​
Prerequisites

Install dependencies: 
pip install "quotientai>=0.4.6" "qdrant-client" "openinference-instrumentation-qdrant>=0.1.6"

​
Sample Integration

trace_qdrant.py
from openinference.instrumentation.qdrant import QdrantInstrumentor
from qdrant_client import QdrantClient

from quotientai import QuotientAI

quotient = QuotientAI()
quotient.tracer.init(
    app_name="qdrant-retrieval",
    environment="dev",
    instruments=[QdrantInstrumentor()],
)

client = QdrantClient(host="localhost", port=6333)
client.create_collection(collection_name="support", vector_size=3, distance="Cosine")
client.upsert(collection_name="support", points=[
    {
        "id": 1,
        "vector": [0.1, 0.2, 0.3],
        "payload": {"title": "Reset password"},
    }
])
response = client.search(collection_name="support", query_vector=[0.2, 0.1, 0.3], limit=2)
print(response)

​
Notes

  • Spans surface collection dimensions, filters, and limits so you can diagnose retrieval performance.
  • Instrumentation degrades gracefully—if the Qdrant client is missing, the instrumentor simply logs a warning.
Back: Vector Database Integrations