Data Query & Visualisation using LLM Agents from Scratch
Last Updated on October 31, 2024 by Editorial Team
Author(s): Akash Modi
Originally published on Towards AI.
Building a simple data analysis & plotting engine using LLaMa and LangChain Agentic Framework with Structured Data
This member-only story is on us. Upgrade to access all of Medium.
Image by authorIn this article, we will build a tool from scratch that enables querying from various structured datasets, including tables, CSVs, and DataFrames. This tool is designed to perform data analysis and generate charts/graphs for better visualization and understanding of the provided data. This tool uses llama-3.2β90b-text and LangChains Agentic framework to automatically understand the type of query and respond accordingly with an text or chart. We will be using GROQ as the free LLM inferencing platform to consume LlaMa 3.2.
If you are not able to view this please click here for free view.
To fully grasp the concepts in this article, a basic understanding of LLMs and agents is recommended. You can refer to the articles below to refresh and strengthen your knowledge of these topics.
LLMs β How do LLM Works?Agents β Agents from scratch
We are going to use the Financial Tabular dataset from Kaggle.
Financial Statements.csv
This dataset is a compilation of information extracted from the 10-K annual reports and balance sheets of various companies. It features longitudinal or panel data covering the years 2009 to 2022. The companies are categorized according to their stock classifications. Here is a… Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming aΒ sponsor.
Published via Towards AI