Coinka.co (https://Coinka.co) - budget tracking app on Telegram Mini Apps and iOSCoinka.co (https://Coinka.co) - budget tracking app on Telegram Mini Apps and iOS
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Huge congratulations on hitting the $10k milestone! 🚀 Truly inspiring to see what’s possible on Contra.
I joined Contra just about a month ago as a full-stack developer. I’ve set up my services and published a few case studies, but I'm constantly learning how to optimize my presence here.
If you could look back at your early days, what’s the #1 thing you did that moved the needle for your profile visibility and landing initial inbound clients?
I joined Contra a while ago without really knowing what to expect, and it’s been really nice to see it gradually become a place where I’ve met great clients and worked on projects I genuinely love.
AI Assistant Using Your Business Knowledge Base — RAG on Your Documents
THE PROBLEM
Q&A bots break down when knowledge lives in documents: a 100-page manual has no "questions" to match, it can't fit into a prompt, and generic chatbots hallucinate instead of admitting what they don't know.
THE SOLUTION
A RAG (Retrieval-Augmented Generation) knowledge base: documents are split into meaningful chunks, embedded into a vector index, and the assistant answers from the right sections — by meaning, not keywords.
Any format as-is: PDF, DOCX, TXT, Markdown — 100+ pages is fine
Answers grounded in YOUR documents — it says "I don't have that information" rather than inventing
Source references — every answer shows which document and section it came from
Runs on your infrastructure — documents never leave your control
One command to re-index after updating documents — documented, no programmer needed
The 'I don't have that information' line is the part most RAG builds skip, and it's the one that matters. How do you set the cutoff? On mine, a fixed similarity threshold broke once I filtered results by user role. Scores shifted and it refused questions it could answer.