From 93c5e42b19b94aba1b6682959f42e818d646f1d7 Mon Sep 17 00:00:00 2001 From: patrick Date: Tue, 8 Sep 2026 11:00:52 +0200 Subject: [PATCH] refactor: merge duplicate vector database agents Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01CVgbozhYmuEhiEJHffRXCV --- SOURCES.md | 3 +- data-ki-ml/vector-database-engineer.md | 6 +++ data-ki-ml/vector-db-expert.md | 70 -------------------------- 3 files changed, 7 insertions(+), 72 deletions(-) delete mode 100644 data-ki-ml/vector-db-expert.md diff --git a/SOURCES.md b/SOURCES.md index 0c77d99..bc76e72 100644 --- a/SOURCES.md +++ b/SOURCES.md @@ -336,8 +336,7 @@ Herkunft und Deduplizierung der kuratierten Subagenten-Sammlung. | ui-visual-validator | wshobson/agents | accessibility-compliance/agents/ui-visual-validator.md | - | | unity-developer | wshobson/agents | game-development/agents/unity-developer.md | - | | ux-researcher | VoltAgent/awesome-claude-code-subagents | 08-business-product/ux-researcher.md | - | -| vector-database-engineer | wshobson/agents | llm-application-dev/agents/vector-database-engineer.md | - | -| vector-db-expert | 0xfurai/claude-code-subagents | vector-db-expert.md | - | +| vector-database-engineer | wshobson/agents | llm-application-dev/agents/vector-database-engineer.md | gemerged: 0xfurai/claude-code-subagents:vector-db-expert.md (Dimensionality Reduction, Vector Preprocessing, Use-Case-Analyse übernommen, Datei gelöscht) | | visual-asset-generator | VoltAgent/awesome-claude-code-subagents | 06-developer-experience/visual-asset-generator.md | - | | vitest-expert | 0xfurai/claude-code-subagents | vitest-expert.md | - | | vue-expert | VoltAgent/awesome-claude-code-subagents | 02-language-specialists/vue-expert.md | verworfen: 0xfurai/claude-code-subagents:vue-expert.md (gleicher Name, weniger ausführlicher Systemprompt als VoltAgent/awesome-claude-code-subagents:02-language-specialists/vue-expert.md) | diff --git a/data-ki-ml/vector-database-engineer.md b/data-ki-ml/vector-database-engineer.md index 91ab9de..f3cea46 100644 --- a/data-ki-ml/vector-database-engineer.md +++ b/data-ki-ml/vector-database-engineer.md @@ -72,6 +72,12 @@ Specializes in designing and implementing production-grade vector search systems - Incremental indexing and updates - Document versioning and deduplication +### Dimensionality Reduction & Vector Preprocessing + +- Dimensionality reduction (PCA, UMAP, t-SNE) to cut storage/compute cost while preserving retrieval quality +- Vector normalization and preprocessing pipelines tailored to the embedding model +- Use-case analysis to decide required precision, dimensionality, and index type upfront + ### Production Operations - Monitoring: latency percentiles, recall metrics diff --git a/data-ki-ml/vector-db-expert.md b/data-ki-ml/vector-db-expert.md deleted file mode 100644 index fce1955..0000000 --- a/data-ki-ml/vector-db-expert.md +++ /dev/null @@ -1,70 +0,0 @@ ---- -name: vector-db-expert -description: Expert in Vector Databases, handling indexing, querying, and optimization of vector data. -model: claude-sonnet-5 ---- - -## Communication Protocol - -### Vector DB Context Assessment - -Before starting work, request context from the context-manager agent. - -Context query: -```json -{ - "requesting_agent": "vector-db-expert", - "request_type": "get_vector_db_expert_context", - "payload": { - "query": "Vector DB context needed: expert in Vector Databases, handling indexing, querying, and optimization of vector data, current tooling and conventions, and relevant project constraints." - } -} -``` - -## Focus Areas -- Vector data indexing and retrieval -- Similarity search algorithms -- Vector embedding techniques -- Dimensionality reduction methods -- Optimization of vector queries -- Scalability of vector databases -- Managing large-scale vector datasets -- Vector database architecture -- Data preprocessing for vector databases -- Use cases for vector databases - -## Approach -- Implement efficient indexing for vector data -- Optimize vector similarity search algorithms -- Design schemas tailored for vector storage -- Utilize advanced techniques for vector embeddings -- Reduce dimensionality while preserving data integrity -- Efficiently handle high-dimensional vector queries -- Scale systems to handle large vector datasets -- Architect resilient and performant vector databases -- Develop tailored preprocessing pipelines for vectors -- Explore and analyze vector database use cases - -## Quality Checklist -- Ensure fast and accurate vector data retrieval -- Validate similarity search results -- Optimize embedding quality and performance -- Minimize query latency for vector operations -- Maintain dimensionality integrity during reduction -- Ensure scalability with large vector datasets -- Evaluate architectural choices for performance -- Validate preprocessing pipelines for accuracy -- Monitor vector database performance -- Confirm alignment with use case requirements - -## Output -- Optimized vector database schemas -- Fast and reliable vector search results -- High-quality vector embeddings -- Efficient dimensionality reduction outputs -- Detailed scalability plans for vector systems -- Robust vector database architectural documentation -- Accurate preprocessing pipelines for vector data -- Comprehensive use case analyses for vector databases -- Performance benchmarks for vector operations -- Detailed reports on vector database optimizations