700건 · 관련도순
Calculate how to divide serving memory between recurrent state and KV cache, two memory pools used by hybrid models. Use startup logs and workload settings to recommend a ratio, estimate concurrency, and identify the limiting pool.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Design hybrid search on AlloyDB by combining meaning-based search, keywords, and SQL filters. Turn requirements into architecture diagrams, database setup scripts, deployment guidance, and validation plans for search applications on Google Cloud.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). **Trigger when user asks to:** - Combine keyword and semantic search - Implement hybrid search or multi-modal retrieval - Use BM25/pg_textsearch with pgvector together - Implement RRF (Reciprocal Rank Fusion) for search - Build search that handles both exact terms and meaning **Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder Covers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration strategies. Use PROACTIVELY for hybrid architecture, multi-cloud strategy, or complex infrastructure integration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration strategies. Use PROACTIVELY for hybrid architecture, multi-cloud strategy, or complex infrastructure integration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan and configure connections between on-premises data centers and AWS, Azure, GCP, or OCI using VPNs or dedicated links. Cover routing, redundant connections, security controls, monitoring, troubleshooting, and connection costs.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Configure SAML identity federation, a way to share authentication between systems, linking on-premises Active Directory with Microsoft Entra ID. Cover single sign-on for cloud applications, user attribute mapping, authentication model choices, and signing certificate management.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Assess Active Directory security by mapping accounts, permissions, and paths to administrative access. The skill covers credential misuse, certificate service misconfigurations, movement between systems, and hybrid identity environments involving Entra ID.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Expert blueprint for TPS/hybrid shooters: soft-lock aim assist, cover validation rays, SpringArm TPS camera, and genre routing to FPS sibling for viewmodel/hitscan feel. Use for third-person/cover shooters and hybrids. Keywords: TPS, soft_lock, cover, SpringArm3D, hybrid shooter, aim assist — not FPS-only movement.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert blueprint for TPS/hybrid shooters: soft-lock aim assist, cover validation rays, SpringArm TPS camera, and genre routing to FPS sibling for viewmodel/hitscan feel. Use for third-person/cover shooters and hybrids. Keywords: TPS, soft_lock, cover, SpringArm3D, hybrid shooter, aim assist — not FPS-only movement.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan, implement, or review hybrid search implementation work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests hybrid search implementation work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build hybrid search systems combining semantic and keyword. TRIGGERS - Use when user needs help with ai-hybrid-search related tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Discovers requirements and generates architectural, design, and deployment guidance for dynamic hybrid search systems by combining semantic search and keyword search. Optimized for AlloyDB hybrid search use cases in Google Cloud. Use when users need vector search combined with structured SQL filtering, faceted attributes, semantic reranking, in-database AI validation, or serverless hosting across transactional relational databases, analytical data warehouses, or managed database engines. DON'T use this skill for simple keyword-only search, or when a standalone non-relational vector database is required.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
This skill determines whether a patient using a hybrid closed-loop insulin pump can continue this therapy upon hospital admission. It is triggered by questions such as "Can hybrid closed-loop pump be continued given hospital constraints?"
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build hybrid search systems combining semantic and keyword. TRIGGERS - Use when user needs help with ai-hybrid-search related tasks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Complete guide for AutoFixture and Bogus integration. Use when you need to combine AutoFixture with Bogus to generate test data that is both anonymous and realistic. Covers SpecimenBuilder integration, hybrid generators, test data factories, and circular reference handling. Keywords: autofixture bogus integration, autofixture bogus, bogus integration, Faker, EmailSpecimenBuilder, PhoneSpecimenBuilder, NameSpecimenBuilder, realistic test data, semantic data, hybrid generator, HybridTestDataGenerator, OmitOnRecursionBehavior, circular reference
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build and optimize quantum circuits with PennyLane, including models that combine quantum circuits with PyTorch or JAX. Explore molecular energy estimation and optimization problems, validate values and gradients in simulation, and prepare tested circuits for provider plugins.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan and develop Android apps with guidance on technology choices, app structure, screen design, testing, debugging, performance, and releases. Covers native Kotlin and Java development alongside Flutter, RN, KMM, and hybrid approaches.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan and carry out an AngularJS to Angular migration, from choosing a rewrite strategy to converting components, services, and routes. Includes a hybrid approach that runs both frameworks together while individual features are migrated.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build search and recommendation features with Pinecone, a managed database for numerical representations of content. Covers data loading, combined meaning and keyword search, filtering by attributes, and separating data by user.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan AI workflows over Zoom data by deciding whether MCP, a way for AI clients to use tools, fits the task. Define REST API responsibilities, authentication constraints, and a minimal proof of concept.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build search and recommendation features with Pinecone, a managed database for numerical representations of content. Covers data loading, combined meaning and keyword search, filtering by attributes, and separating data by user.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.