top of page
Writer's pictureAmar Harolikar

GenAI App | LLM Analytics Assistant: Simplifying Data Transformation & Insights. AWS & Azure MySQL DW Example

Updated: Oct 24, 2024









3rd part of the series on LLM Analytics Assistant Apps


Demonstrating data transformation and analysis on AWS MySQL via an LLM App. The app is deployed on my public website (outside of GPT Store, access-controlled section).


I cover 3 areas:


๐—Ÿ๐—Ÿ๐—  ๐—”๐—ฃ๐—ฃ ๐——๐—˜๐— ๐—ข

๐——๐—ฎ๐˜๐—ฎ ๐—ช๐—ฟ๐—ฎ๐—ป๐—ด๐—น๐—ถ๐—ป๐—ด & ๐—”๐—ป๐—ฎ๐—น๐˜†๐˜€๐—ถ๐˜€: prototype customer table and transaction table with a million to 10 million records, creating summaries and merging data into new tables with additional variables... analyzing and creating customer profiles. All instructions in natural language... sometimes fuzzy and unclear... and sometimes with spellos...



๐—•๐—”๐—ฆ๐—œ๐—– ๐—”๐—ฅ๐—–๐—›๐—œ๐—ง๐—˜๐—–๐—ง๐—จ๐—ฅ๐—˜

Similar to one that I am currently using on a live client project.


๐—Ÿ๐—Ÿ๐—  ๐—”๐—ฝ๐—ฝ ๐—•๐˜‚๐—ถ๐—น๐—ฑ ๐—ฎ๐—ป๐—ฑ ๐—จ๐—œ: using Flowise AI. Open-source. Allows for rapid deployment. Powerful capabilities. Many other options - e.g. custom build with React/Next.js that can link up to company SSO and authentications.


๐— ๐—ผ๐—ฑ๐—ฒ๐—น ๐—–๐—ต๐—ผ๐—ถ๐—ฐ๐—ฒ: trade-offs between pricing, speed, response quality, and security/privacy. Premium model vs. open-source on-prem solution.


๐—”๐—ฟ๐—ฐ๐—ต๐—ถ๐˜๐—ฒ๐—ฐ๐˜๐˜‚๐—ฟ๐—ฒ ๐—™๐—น๐—ฒ๐˜…๐—ถ๐—ฏ๐—ถ๐—น๐—ถ๐˜๐˜†: FastAPI processing server. Separate from the main system, making it reusable with different UI apps and backend databases.


๐—–๐—ข๐—ฆ๐—ง ๐—–๐—ข๐—ก๐—ฆ๐—œ๐——๐—˜๐—ฅ๐—”๐—ง๐—œ๐—ข๐—ก๐—ฆ

๐—–๐—ผ๐˜€๐˜ ๐—˜๐˜…๐—ฎ๐—บ๐—ฝ๐—น๐—ฒ: ran 478 API requests/queries over 10 hours with GPT-3.5, costing around $1... working with the 1 million-10 million dataset referred to above... also discuss optimization strategies...


๐—–๐—ต๐—ผ๐—ผ๐˜€๐—ถ๐—ป๐—ด ๐—Ÿ๐—Ÿ๐—  ๐—บ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€: depends on use case. e.g. Multi-LLM option...for difficult tasks, use an expensive model, and for simpler tasks, use a lower cost model.... or On-Prem solution for specific use cases.


๐—™๐˜‚๐—น๐—น ๐——๐—ฎ๐˜๐—ฎ ๐—œ๐—ป๐—ด๐—ฒ๐˜€๐˜๐—ถ๐—ผ๐—ป by the LLM model is not always necessary... can significantly increase costs... potentially increasing by 100 times or more. For many use cases, processing can be done separately, and the LLM only passes SQL queries/Python commands.


๐—ฆ๐—ฝ๐—น๐—ถ๐˜ ๐—ช๐—ผ๐—ฟ๐—ธ๐—ณ๐—น๐—ผ๐˜„ ๐—”๐—ฝ๐—ฝ๐—ฟ๐—ผ๐—ฎ๐—ฐ๐—ต: for scenarios requiring full data ingestion, split the workflow into multiple modules. LLM to only ingest the necessary and smallest amount of data directly... process the rest of the data separately.


๐—จ๐—ฃ๐—–๐—ข๐— ๐—œ๐—ก๐—š ๐—ฉ๐—œ๐——๐—˜๐—ข๐—ฆ ๐—”๐—ก๐—— ๐—ฃ๐—ข๐—ฆ๐—ง๐—ฆ

Currently preparing detailed tutorials and step-by-step guides covering code, tips, and leveraging GPTs to develop apps. In future videos and posts, I will also cover areas like : processing with on-prem solutions, multiple LLM approaches, segregation of Python processing vs. MySQL processing, machine learning model builds, selective accesses, and more.




10 views
bottom of page