AI Hackathon
← DEPARTURES
IN1110RAG & SearchStatus: Ended

GL Bajaj · Db2Hack 2026 | Build AI Applications on IBM Db2

GL Bajaj Group of Institutions, Mathura, Uttar Pradesh · on Unstop

Cash prize: Not stated
Free credits: Credits: not stated
Who can enter: Solo OK Country rules: unknown
Code rights: Not checked yet
IBMIBM Db2IBM Db2 Community EditionLangChainLlamaIndexHaystack
Submissions closedNov 10

This hackathon has ended. Submissions closed on 2026-11-10 11:30 UTC.

Ship a solo AI project that puts an enterprise relational database to work with modern frameworks.

Imported from Unstop and approved by our team. We haven't checked the rules by hand.

One email a week

New events that match your topics, every Monday. Unsubscribe anytime.

Flight details

Deadline:
2026-11-10 11:30 UTC
Cash prize:
Not stated

Prizes listed: Top 3 Winners: amount not stated (Trophy, IBM Db2 Kit and Certificate of Excellence.); Top 10 Participants: amount not stated (IBM Db2 Goodies and Certificate of Merit.); High-Potential Projects: amount not stated (Opportunity to contribute the project use case to the IBM Db2 GitHub Organisation.)

Project ideas

Text-to-SQL Analyst for Db2

A chat interface turns a plain-English question into a Db2 SQL query, runs it, and explains the rows with the generated SQL shown.

Architecture: Chat UI captures question and target schema → LangChain agent maps question to tables and columns → SQL generator emits a Db2-compatible statement → Db2 runs the query and returns rows, SQL and a narrative

Stack: Python, LangChain, IBM Db2 Community Edition, Git

Document Intelligence Layer on Db2

Uploads PDFs and policy documents, stores chunks and embeddings in Db2 with vector search, and answers questions with page citations.

Architecture: Upload endpoint stores PDFs and policy documents → Parser splits documents into chunks → LlamaIndex builds embeddings for each chunk → Db2 vector search retrieves passages for cited answers

Stack: Python, LlamaIndex, IBM Db2 Community Edition, Git

CrewAI Operations Copilot for Retail

A small agent crew watches an enterprise Db2 dataset, flags anomalies, drafts a summary of changes, and suggests the next query.

Architecture: Scheduled job pulls fresh rows from Db2 → CrewAI analyst agent computes trends and outliers → CrewAI writer agent turns findings into a digest → Db2 log and dashboard show digest and drill-down queries

Stack: Python, CrewAI, IBM Db2 Community Edition, Git

FAQ

Can I enter on my own, or do I need a team?
Solo entry is allowed and is the only option listed: team size is 1 to 1 and team submissions are not permitted. Registration is free.
Who is eligible to take part?
The listing says it is open to all, including students, developers, freshers, working professionals and AI enthusiasts, with no prior Db2 experience required. Eligibility is not confirmed, so check the official rules.

Sources

Open the original event page →

More open AI hackathons