Qdrant | Respan Docs

Qdrant is an open-source vector similarity search engine with a focus on performance and developer experience. It provides advanced filtering, payload indexing, and support for multiple distance metrics with both on-disk and in-memory storage. Respan gives you full observability over every collection operation, upsert, and query.

Set up Respan

Create an account at platform.respan.ai and grab an API key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-qdrant qdrant-client

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from qdrant_client import QdrantClient, models
2 from respan import Respan
3 from opentelemetry.instrumentation.qdrant import QdrantInstrumentor
4 
5 respan = Respan(instrumentations=[QdrantInstrumentor()])
6 
7 client = QdrantClient(url="http://localhost:6333")
8 
9 client.create_collection(
10     collection_name="documents",
11     vectors_config=models.VectorParams(size=4, distance=models.Distance.COSINE),
12 )
13 
14 client.upsert(
15     collection_name="documents",
16     points=[
17         models.PointStruct(id=1, vector=[0.1, 0.2, 0.3, 0.4], payload={"topic": "observability"}),
18         models.PointStruct(id=2, vector=[0.5, 0.6, 0.7, 0.8], payload={"topic": "search"}),
19         models.PointStruct(id=3, vector=[0.2, 0.3, 0.4, 0.5], payload={"topic": "embeddings"}),
20     ],
21 )
22 
23 results = client.query_points(
24     collection_name="documents",
25     query=[0.1, 0.2, 0.3, 0.4],
26     limit=2,
27     with_payload=True,
28 )
29 for point in results.points:
30     print(f"ID: {point.id} (score: {point.score:.4f}) — {point.payload['topic']}")
31 
32 respan.flush()

View your trace

Open the Traces page to see your Qdrant operation spans.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `QdrantInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

1 from respan import Respan
2 from opentelemetry.instrumentation.qdrant import QdrantInstrumentor
3 
4 respan = Respan(
5     instrumentations=[QdrantInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "rag-api", "version": "1.0.0"},
8 )

With propagate_attributes

1 from respan import Respan, propagate_attributes
2 from opentelemetry.instrumentation.qdrant import QdrantInstrumentor
3 
4 respan = Respan(instrumentations=[QdrantInstrumentor()])
5 
6 def search(user_id: str, query_vector):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         return client.query_points(collection_name="documents", query=query_vector, limit=2)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.