> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/docs/_mcp/server.

# Milvus (tracing)

> Trace Milvus vector search operations with Respan — auto-instrumented spans and full observability.

[Milvus](https://milvus.io/) is an open-source vector database built for scalable similarity search. It supports billion-scale vector data, multiple index types (IVF, HNSW, DiskANN), and hybrid search combining vector similarity with scalar filtering. Respan gives you full observability over every collection operation, search, and insert.

#### Set up Respan

Create an account at [platform.respan.ai](https://platform.respan.ai) and grab an [API key](https://platform.respan.ai/platform/gateway/api-keys).

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

#### Example projects

* [Python examples](https://github.com/respanai/respan-example-projects/tree/main/python/tracing/milvus)

#### Tracing

## Setup

#### Install packages

```bash
pip install respan-ai opentelemetry-instrumentation-milvus pymilvus
```

#### Set environment variables

```bash
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
```

`RESPAN_API_KEY` is used to export traces to Respan.

#### Initialize and run

```python
from pymilvus import MilvusClient
from respan import Respan
from opentelemetry.instrumentation.milvus import MilvusInstrumentor

respan = Respan(instrumentations=[MilvusInstrumentor()])

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

client.create_collection(collection_name="documents", dimension=4)

data = [
    {"id": 1, "vector": [0.1, 0.2, 0.3, 0.4], "text": "AI observability with Respan"},
    {"id": 2, "vector": [0.5, 0.6, 0.7, 0.8], "text": "Vector similarity search"},
    {"id": 3, "vector": [0.2, 0.3, 0.4, 0.5], "text": "Scalable vector indexing"},
]
client.insert(collection_name="documents", data=data)

results = client.search(
    collection_name="documents",
    data=[[0.1, 0.2, 0.3, 0.4]],
    limit=2,
    output_fields=["text"],
)
for hits in results:
    for hit in hits:
        print(f"{hit['entity']['text']} (distance: {hit['distance']:.4f})")

```

#### View your trace

Open the [Traces page](https://platform.respan.ai/platform/traces) to see your Milvus 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. `MilvusInstrumentor()`). |
| `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()

```python
from respan import Respan
from opentelemetry.instrumentation.milvus import MilvusInstrumentor

respan = Respan(
    instrumentations=[MilvusInstrumentor()],
    customer_identifier="user_123",
    metadata={"service": "vector-api", "version": "1.0.0"},
)
```

### With propagate_attributes

```python
from respan import Respan, propagate_attributes
from opentelemetry.instrumentation.milvus import MilvusInstrumentor

respan = Respan(instrumentations=[MilvusInstrumentor()])

def search(user_id: str, query_vector):
    with propagate_attributes(
        customer_identifier=user_id,
        thread_identifier="conv_abc_123",
        metadata={"plan": "pro"},
    ):
        return client.search(collection_name="documents", data=[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. |