Load GMI Cloud Inference Engine data in Python using dltHub

Build a GMI Cloud Inference Engine-to-database or-dataframe pipeline in Python using dlt with automatic Cursor support.

In this guide, we'll set up a complete GMI Serving 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 gmi_cloud_inference_engine_source(access_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.gmi-serving.com/v1/",
            "auth": {
                "type": "bearer",
                "token": access_token,
            },
        },
        "resources": [
            chat/completions,
            models,
            inference-engine/resources/artifacts
            ],
    }
    [...]
    yield from rest_api_resources(config)


def get_data() -> None:
    # Connect to destination
    pipeline = dlt.pipeline(
        pipeline_name='gmi_cloud_inference_engine_pipeline',
        destination='duckdb',
        dataset_name='gmi_cloud_inference_engine_data', 
    )
    # Load the data
    load_info = pipeline.run(gmi_cloud_inference_engine_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 gmi_cloud_inference_engine’s API and loads it into Iceberg, DataFrames, files, or a database of your choice. Here are some of the endpoints you can load:

  • Request Queue: Handles requests for processing and managing tasks.
  • Models: Interacts with models available for use in requests.
  • Completions: Facilitates chat completions using the inference engine.
  • Resources: Accesses artifacts and tasks related to the inference engine.

You will then debug the GMI Serving 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 GMI Serving support.

    dlt init dlthub:gmi_cloud_inference_engine 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 GMI Serving API, as specified in @gmi_cloud_inference_engine-docs.yaml 
Start with endpoints chat/completions and models and skip incremental loading for now. 
Place the code in gmi_cloud_inference_engine_pipeline.py and name the pipeline gmi_cloud_inference_engine_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 gmi_cloud_inference_engine_pipeline.py and await further instructions.

  3. 🔒 Set up credentials

    API keys should be provided via HTTP Bearer authentication, and they must be included in the headers. The header name for the authorization is 'Authorization'.

    To get the appropriate API keys, please visit the original source at https://www.gmi-serving.com/. 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 gmi_cloud_inference_engine_pipeline.py

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

    Pipeline gmi_cloud_inference_engine load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset gmi_cloud_inference_engine_data
The duckdb destination used duckdb:/gmi_cloud_inference_engine.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 gmi_cloud_inference_engine_pipeline show --dashboard

  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("gmi_cloud_inference_engine_pipeline").dataset()
# get hat/completion table as Pandas frame
data.hat/completion.df().head()

Running into errors?

It's crucial to never expose API keys in client-side code. Be aware that the processing time for video generation requests varies significantly based on the model and video length. Additionally, API rate limits are enforced at the organization level and can differ based on the tier and model being used.

Extra resources:

Next steps