation, agent security, evaluation pipelines, and product strategy. This overview explains the approaches; the individual workflow packages, test cases, and CI templates are not included.
中文简介正在准备中。当前显示英语简介。