Load ONNX data in Python using dltHub

Build a ONNX-to-database or-dataframe pipeline in Python using dlt with automatic Cursor support.

In this guide, we'll set up a complete ONNX Runtime data pipeline from API credentials to your first data load in just 10 minutes. You'll end up with a fully declarative Python pipeline based on dlt's REST API connector, like in the partial example code below:

Example code
@dlt.source
def onnx_runtime_migrations_source(access_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://onnxruntime.ai/v1/",
            "auth": {
                "type": "bearer",
                "token": access_token,
            },
        },
        "resources": [
            A, B, Y
            ],
    }
    [...]
    yield from rest_api_resources(config)


def get_data() -> None:
    # Connect to destination
    pipeline = dlt.pipeline(
        pipeline_name='onnx_runtime_migrations_pipeline',
        destination='duckdb',
        dataset_name='onnx_runtime_migrations_data', 
    )
    # Load the data
    load_info = pipeline.run(onnx_runtime_migrations_source())
    print(load_info)

Why use dltHub Workspace with LLM Context to generate Python pipelines?

  • Accelerate pipeline development with AI-native context
  • Debug pipelines, validate schemas and data with the integrated Pipeline Dashboard
  • Build Python notebooks for end users of your data
  • Low maintenance thanks to Schema evolution with type inference, resilience and self documenting REST API connectors. A shallow learning curve makes the pipeline easy to extend by any team member
  • dlt is the tool of choice for Pythonic Iceberg Lakehouses, bringing mature data loading to pythonic Iceberg with or without catalogs

What you’ll do

We’ll show you how to generate a readable and easily maintainable Python script that fetches data from onnx_runtime_migrations’s API and loads it into Iceberg, DataFrames, files, or a database of your choice. Here are some of the endpoints you can load:

  • A: Retrieves information related to a specific operation.
  • B: Provides access to various models.
  • Y: Retrieves details about the opsets available.
  • X: Enables adding a new model to the runtime.
  • Conv: Implements the convolution operation with specified parameters.

You will then debug the ONNX Runtime pipeline using our Pipeline Dashboard tool to ensure it is copying the data correctly, before building a Notebook to explore your data and build reports.

Setup & steps to follow

💡
Before getting started, let's make sure Cursor is set up correctly:

Now you're ready to get started!

  1. ⚙️ Set up dlt Workspace

    Install dlt with duckdb support:

    pip install "dlt[workspace]"

    Initialize a dlt pipeline with ONNX Runtime support.

    dlt init dlthub:onnx_runtime_migrations duckdb

    The init command will setup the necessary files and folders for the next step.

  2. 🤠 Start LLM-assisted coding

    Here’s a prompt to get you started:

    Prompt
    Please generate a REST API Source for ONNX Runtime API, as specified in @onnx_runtime_migrations-docs.yaml 
Start with endpoints A and  and skip incremental loading for now. 
Place the code in onnx_runtime_migrations_pipeline.py and name the pipeline onnx_runtime_migrations_pipeline. 
If the file exists, use it as a starting point. 
Do not add or modify any other files. 
Use @dlt rest api as a tutorial. 
After adding the endpoints, allow the user to run the pipeline with python onnx_runtime_migrations_pipeline.py and await further instructions.

  3. 🔒 Set up credentials

    The source uses API key-based authentication, requiring the user to supply an API key for access.

    To get the appropriate API keys, please visit the original source at https://www.onnxruntime.ai/. If you want to protect your environment secrets in a production environment, look into setting up credentials with dlt.

  4. 🏃‍♀️ Run the pipeline in the Python terminal in Cursor

    python onnx_runtime_migrations_pipeline.py

    If your pipeline runs correctly, you’ll see something like the following:

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

  5. 📈 Debug your pipeline and data with the Pipeline Dashboard

    Now that you have a running pipeline, you need to make sure it’s correct, so you do not introduce silent failures like misconfigured pagination or incremental loading errors. By launching the dlt Workspace Pipeline Dashboard, you can see various information about the pipeline to enable you to test it. Here you can see:

    • Pipeline overview: State, load metrics
    • Data’s schema: tables, columns, types, hints
    • You can query the data itself
    dlt pipeline onnx_runtime_migrations_pipeline show

  6. 🐍 Build a Notebook with data explorations and reports

    With the pipeline and data partially validated, you can continue with custom data explorations and reports. To get started, paste the snippet below into a new marimo Notebook and ask your LLM to go from there. Jupyter Notebooks and regular Python scripts are supported as well.

    import dlt

data = dlt.pipeline("onnx_runtime_migrations_pipeline").dataset()
# get  table as Pandas frame
data..df().head()

Running into errors?

Users should be aware of several limitations, including a model size limit of 2 GB, and potential issues with unsupported operations if the operation is not included in the ONNX opset. Additionally, users might encounter errors due to invalid input shapes or unauthorized access if the token is expired or the OAuth scopes are incorrect.

Extra resources:

Next steps