optimizing-rag
Optimize RAG performance with reranking, caching, parallel processing, and production deployment patterns. Use when improving retrieval quality, adding rerankers, deploying to production, implementing caching s...
浏览 tkhongsap 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
10收录技能的仓库 Stars 合计
5仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Optimize RAG performance with reranking, caching, parallel processing, and production deployment patterns. Use when improving retrieval quality, adding rerankers, deploying to production, implementing caching s...
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visu...
Translate English content to Thai with cultural adaptation for idioms, formality levels (กระผม/ผม/ครับ/ค่ะ/นะ), honorifics, and context-appropriate register. Use when translating to Thai, adapting cultural refe...
Evaluate RAG systems with hit rate, MRR, faithfulness metrics and compare retrieval strategies. Use when testing retrieval quality, generating evaluation datasets, comparing embeddings or retrievers, A/B testin...
Set up RAG pipelines with document chunking, embedding generation, and retrieval strategies using LlamaIndex. Use when building new RAG systems, choosing chunking approaches, selecting embedding models, or impl...
Create new SciCode benchmark tasks from research papers. Use when authoring scientific coding problems, creating step files, writing problem.yaml, or setting up new benchmark tasks. Triggers on "create task", "...
Review and validate SciCode benchmark problems for quality and correctness. Use when checking problem quality, verifying test cases, reviewing decomposition, or preparing tasks for submission. Triggers on "revi...
Translate English content to Thai with cultural adaptation for idioms, formality levels (กระผม/ผม/ครับ/ค่ะ/นะ), honorifics, and context-appropriate register. Use when translating to Thai, adapting cultural refe...
Analyze story beginnings and write coherent continuations (approximately 200 words) that naturally incorporate randomly generated sentences. Use for story writing tasks, creative writing practice, bilingual sto...
Analyze and fix "ineffective" subproblems in SciCode benchmark. Classify issues as MAJOR or MINOR, apply minimal fixes to MAJOR issues. Use when "analyze subproblem", "classify issue", "fix benchmark problem",...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。