Volcengine Ai Search Rag

该 Skill 给出在 Volcengine AI 栈上实现检索优先问答的流程：先确认语料来源与分块策略，再生成向量并建立或更新索引，随后按过滤条件做 top-k 检索，最后基于检索片段生成带引用的回答。质量规则要求检索提示与生成提示分离、保留来源与时间戳等分块元数据，并在无命中时返回置信度与回退路径。

cinience

热度 80.22

最近更新 2026-05-11 16:23:40

分类：知识依赖：第三方 API / 内部调用大模型应用场景：研究 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add volcengine-ai-search-rag

Metadata

name: volcengine-ai-search-rag
description: Retrieval and RAG workflow on Volcengine AI stack. Use when users need embedding search, document indexing, top-k retrieval, grounding prompts, or search relevance tuning.

volcengine-ai-search-rag

Implement retrieval-first answering with explicit indexing, retrieval, and grounding stages.

Execution Checklist

Confirm corpus source and chunking strategy.
Generate embeddings and build/update index.
Retrieve top-k context with filters.
Build grounded answer with citations to retrieved chunks.

Quality Rules

Separate retrieval prompt from generation prompt.
Keep chunk metadata (source, timestamp, id).
Return confidence and fallback path if no hits.

References

references/sources.md