Load Haystack Audio API data in Python using dltHub

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

In this guide, we'll set up a complete Cohere 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 haystack_audio_api_source(access_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.cohere.com/v1/",
            "auth": {
                "type": "apikey",
                "token": api_key,
            },
        },
        "resources": [
            run,,chat,,embed
            ],
    }
    [...]
    yield from rest_api_resources(config)


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

Run: Executes a specified task with input data.
Chat: Facilitates chat interactions.
Embed: Generates embeddings for given inputs.
Search: Allows searching through documents or data.
Rerank: Reranks a list of items based on a specified criterion.
Ranker: Provides ranking capabilities for specified inputs.
Caching: Manages cached data for efficiency.
Joiners: Combines multiple data sources or inputs.
Documents: Manages document-related operations.
Convert: Handles conversions between formats such as PDF to image.

You will then debug the Cohere 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:

We suggest using a model like Claude 3.7 Sonnet or better
Index the REST API Source tutorial: https://dlthub.com/docs/dlt-ecosystem/verified-sources/rest_api/ and add it to context as @dlt rest api
Read our full steps on setting up Cursor

Now you're ready to get started!

⚙️ Set up dlt Workspace

Install dlt with duckdb support:
```
pip install dlt[workspace]
```
Initialize a dlt pipeline with Cohere support.
```
dlt init dlthub:haystack_audio_api duckdb
```
The init command will setup the necessary files and folders for the next step.

🤠 Start LLM-assisted coding

Here’s a prompt to get you started:

Prompt
Please generate a REST API Source for Cohere API, as specified in @haystack_audio_api-docs.yaml 
Start with endpoints run and  and skip incremental loading for now. 
Place the code in haystack_audio_api_pipeline.py and name the pipeline haystack_audio_api_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 haystack_audio_api_pipeline.py and await further instructions.

🔒 Set up credentials

Authentication is handled via an API key, which must be included in the request headers to access the endpoints.

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

🏃‍♀️ Run the pipeline in the Python terminal in Cursor


python haystack_audio_api_pipeline.py

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


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

📈 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 haystack_audio_api_pipeline show --dashboard
```
🐍 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("haystack_audio_api_pipeline").dataset()
# get u table as Pandas frame
data.u.df().head()
```

Running into errors?

Ensure that the API key is valid and has the necessary permissions. Be aware of rate limits and handle errors gracefully. The API may require specific input formats for certain endpoints.

Extra resources:

Learn more with our 1h LLM-assisted coding course!