Hello!

Welcome to this portfolio

All projects

CASE STUDY 04

  • Professional
  • Generative AI
  • BI

Querying data in your own words

An NL2SQL application for non-technical users.

Tressol-Chabrier · Work-study placement

Mistral LargeStreamlitPythonpyodbcPlotly

The project, step by step

Natural languagecustomer master data exploration

  1. 01

    Ask a question

    In natural language

  2. 02

    Generate the query

    Mistral Large translates the question into SQL

  3. 03

    Query the data

    Access customer master data through pyodbc

  4. 04

    Explore the answer

    Plotly charts in Streamlit

01

Context

Development of a natural language analytics application at Groupe Tressol-Chabrier.

02

Problem

Enable non-technical users to explore customer master data without writing SQL queries.

03

Data

The group's customer master data. Its exact scope and volume are not specified.

04

Approach

I developed a Streamlit application combining natural language queries, SQL access and visualisation.

05

Method

The application uses the Mistral Large API, Python, pyodbc and Plotly to enable exploration of the master data.

06

Results

An NL2SQL application that enables business teams to query customer master data in natural language.

07

Technologies

Streamlit, Mistral Large API, Python, pyodbc and Plotly.

08

Lessons and limitations

Query reliability, handling of ambiguous questions and access control arrangements remain to be documented; no success rate is reported.