Milvus Python API Docs | dltHub

Milvus is an open-source vector database for scalable similarity search and AI applications. The REST API base URL is http://localhost:19530 and optional token-based Bearer auth when authentication is enabled..

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 pip install "dlt[workspace]" 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?

By default Milvus REST endpoints do not require authentication. If authentication is enabled, include an Authorization header with a token formed by colon-joining username and password (username:password) and prefixed with Bearer, e.g. Authorization: Bearer root:milvus.

1. Get your credentials

1. Ensure Milvus authentication is enabled in your Milvus deployment. 2) Use a Milvus account username and password (e.g., root and its password). 3) Form the token by concatenating username and password with a colon: username:password. 4) Use that value as the bearer token in the Authorization header.

2. Add them to .dlt/secrets.toml

Copy
[sources.milvus_source]
authorization_token = "root:milvus"

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 venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt 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
dlt ai toolkit rest-api-pipeline install

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
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
dlt pipeline milvus_pipeline 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 collections and collections_describe 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(authorization_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "http://localhost:19530",
            "auth": {
                "type": "bearer",
                "authorization_token": authorization_token,
            },
        },
        "resources": [
            {"name": "collections", "endpoint": {"path": "v2/vectordb/collections/list", "data_selector": "data"}},
            {"name": "collections_describe", "endpoint": {"path": "v2/vectordb/collections/describe", "data_selector": "data"}}
        ],
    }
    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.

---

Troubleshooting

Authentication failures

If Milvus authentication is enabled and you omit or send an incorrect Authorization header the API returns an error (non-0 code) and an error message. Ensure Authorization: Bearer username:password is sent. For diagnose, check server auth settings and use correct user credentials.

Request structure and content-type

Milvus REST API expects JSON request bodies and Content-Type: application/json. Missing or invalid JSON bodies for endpoints such as /v2/vectordb/collections/list or /v2/vectordb/collections/describe can result in 4xx responses.

Versioning and endpoint differences

Milvus exposes v1 and v2 endpoints; v2 covers expanded functionality. Use the v2 endpoints when available. Some older operations (vector query) remain under v1 with different request/response shapes.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

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

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

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• 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