How to Use a Vector Database for Real Estate

# Python example - Build a Real Estate Vector Database with ChromaDB
import chromadb
from openai import OpenAI
import os

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
chroma_client = chromadb.Client()
collection = chroma_client.create_collection(name="nashville_listings")

# Sample listing profiles
listings = [
    {
        "id": "listing_001",
        "text": "4BR/3BA colonial in Franklin. 3,200 sqft on a quiet half-acre. Renovated kitchen with marble counters. In-ground pool. Walking distance to downtown Franklin shops and restaurants. Established neighborhood with mature trees.",
        "metadata": {"price": 620000, "beds": 4, "baths": 3, "sqft": 3200, "neighborhood": "Franklin"}
    },
    {
        "id": "listing_002",
        "text": "2BR/2BA modern loft in Germantown. 1,100 sqft with 14-foot ceilings and exposed brick. Rooftop terrace access. Walk to restaurants, coffee shops, and the Farmers Market. Open concept living with industrial character.",
        "metadata": {"price": 385000, "beds": 2, "baths": 2, "sqft": 1100, "neighborhood": "Germantown"}
    }
]

# Generate embeddings and store
for listing in listings:
    embedding = client.embeddings.create(
        model="text-embedding-3-small",
        input=listing["text"]
    ).data[0].embedding
    
    collection.add(
        ids=[listing["id"]],
        embeddings=[embedding],
        documents=[listing["text"]],
        metadatas=[listing["metadata"]]
    )

# Semantic search
query = "walkable neighborhood with restaurants, modern feel, space for entertaining"
query_embedding = client.embeddings.create(
    model="text-embedding-3-small", input=query
).data[0].embedding

results = collection.query(
    query_embeddings=[query_embedding],
    n_results=2
)

print(results["documents"])