querychat is a multilingual package that allows you to chat with your data using natural language queries. It's available for:
Imagine typing questions like these directly into your dashboard, and seeing the results in realtime:
querychat is a drop-in component for Shiny that allows users to query a data frame using natural language. The results are available as a reactive data frame, so they can be easily used from Shiny outputs, reactive expressions, downloads, etc.
This is not as terrible an idea as you might think! We need to be very careful when bringing LLMs into data analysis, as we all know that they are prone to hallucinations and other classes of errors. querychat is designed to excel in reliability, transparency, and reproducibility by using this one technique: denying it raw access to the data, and forcing it to write SQL queries instead.
querychat's natural language chat experience is powered by LLMs (like GPT-4o, Claude 3.5 Sonnet, etc.) that support function/tool calling capabilities.
querychat does not have direct access to the raw data; it can only read or filter the data by writing SQL SELECT statements. This is crucial for ensuring relability, transparency, and reproducibility:
Currently, querychat uses DuckDB for its SQL engine when working with data frames. For database sources, it uses the native SQL dialect of the connected database.
Language-specific DocumentationFor detailed information on how to use querychat in your preferred language, see the language-specific READMEs:
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4