Skip to main content
GuideTutorialsAdvanced TutorialsAPI ReferenceCLI ReferenceRelease Notes
Version: 2.0.0

Run Your First Data Integration

Before you start

Finish Install Tabsdata and Connect an AI Agent first, and make sure the server is running.

Before You Begin
Note

This quickstart is designed for use with a Tabsdata MCP integtration. To deploy and run Tabsdata without an LLM, switch to the developer doc mirror.

Quickstart Overview

We will be building a Tabsdata Workflow that:

  1. Ingests a local file called persons.csv and writes the data into a Tabsdata Table called persons
  2. Creates a new Tabsdata table called people that drops the age column and adds a full_name column
  3. Writes the people tables as a .jsonl file back into your local file system.
Click any node for what it does
Local File
Local File
Publisher
qs_pub
Pending
Table
persons
Pending
Transformer
qs_tfr
Pending
Table
people
Pending
Subscriber
qs_sub
Pending
Local File
Local File
Not written yet

Steps​

Get the example project​

tdk examples extract --name quickstart-ai --dir qs-example
⌄qs-example
⌄input-data
persons.csv
⌄output-data
conn-input.yaml
conn-output.yaml
README.txt

Creates qs-example/, which contains the source data persons.csv and two connection files.

Login to Tabsdata and start your LLM​

Log in, then start your agent from the same terminal:

tdk login --server localhost --user admin --password tabsdata
claude

Prompt your LLM to build a Tabsdata workflow​

Give the following prompt to your LLM:

Build a tabsdata workflow that 
1. ingests `qs-example/input-data/persons.csv`
2. creates a new column for the full name and drops the age column,  
3. writes the result as a .jsonl to the `output-data` folder

More info can be found under `qs-example/README.md`

Check Workflow Execution​

⌄qs-example
⌄input-data
persons.csv
⌄output-data
people.jsonl
conn-input.yaml
conn-output.yaml
README.txt

After your LLM finishes processing your request, you should have a new people.jsonl file in the qs-example/output-data/ folder.

Open the UI​

Go to http://localhost:2457 and log in with admin / tabsdata. You'll see your project, its collections, and the tables the flow just produced.