Go from a 200MB flat file with 1.5M records to analysis in minutes with my open-source AI-SQL App

https://www.youtube.com/watch?v=vrGSzzGmZDA

20 Yrs ODI Cricket stats - i'm providing the data and tools. Go run it.

𝟭. 𝗚𝗲𝘁 𝘁𝗵𝗲 𝗗𝗮𝘁𝗮

𝗗𝗮𝘁𝗮: 25 years of ODI cricket data from cricsheet.org processed with Tigzig tools.

𝗙𝗼𝗿𝗺𝗮𝘁: Pipe delimited raw TXT file, ~200MB, 1.5M records.

𝗗𝗼𝘄𝗻𝗹𝗼𝗮𝗱 Link: https://drive.google.com/drive/u/1/folders/1VHD9UzeYaJF_dBPecnjucHpoGocf4IvR

𝟮. 𝗚𝗲𝘁 𝘁𝗵𝗲 𝗙𝗿𝗲𝗲 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲

𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺: neon.com.

𝗔𝗰𝘁𝗶𝗼𝗻: Go to their site. Get a free, live Postgres database in seconds. No CC required. Copy the credentials. This is your temporary analysis sandbox.

𝟯. 𝗟𝗼𝗮𝗱 𝘁𝗵𝗲 𝗗𝗮𝘁𝗮

𝗣𝗹𝗮𝘁𝗳𝗼𝗿𝗺: app.tigzig.com → Database Apps → DATS-4

𝗔𝗰𝘁𝗶𝗼𝗻: Connect to your Neon DB, then upload the 200MB text file. The app handles the rest. Takes ~2 minutes.

▸ Menu → Connect to Database

▸ Menu → Choose File

𝟰 𝗤𝘂𝗲𝗿𝘆 𝘄𝗶𝘁𝗵 𝗡𝗮𝘁𝘂𝗿𝗮𝗹 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲

𝗔𝗰𝘁𝗶𝗼𝗻: Just type or dictate your question.

▪️ Example 1: 'Show top 10 batsmen by runs off the bat with chart'

▪️ Example 2: 'For these, show runs, matches, overs, run rate per match & per over, with chart'

𝗗𝗔𝗧𝗦-𝟰

My open-source SQL multi-agent app. It handles Text-to-SQL, Python charting, stats, instant Postgres creation, PDF outputs, and provides 9 reasoning models (Gemini, Claude, DeepSeek, more.

⚠️ 𝗣𝗿𝗮𝗰𝘁𝗶𝘁𝗶𝗼𝗻𝗲𝗿'𝘀 𝗪𝗮𝗿𝗻𝗶𝗻𝗴

This is a public-facing app. All credentials and API calls run through my backend server.

𝗥𝘂𝗹𝗲: Use this public version for sandbox testing ONLY, with temporary databases and non-sensitive data.

𝗙𝗼𝗿 𝗟𝗶𝘃𝗲 𝗨𝘀𝗲: Full source code shared. Deploy it on your VPN. Current setup is low-security for open testing; live use must tighten auth and access controls. Basic OAuth module with Auth0 included in source.

𝗪𝗵𝗲𝗿𝗲 𝗶𝘁 𝗴𝗲𝘁𝘀 𝗺𝗲𝘀𝘀𝘆

This example uses file i pre-processed for rapid analysis

𝗥𝗲𝗮𝗹𝗶𝘁𝘆: is not like click-click and report appears. It's more like bang-head, bang-head and then a drop appears

𝗧𝗵𝗲 𝗪𝗼𝗿𝗸: needs data cleaning, semantic layers, pre-computed metrics, marts and summary tables. AI is a powerful tool, but it doesn't replace solid data engineering - even though I use AI for data engineering too, including pre-processing of this data.