# Instructions ## Prerequisites 1. [Download and install ](/v0.20.x/using-distributional/getting-started.md#installing-distributional)our Python client. 2. Ensure `pandas` is [installed](https://pandas.pydata.org/docs/getting_started/install.html#other-data-sources): `pip install "pandas[parquet]"`. ## Instructions The tutorials come with data and Jupyter notebooks that show you how to get your application data into dbnl and how to create projects and runs. To connect to dbnl, you will need to have the `DBNL_API_TOKEN` environment variable set. Some tutorials demonstrate how to use dbnl with proprietary data stores such as Snowflake — in that case, we provide example Run data so that you can execute the tutorial regardless. 1. For each tutorial, download the relevant zip files at the beginning of the tutorial. The notebooks found in the zip files can be used to generate the project, runs, and tests within the dbnl platform. 2. If you are simply interested in creating existing data on the platform, then execute the notebook within the extracted folder. 3. To walk through the tutorial and learn the pieces of information we believe will be relevant for successful product usage, create a new notebook in the extracted folder and follow any of the tutorials in this section. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.dbnl.com/v0.20.x/tutorials/instructions.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.