Turning Tables: Turn English to Data Using Self-Hosted LLMs

Registration/RSVP is now closed due to all workshop seats being filled.

About the workshop 📚

Participants will create a web application from scratch using Streamlit and Ollama. This application will generate SQL to manage databases, analyze and transform English to Tabular data. This application will help business users and non-technical professionals to make faster business decisions, without data analysts - saving them both time and money.

• The workshop is of 2.5 hours duration.
• This is an in-person workshop.
• Only 35 seats are open for workshop participation.
• Recording of the workshop will be made available for The Fifth Elephant members.

Important Prerequisites for Participants attending the workshop 📝

To attend this workshop, participants must be familiar with Python

Workshop outline 🗂️

• Overview of the workshop.
• Demo of the application.
• Discussion on running LLMs locally for data privacy.
• Hands-on: setting up Ollama model server.
• Hands-on: setting up Streamlit and building quick interactive front-end applications.
• Hands-on: pipeline for using natural language prompts to transform tabular data using CSV files.
• Hands-on: data processing techniques like prompt pruning and correcting LLM Hallucinations using static analysis with SQLGlot
• Discussion on how to create generic “Chat with X” capabilities.

About the instructors 👨 🏫

Abhijeet Kumar is Director of Data Science at Fidelity Investments.

Subhom Mitra is a Data Scientist at Fidelity Investments.

Who should attend this workshop 👨 💻

• Data engineers
• Data scientists
• Researchers
  who are working on Generative AI use-cases and want to leverage enterprise data.

This workshop may also be of interest to business analysts and business consumers who require data querying and analytics services regularly.

How will participants benefit from the workshop 🎓

At the end of the workshop participants will learn:

1. How to run LLMs locally or within their organizational network using Ollama.
2. How to quickly develop interactive web applications using Streamlit.
3. How to analyze tabular data in CSV format using English language queries.
4. How to create “Chat with X” applications for other data formats.

How to Register

This workshop is free to attend for The Fifth Elephant members or The Fifth Elephant Conference ticket buyers.

This workshop is open to 35 participants only. Seats will be available on first-come-first-serve basis. RSVP to secure a seat. 🎟️

Contact information ☎️

For inquiries about the workshop, contact +91-7676332020 or write to info@hasgeek.com

Additional Reading

Here are some links to open-source and proprietary products currently available which leverage LLMs to generate SQL and power database interactions.

1. Vanna: an MIT-licensed open-source Python RAG (Retrieval-Augmented Generation) framework for SQL generation and related functionality.
2. Dataherald: a natural language-to-SQL engine built for enterprise-level question answering over relational data.
3. ChatDB: build dashboards for your database with AI.
4. DB-GPT: an open source AI native data app development framework for building infrastructure in the field of large models.