dlthub/dlt-plus-assistant icon
public
Published on 2/26/2025
dlt+ Assistant

Helps you manage your dlt+ project, build dlt pipelines, and explore loaded data. We recommend an LLM with strong tool-calling abilities and prompt adherence for the best experience. Reach out for an early access dlt+ license: https://dlthub.com/docs/plus/intro

Rules
Models
Context
128kinput·16.384koutput
200kinput·8.192koutput

MCP Servers

Learn more
uv tool run --prerelease=allow --with dlt-plus==0.9.0 --with sqlglot --with pyarrow --with pandas --with mcp dlt mcp run_plus
# dlt rules
## Basics
1. dlt means "data load tool". It is an open source Python library installable via `pip install dlt`.
2. To create a new pipeline, use `dlt init <source> <destination>`.
3. The dlt library comes with the `dlt` CLI. Add the `--help` flag to any command to verify its specs.
4. The preferred way to configure dlt (sources, resources, destinations, etc.) is to use `.dlt/config.toml` and `.dlt/secrets.toml`. Make sure to fill required fields when adding a source or resource.
5. During development, always set `dev_mode=True` when creating a dlt Pipeline. `pipeline = dlt.pipeline(..., dev_mode=True)`. This allows to reset the pipeline's schema and state between iterations.
6. Use type annotations only if you're certain you're properly importing the types.
7. Use dlt's REST API source if loading data from the web.
8. Use dlt's SQL source when loading data from an SQL database or backend.
9. Use dlt's filesystem source if loading data from files (CSV, PDF, Parquet, JSON, and more). This works for local filesystems and cloud buckets (AWS, Azure, GCP, Minio, etc.).
dlt Docshttps://dlthub.com/docs/general-usage
dlt+ Docshttps://dlthub.com/docs/plus/intro

Prompts

Learn more

No Prompts configured

Context

Learn more
Reference specific functions or classes from throughout your project
Reference all of the changes you've made to your current branch
Reference the last command you ran in your IDE's terminal and its output
Get Problems from the current file
Uses the same retrieval mechanism as @Codebase, but only on a single folder
Reference the most relevant snippets from your codebase
Reference the contents from any documentation site