top of page
Writer's pictureAmar Harolikar

Analyze Live Data | AWSโ€“Azure DW | via Custom GPT & LLM Apps

Updated: Oct 24, 2024

Lighthearted Introduction




๐—ค๐˜‚๐—ฒ๐—ฟ๐˜†. ๐—ง๐—ฟ๐—ฎ๐—ป๐˜€๐—ณ๐—ผ๐—ฟ๐—บ. ๐—”๐—ป๐—ฎ๐—น๐˜†๐˜‡๐—ฒ. ๐—–๐—ต๐—ฎ๐—ฟ๐˜. ๐—™๐—ถ๐—น๐—ฒ ๐—ข๐—ฝ๐˜€. ๐—•๐˜‚๐—ถ๐—น๐—ฑ ๐— ๐—Ÿ ๐— ๐—ผ๐—ฑ๐—ฒ๐—น๐˜€


All in the Natural Language of your choice....

From within Custom GPT (ChatGPT Plus) as well as via externally deployed LLM apps on your intranet or public website...."


โžก๏ธ Earlier this year, I published a video demonstrating how to build a machine learning model with ChatGPT Plus using natural language. That required an offline data upload.


โžก๏ธ What if we could build ML models and perform analyses by directly connecting to live data warehouses in AWS and Azure?


....and not just the final analysis and model building, but also data transformations, modeling dataset creation, table level operations, record insertions, modifications, charts, and cross tabs. Pretty much anything you can do with Python/SQL, but with a simple UI and natural language.


I had to do something similar for client recently.


โžก๏ธ In this series, I'll show you how to do just that. I'll be working with prototype data warehouse I set up in AWS (RDS-MySQL) and Azure (MySQL), with tables ranging from just a few records to millions (the largest table has 10 Million records).


โžก๏ธ This is the kick-off video ....and a light-hearted introduction to connecting and working with AWS and Azure data warehouses via Custom GPT


Hope you have as much fun watching this video as I had making it.


-------------------------------------------


๐Ÿ“บ ๐—จ๐—ฃ๐—–๐—ข๐— ๐—œ๐—ก๐—š ๐—˜๐—ฃ๐—œ๐—ฆ๐—ข๐——๐—˜๐—ฆ : ๐—–๐—ข๐— ๐—œ๐—ก๐—š ๐—ก๐—˜๐—ซ๐—งย 

๐—š๐—ฃ๐—ง-๐—Ÿ๐—Ÿ๐—  ๐—–๐—ฎ๐—ฝ๐—ฎ๐—ฏ๐—ถ๐—น๐—ถ๐˜๐˜† ๐——๐—ฒ๐—บ๐—ผ๐—ป๐˜€๐˜๐—ฟ๐—ฎ๐˜๐—ถ๐—ผ๐—ป ๐—ฉ๐—ถ๐—ฑ๐—ฒ๐—ผ๐˜€

๐Ÿ”นVoice Mode Interactionย 

๐Ÿ”นData Transformations

๐Ÿ”นData Analysis

๐Ÿ”นTable Operations

๐Ÿ”นInter-Warehouse Operations: Across AWS & Azureย 

๐Ÿ”นBuild ML Models

๐Ÿ”นLimitations, Caveats & Constraints



๐—›๐—ผ๐˜„-๐—ง๐—ผ ๐—š๐˜‚๐—ถ๐—ฑ๐—ฒ๐˜€ย 

With Codes / Schemas / Github Repos



๐Ÿ‘‰ ๐—ช๐—ถ๐˜๐—ต ๐˜€๐—ฝ๐—ฒ๐—ฐ๐—ถ๐—ฎ๐—น ๐—ณ๐—ผ๐—ฐ๐˜‚๐˜€ ๐—ผ๐—ป ๐—ต๐—ผ๐˜„ ๐˜๐—ผ ๐˜‚๐˜€๐—ฒ ๐—š๐—ฃ๐—ง๐˜€ ๐˜๐—ผ ๐—ด๐—ฒ๐˜ ๐—ฎ๐—น๐—น ๐˜๐—ต๐—ถ๐˜€ ๐—ฑ๐—ผ๐—ป๐—ฒ ๐—พ๐˜‚๐—ถ๐—ฐ๐—ธ๐—น๐˜† ๐—ฎ๐—ป๐—ฑ ๐—ฒ๐—ณ๐—ณ๐—ถ๐—ฐ๐—ถ๐—ฒ๐—ป๐˜๐—น๐˜†

๐Ÿ”นFastAPI Server and Endpoints

๐Ÿ”นCustom GPT: Custom Actions / JSON schemas.

๐Ÿ”นExternal LLM Apps: Build with Flowise AI. Rapid deploy to internet/ intranet

๐Ÿ”นExternal LLM Apps: LLM options. Cost-Performance trade-offs

๐Ÿ”นExternal LLM Apps: Low-cost custom deployment of Open Source LLMs.

๐Ÿ”นExternal LLM Apps : API Connections with Flowise Custom Tool and JavaScript functions.

๐Ÿ”นBasic Security: LLM Injection / API Keys / IP Rules / Allowed Domains

๐Ÿ”นAccess Controls and selective access.

๐Ÿ”นSetting up MySQL Server on AWS & Azre, Installing phpMyAdmin for rapid prototyping

2 views
bottom of page