Multi-agent LLM Framework for Conversational Data Retrieval from Enterprise Databases

Introduction

The rapid development of Large Language Models (LLMs) such as OpenAI's GPT-4 has spurred significant interest among companies in diverse sectors such as automotive, software, hardware, manufacturing, and cloud computing. Enterprises are eager to investigate the potential integration of these advanced language models with their enterprise data. Application areas include but are not limited to:

1. Text-to-SQL on databases – generate a SQL query to fetch results from a DB.
2. Conversational chatbots – question-answering on documents.
3. Text-to-Code – generate code to perform a task based on the user input.

This internship aims to explore various methods for deploying LLMs on new and unseen data, specifically in the automotive industry. The investigation encompasses aspects such as Retrieval Augmented Generation (RAG), Microsoft's AutoGen multi-agent framework, and the fine-tuning of open-source models like Meta's Llama-2. The internship also involves the development of a web app that interacts with the GPT-4 model for data retrieval. 

Objectives
The primary goal of this internship was to create a prototype framework using recent advancements in LLMs to extract conversational information from enterprise data. This prototype served as a starting point to investigate the potential scalability of the framework for enterprise-wide use beyond the internship's scope.

During the internship, our focus was on the following tasks:

We explored and developed a RAG (Embeddings with Vector Search and AutoGen multi-agents) framework for:

    a) Performing text-to-SQL operations on tables containing sensor data.
    b) Retrieving data from files containing documentation.