Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →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.
Passed 11 of 22 test cases with the skill, and 9 of 22 without it.
3 fixed8 passed either way10 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
When indexing highly technical scientific and specialized construction material literature, which domain-adapted embedding model is recommended over general-purpose models like all-MiniLM-L6-v2 or all-mpnet-base-v2?
| Checked | Without skill | With skill |
|---|---|---|
| Selects model allenai/scibert_scivocab_uncased for specialized scientific literature. | Missed | Passed |
The instructions your model reads when the skill loads.
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
from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance, PointStruct
# Initialize embedding model
model = SentenceTransformer('all-MiniLM-L6-v2')
# Create Qdrant client (in-memory for demo)
client = QdrantClient(":memory:")
# Create collection
client.create_collection(
collection_name="construction_docs",
vectors_config=VectorParams(size=384, distance=Distance.COSINE)
)
# Sample construction documents
documents = [
"Concrete mix design for C30 grade with water-cement ratio 0.45",
"Steel reinforcement specifications for structural columns",
"Waterproofing membrane installation for basement walls",
"Fire-rated door specifications for escape routes"
]
# Index documents
for idx, doc in enumerate(documents):
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.