All Scaffoldings

Load Helicone Gemini data in Python using dltHub

Build a Helicone Gemini-to-database pipeline in Python using dlt with AI Workbench support for Claude Code, Cursor, and Codex.

Last updated:

In this guide, we'll set up a complete Helicone 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 helicone_gemini_source(access_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://ai-gateway.helicone.ai/v3/",
            "auth": {
                "type": "bearer",
                "token": access_token,
            },
        },
        "resources": [
            "features/alerts", "features/reports", "features/sessions"
            ],
    }
    [...]
    yield from rest_api_resources(config)


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

Why use dlt 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 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 Helicone Gemini's API and loads it into Iceberg, DataFrames, files, or a database of your choice. Here are some of the endpoints you can load:

  • features: Contains endpoints for alerts, reports, and sessions.
  • chat: Endpoints for chat completions and interactions.
  • user_metrics: Access user-related metrics and analytics.

You will then debug the Helicone 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, set up a virtual environment (instructions) and install the dlt workspace:


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

Now you're ready to get started!

  1. Install the dlt AI Workbench

    Configure the workbench for your coding assistant:

    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 about the dltHub AI Workbench and setup details for each assistant →

  2. Install the rest-api-pipeline toolkit

    The AI Workbench provides different toolkits for each phase of the data engineering lifecycle. To start you need to install the rest-api-pipeline toolkit:

    dlt ai toolkit rest-api-pipeline install

    This loads different skills and contexts about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. Importantly, it does not need to ask you for credentials directly. In dlt, API credentials are provided via a secrets.toml file (learn more about secrets management →), and the agent should use the MCP tools to see their shape and detect misconfigurations. It never needs to access the file directly.

    Learn more about the rest-api-pipeline toolkit →

  3. Start LLM-assisted coding

    Here's a prompt to get you started:

    Prompt
    Use /find-source to load data from the Helicone Gemini API into DuckDB.

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

  4. View the result

    After the rest-api-pipeline workflow has finished, you will end up with a working REST API source with validated endpoints and a pipeline that writes data into a local dataset you have inspected and verified.

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

    By launching the Pipeline Dashboard, you can see various information about the pipeline and the loaded data

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

Running into errors?

Ensure the API key has write permissions, as all keys will have write access starting June 2024. Rate limits apply, and requests may be subject to delays for analytics aggregation. Make sure to monitor for 401 and 429 errors to handle authentication and rate limiting issues.

Next steps

Was this page helpful?

Community Hub

Need more dlt context for Helicone Gemini?

Request dlt skills, commands, AGENT.md files, and AI-native context.

Request more contextSubmit context