rerank-service
文档重排序服务(Reranker)。基于深度学习模型对检索候选结果进行细粒度相关性打分与重新排序,显著提升检索结果的精准度(Top-K 准确率)。
Découvrez les skills DevOps, comparez leurs dépôts et consultez leurs instructions.
文档重排序服务(Reranker)。基于深度学习模型对检索候选结果进行细粒度相关性打分与重新排序,显著提升检索结果的精准度(Top-K 准确率)。
高精度光学字符识别(OCR)服务。支持多语言、多格式图像的文字检测与提取,并提供文本区域坐标与置信度评分,适用于文档数字化与图像内容分析。
安全隔离的 Docker 沙盒代码执行服务。支持 Python/Shell/Bash 多语言动态执行,内置超时与资源限制。提供信任模式用于服务间代码融合调用。
基于 SearXNG 与 VLM 的实时联网搜索服务。专用于获取最新新闻、实时事件及特定事实。内置智能双层缓存(向量+数据库)与网页内容自动提取分析功能。
高性能 RAG 多路检索服务。集成 Milvus 向量数据库进行语义检索,并结合 Rerank 模型进行精准重排序,支持海量文档的高效存储与历史内容召回。
This skill should be used when the user asks to "run TabularEditor.exe", "deploy a model via CLI", "use Tabular Editor command line", "set up CI/CD for Power BI", "automate model deployment", "run BPA from comm...
This skill should be used when the user asks about ".tmuo files", "Tabular Editor user options", "TE3 preferences", "Preferences.json", "UiPreferences.json", "Layouts.json", "workspace database settings", "depl...
This skill should be used when the user asks to "create a BPA rule", "write a Best Practice Analyzer rule", "improve a BPA expression", "fix expression for BPA", "analyze BPA annotations", "check model for best...
This skill should be used when the user asks about "Tabular Editor documentation", "TE docs", "how to do X in Tabular Editor", "Tabular Editor features", "TE3 features", "C# scripts in Tabular Editor", "DAX scr...
This skill should be used when the user asks to "write a C# script", "create a Tabular Editor script", "automate model changes", "bulk update measures", "create calculation groups", "format DAX expressions", "m...
This skill should be used when the user asks to "create a macro", "write a Tabular Editor macro", "save a script as macro", "edit MacroActions.json", "automate TE3 actions", or mentions Tabular Editor C# macros...
Motion-based animation system for Next.js with performance-optimized patterns
Use when getting started with llmemory document storage and search - covers installation, initialization, adding documents, vector search, hybrid search, semantic search, BM25 full-text search, document managem...
Use when building search systems that need both semantic similarity and keyword matching - covers combining vector and BM25 search with Reciprocal Rank Fusion, alpha tuning for search weight control, and optimi...
Use when building SaaS applications needing data isolation between customers - implements owner-based filtering for secure multi-tenant document storage and search with workspace, organization, or tenant-level...
Use when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and fuses results using RRF for improved retrieval quality especially with ambiguous...
Use when building Retrieval-Augmented Generation systems - covers document ingestion, hybrid search retrieval, reranking results, and prompt augmentation for accurate LLM responses grounded in your knowledge ba...
This skill provides a comprehensive approach for building astrology-specific backend systems with AI integration. Use when implementing vedic astrology features including kundli generation, dasha analysis, dosh...
This skill provides a migration guide for react native from 0.79.x to latest 0.83.x version.
Comprehensive guide for building production-grade AI-integrated backends with multi-provider support, intelligent fallback mechanisms, region configuration, prompt management with variables/tools, and session-b...
ZSH completion system patterns and conventions. Use when implementing custom completion handling, writing completion files, or working with zsh autocomplete. Do not use when installing packages from homebrew, s...
TypeScript functional programming. Use for pure functions, immutability, composition. Favors ternaries, switch, map/filter/reduce over imperative code. Concise, declarative patterns.
SvelteKit remote functions guidance. Use for command(), query(), form() patterns in .remote.ts files.
SvelteKit data flow guidance. Use for load functions, form actions, and server/client data. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error().
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.