Skip to main content
  1. Sign up — Create an account at platform.respan.ai
  2. Create an API key — Generate one on the API keys page
  3. Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page
Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.
{
  "mcpServers": {
    "respan-docs": {
      "url": "https://docs.respan.ai/mcp"
    }
  }
}

​
What is Milvus?

Milvus is an open-source vector database built for scalable similarity search and AI applications. Respan auto-instruments Milvus operations so every insert, search, and collection operation is captured as a traced span.

​
Setup

1

Install packages

pip install respan-ai opentelemetry-instrumentation-milvus pymilvus python-dotenv
2

Set environment variables

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
export MILVUS_URI="YOUR_MILVUS_URI"
3

Initialize and run

import os
from dotenv import load_dotenv

load_dotenv()

from pymilvus import MilvusClient
from respan import Respan

# Initialize Respan with auto-instrumentation
respan = Respan(is_auto_instrument=True)

# Create a Milvus client
client = MilvusClient(uri=os.getenv("MILVUS_URI", "http://localhost:19530"))

# Create a collection
client.create_collection(
    collection_name="respan_demo",
    dimension=1536,
)

# Insert vectors
client.insert(
    collection_name="respan_demo",
    data=[
        {"id": 1, "vector": [0.1] * 1536, "genre": "drama"},
        {"id": 2, "vector": [0.2] * 1536, "genre": "comedy"},
    ],
)

# Search
results = client.search(
    collection_name="respan_demo",
    data=[[0.1] * 1536],
    limit=3,
    output_fields=["genre"],
)
print(results)

respan.flush()
4

View your trace

Open the Traces page to see your Milvus spans including collection creation, insert, and search operations.

​
Configuration

ParameterTypeDefaultDescription
api_keystr | NoneNoneFalls back to RESPAN_API_KEY env var.
base_urlstr | NoneNoneFalls back to RESPAN_BASE_URL env var.
is_auto_instrumentbool | NoneFalseAuto-discover installed instrumentors. Required for Traceloop instrumentors.
customer_identifierstr | NoneNoneDefault customer identifier for all spans.
metadatadict | NoneNoneDefault metadata attached to all spans.
environmentstr | NoneNoneEnvironment tag (e.g. "production").

​
Attributes

Attach customer identifiers, thread IDs, and metadata to spans.

​
In Respan()

Set defaults at initialization — these apply to all spans. 
from respan import Respan

respan = Respan(
    is_auto_instrument=True,
    customer_identifier="user_123",
    metadata={"service": "search-api", "version": "1.0.0"},
)

​
With propagate_attributes

Override per-request using a context manager. 
from respan import Respan, propagate_attributes

respan = Respan(is_auto_instrument=True)

with propagate_attributes(
    customer_identifier="user_456",
    thread_identifier="session_abc",
    metadata={"plan": "enterprise"},
):
    results = client.search(
        collection_name="respan_demo",
        data=[[0.1] * 1536],
        limit=5,
        output_fields=["genre"],
    )
    print(results)
AttributeTypeDescription
customer_identifierstrIdentifies the end user in Respan analytics.
thread_identifierstrGroups related messages into a conversation.
metadatadictCustom key-value pairs. Merged with default metadata.

​
Examples

​
Create collection

from pymilvus import MilvusClient

client = MilvusClient(uri="http://localhost:19530")

client.create_collection(
    collection_name="product_embeddings",
    dimension=1536,
)

​
Insert vectors

client.insert(
    collection_name="product_embeddings",
    data=[
        {
            "id": 1,
            "vector": [0.12, 0.34, 0.56] + [0.0] * 1533,
            "category": "electronics",
            "price": 299.99,
        },
        {
            "id": 2,
            "vector": [0.78, 0.91, 0.23] + [0.0] * 1533,
            "category": "clothing",
            "price": 49.99,
        },
    ],
)

results = client.search(
    collection_name="product_embeddings",
    data=[[0.12, 0.34, 0.56] + [0.0] * 1533],
    limit=5,
    output_fields=["category", "price"],
    filter='category == "electronics"',
)

for hits in results:
    for hit in hits:
        print(f"id={hit['id']}, distance={hit['distance']:.4f}, entity={hit['entity']}")

​
Delete

# Delete by IDs
client.delete(
    collection_name="product_embeddings",
    ids=[1, 2],
)

# Delete by filter
client.delete(
    collection_name="product_embeddings",
    filter='category == "electronics"',
)