“RAG”

Retrieve relevant excerpts from a project's text files without loading entire files into context.

Local knowledge retrieval and indexing skill.

Use for RAG pipelines, retrieval augmented generation, ColBERTv2, context retrieval, multi-hop RAG, and grounded DSPy answers.

Build a local RAG index by splitting a document and embedding its chunks using the on-device engine (private/offline).

Design RAG pipelines: chunking, retrieval evaluation, and architecture.

Use when comparing basic, enhanced, GraphRAG, or agentic RAG designs, evaluating domain-specific RAG quality, tuning retrieval components, or deciding whether…

Use this skill when you need evidence-bounded grounding, relevance, completeness, citation support, abstention, and answer-level evidence in RAG outputs…

Query a RAG (Retrieval-Augmented Generation) knowledge base to find relevant information from ingested documents.

RAG (Retrieval-Augmented Generation) system for affidavit workflows.

Acts as the verification and grounding layer in Retrieval-Augmented Generation (RAG) pipelines.

Use when Codex needs to build or query a local RAG knowledge base for academic papers, literature matrices, public author guidelines, GB/T7714 rules, CSL…

Private knowledge base for indexing multimodal files or folders into a knowledge graph, supporting multi-hop graph retrieval

Query the local RAG knowledge base using a python script.

Use when | Pipeline para integrar documentos de OnlyOffice con el sistema RAG de KAI.

Use this skill for public-safe reasoning about RAG and LangChain pipelines, document loading, splitting, embedding, vector stores, retrievers, prompts…

Use when the user asks about internal/private knowledge, documents, policies, or any indexed corpus that should be answered from a knowledge base rather than…

Use this skill when you need evidence-bounded query variants, chunking, filters, recall/precision proxies, ranking, freshness, and retrieval evidence…

Audits whether website content has clear, bounded, retrieval-friendly structural units for AI retrieval and answer generation.

Retrieval-augmented literature search over local paper library.

检索多模态数据处理平台已完成工作流的最新处理结果。适用于网页爬取、文档解析、OCR、Markdown/JSON 转换等已写入数据集的结果问答，并返回可回溯的数据集版本与来源引用。

Use when a medical AI paper should be found and cited by AI search engines and RAG tools.

Test RAG vector stores (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) for embedding inversion, cross-tenant data leakage, and data poisoning per OWASP…

将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown，并输出元数据与解析置信度，作为 RAG 与四色卡片的数据底座。

Build, review, or harden AI agents, LLM apps, RAG, tool-calling, coding agents, and agentic workflows with secure-by-default controls.