Agent Skills
› rmyndharis/antigravity-skills
› vector-database-engineer
vector-database-engineer
GitHub专注于向量数据库工程师技能，涵盖Pinecone、Qdrant等工具及RAG、语义搜索实现。提供嵌入优化、索引配置、混合搜索及性能调优方案，适用于推荐系统和相似度检索场景。
触发场景
构建RAG系统
实现文档语义搜索
向量数据库选型与架构设计
嵌入模型优化
推荐引擎开发
安装
npx skills add rmyndharis/antigravity-skills --skill vector-database-engineer -g -y
SKILL.md
Frontmatter
{
"name": "vector-database-engineer",
"description": "Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar"
}
Vector Database Engineer
Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search. Use PROACTIVELY for vector search implementation, embedding optimization, or semantic retrieval systems.
Do not use this skill when
- The task is unrelated to vector database engineer
- You need a different domain or tool outside this scope
Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
Capabilities
- Vector database selection and architecture
- Embedding model selection and optimization
- Index configuration (HNSW, IVF, PQ)
- Hybrid search (vector + keyword) implementation
- Chunking strategies for documents
- Metadata filtering and pre/post-filtering
- Performance tuning and scaling
Use this skill when
- Building RAG (Retrieval Augmented Generation) systems
- Implementing semantic search over documents
- Creating recommendation engines
- Building image/audio similarity search
- Optimizing vector search latency and recall
- Scaling vector operations to millions of vectors
Workflow
- Analyze data characteristics and query patterns
- Select appropriate embedding model
- Design chunking and preprocessing pipeline
- Choose vector database and index type
- Configure metadata schema for filtering
- Implement hybrid search if needed
- Optimize for latency/recall tradeoffs
- Set up monitoring and reindexing strategies
Best Practices
- Choose embedding dimensions based on use case (384-1536)
- Implement proper chunking with overlap
- Use metadata filtering to reduce search space
- Monitor embedding drift over time
- Plan for index rebuilding
- Cache frequent queries
- Test recall vs latency tradeoffs
版本历史
- e63f7dd 当前 2026-07-05 10:36
