Agent skill · data analytics · datadrivenconstruction
vector-search
Implement semantic vector search for construction data. Build AI-powered search using embeddings and vector databases (Qdrant, ChromaDB) for intelligent querying of specifications, standards, and project documents.
Why this skill is useful
Adds executable scripts for semantic vector search using embeddings and Qdrant, which are not commonly found in public documentation.
What it needs
Requires python3 installed locally. Requires openai, qdrant account access. About 6k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
Vector Search for Construction Overview Based on DDC methodology (Chapter 4.4), this skill implements semantic vector search for construction data. Move beyond keyword matching - find documents and data by meaning, not just words. Book Reference: "Современные технологии работы с данными" / "Modern Data Technologies" "Векторные базы данных позволяют находить семантически похожие документы, даже если они используют разную терминологию." — DDC Book, Chapter 4.4 Quick Start Vector Database Setup Qdrant Setup ChromaDB Alternative Construction-Specific Applications Specification Search Standards and Codes Search Work Item Search (OpenConstructionEstimate) RAG for Construction Retrieval Augmented Generation Document Indexing Pipeline Quick Reference Component Description Use Case ----------- ------------- ---------- Qdrant High-performance vector DB Production deployments ChromaDB Simple embedded vector DB Development/testing SentenceTransformers Embedding models Text to vectors RAG Retrieval + Generation Q&A over documents Embedding Models for Construction Resources Book: "Data-Driven Construction" by Artem Boiko, Chapter 4.4 Website: https://datadrivenconstruction.io Qdrant: https://qdrant.tech ChromaDB: https://www.trychroma.com SentenceTransformers: https://www.sbert.net Next Steps See llm-data-automation for LLM integration See document-classification-nlp for document categorization See rag-construction for RAG applications
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/vector-search