Milvus Python API Docs | dltHub

Milvus provides a RESTful API to manage collections, vectors, and database operations in a Milvus instance. The REST API base URL is http://localhost:19530 and all requests require a Bearer token if authentication is enabled in the Milvus instance.

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv add "dlt[hub]" and start loading Milvus data in under 10 minutes.

---

What data can I load from Milvus?

Here are some of the endpoints you can load from Milvus:

---

How do I authenticate with the Milvus API?

Authentication is performed by including an Authorization header with a Bearer token. The token must be a string containing the username and password concatenated with a colon (e.g., 'username

').

1. Get your credentials

To obtain an API key for Zilliz Cloud (managed Milvus), log in to your Zilliz Cloud console. Navigate to the API Keys section in the sidebar or top navigation bar. Click the '+ API Key' button (or 'Create API Key'), assign a name to the key, configure the required access privileges (e.g., Project Read-Write), and save the generated token securely as it will not be displayed again. For self-hosted Milvus instances, authentication is typically performed via 'username

' (default 'root') passed as a token, rather than a generated dashboard API key.

2. Add them to .dlt/secrets.toml

Copy
[sources.milvus_source]
milvus_uri = "https://your-cluster-endpoint.com"
milvus_token = "your_api_key_or_username:password"

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv init
uv add "dlt[hub]"

1. Install the dlt AI harness:

Copy
uv run dlthub ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
uv run dlthub ai toolkit install rest-api-pipeline

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Milvus API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
uv run python milvus_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline milvus_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset milvus_data
The duckdb destination used duckdb:/milvus.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
uv run dlthub show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads /v1/vector and /v2/vectordb from the Milvus API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def milvus_source(token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "http://localhost:19530",
            "auth": {"type": "bearer", "token": token},
        },
        "resources": [
            {"name": "collections", "endpoint": {"path": "v2/vectordb/collections/list", "data_selector": "data"}},
            {"name": "search", "endpoint": {"path": "v2/vectordb/entities/search"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="milvus_pipeline",
        destination="duckdb",
        dataset_name="milvus_data",
    )
    load_info = pipeline.run(milvus_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("milvus_pipeline").dataset()
sessions_df = data.collections.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM milvus_data.collections LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("milvus_pipeline").dataset()
data.collections.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Milvus data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI harness:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-platform — Deploy, schedule, and monitor your pipeline in production.

Copy
uv run dlthub ai toolkit install data-exploration
uv run dlthub ai toolkit install dlthub-platform

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack