Splitgraph

Splitgraph is a ChatGPT plugin that allows users to interact with public datasets found on the Splitgraph Data Delivery Network. These datasets typically originate from open government initiatives and may relate to various fields such as epidemiology, traffic engineering, urban planning, real estate trends, demographical insights, educational statistics, public infrastructure and services, taxation, public officials, and more. The plugin is designed to provide easy access to valuable data for both professionals and enthusiasts.

How to use:

1. Installation: Users can either install the Splitgraph by searching for it in the ChatGPT plugin store or simply press the "try it" button at the top right of this page to open a chat in ChatGPT with the plugin already activated.

2. Finding Tables: Utilize the find_relevant_tables endpoint by providing a prompt or question. This will return a list of tables that may be referenced in an SQL query.

3. Running SQL Queries: Generate a valid SQL query using the tables described in the first step, and submit this query to the run_sql API endpoint to receive results. The queries must be syntactically correct PostgreSQL SQL queries.

4. Prompt Examples:

   • To find relevant tables: "Find tables related to traffic statistics in New York."
   • To run an SQL query: "SELECT \"citydata_traffic\".\"hour\", \"citydata_traffic\".\"count\" FROM \"citydata\".\"traffic\" LIMIT 5"
   • To explore urban planning data: "Find tables related to urban planning in Chicago."
   • To analyze real estate trends: "Find tables showing real estate price trends in San Francisco."

5. Editing Queries: If the generated SQL cannot be executed, an error message will be present in the response. Users can click on the provided link to debug and improve the generated SQL query.

6. Understanding Data: The plugin provides insights into various sectors, and users can craft specific queries to extract the information they need.