DEV Community: Khadija Shafaqat

Stocksage-AI

Khadija Shafaqat — Sun, 25 Oct 2026 17:53:06 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

What I Built

StockSage AI is a smart kitchen waste reducer for restaurants. Running a kitchen means checking stock, spotting what is about to expire, deciding what to cook, and writing shopping lists, every single day. StockSage does that work for you.

You tell it what you have (type it, paste a messy note like "got 5kg tomatoes, 2kg chicken expires tomorrow", or snap a shelf photo), and it:

Flags expiring and expired ingredients and shows the money lost to waste (Rs)
Suggests dishes you can cook right now, using the soon-to-expire ingredients first
Accepts your own menu dishes, so suggestions match what you actually sell
Builds a supplier-wise shopping list for low-stock items, with cost estimates
Generates a daily inventory report you can copy or print
Writes a morning brief with two "use it up" specials when the page opens

The lazy part: nobody types an inventory by hand or plans waste. You open the page and the work is already done.

Demo

Click Load sample data to see the full flow. The AI card talks to Ollama on your own machine, so it only works from the downloaded file.

Code

khadijashafaqat64-ui / stocksage

stocksage

View on GitHub

It is a single stocksage.html file: vanilla JS, no backend, no build step, data in localStorage.

How I Built It

Model: qwen2.5:3b, an open-weight model, run locally with Ollama. The model name is a field in the UI, so any Ollama model can be swapped in. A vision model (like llava) can be set for shelf photos.
Auto-fill stock: the note or photo is sent to the local model with a prompt asking for a strict JSON array (name, qty, unit, days_to_expiry). The page parses it and adds the items. If expiry is not mentioned, the model guesses a typical shelf life.
Morning brief: the page builds its own inventory report, sends it to the model, and shows a short brief plus two creative specials.
Everything else is plain code, not AI: expiry checks, dish matching, shopping lists, and waste cost. They are fast and predictable, so the model only does the typing and the writing.
Graceful fallback: with no Ollama running, the whole app still works.

I tested it on a modest laptop: 7.7 GB RAM, CPU only, no GPU. A 3B model was enough for this job.

Why Does Open Innovation Matter?

Private by default. Stock levels, supplier names, and prices are sensitive for a small restaurant. With a local open-weight model, none of it leaves the laptop.
No per-request bill. A kitchen can run it all day at zero cost.
Works without cloud. Everything runs on one laptop at localhost.
Swappable. The model is one text field. A bigger model, a different family, or a fine-tune on a restaurant's own menu is a one-line change.

A closed API would have meant uploading business data to someone else's server and paying for every note and photo.

The Lazy Payoff

MenuCraft AI: Offline Marketing Content for Small Restaurants

Khadija Shafaqat — Sat, 17 Oct 2026 21:30:47 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

MenuCraft AI is a desktop app that writes marketing content for small restaurants, cafes, bakeries and home kitchens, entirely on the owner's own laptop.

Who would pay for it: small food businesses that need a steady stream of menu descriptions, Instagram captions and WhatsApp messages but have no copywriter and no budget for one. It also fits freelancers and social media managers who run content for several small restaurants and want to produce a month of posts in minutes.

The problem it solves: the usual shortcut is a cloud AI subscription, which means a recurring cost, a stable internet connection, and menu and pricing data sent to servers the owner doesn't control. MenuCraft AI removes all three.

What it does:

Six content types: menu description, Instagram caption, Facebook post, WhatsApp message, Google Business post and special offer
Five tones: friendly, premium, fun, desi street style and family-friendly, plus a creativity slider
Whole menu in one click: load a CSV and get content for every dish. The importer groups rows by dish, so a pizza listed in four sizes becomes one item with all its sizes and prices. I tested it on a real 37-row pizza restaurant menu, which became 15 dishes
Live streaming output with a stop button, so the app feels responsive even on a small model
History and profile: the last 50 generations are saved, and the restaurant name, city, tone and model are remembered
Export to CSV (opens in Excel) or save as text, so the owner can hand the results to a designer or schedule them
Guardrails in the prompt: the model is told never to invent discounts, ingredients or awards that were not in the input

Demo

The demo shows the app running with Wi-Fi switched off, generating a single caption, then generating content for a full menu from a CSV and exporting it to Excel.

Code

khadijashafaqat64-ui / menucraft-ai

Offline marketing content generator for small restaurants, built on Ollama and Qwen

MenuCraft AI

A desktop app that writes menu descriptions and social media content for small restaurants, cafes and home kitchens. It runs entirely on your own computer with an open-weight model through Ollama, so it works offline, has no per-use cost, and keeps menu and pricing data private.

Built for the Hacktoberfest Open-Source AI Challenge, Week 2: Side Hustle.

Features

Six content types: menu description, Instagram caption, Facebook post, WhatsApp message, Google Business post, special offer
Five tones: friendly, premium, fun, desi/street, family-friendly, plus a creativity slider
Whole menu from a CSV: generate content for every dish in one click. Rows that belong to the same dish (for example one pizza in four sizes) are merged into a single item with all sizes and prices
Live streaming output with a Stop button
Model dropdown: every model installed in Ollama shows up automatically
History of the last 50 generations, and…

View on GitHub

How I Built It

The whole thing is built around local inference:

Ollama runs the model on the machine and exposes a simple local HTTP API
Qwen 2.5 (3B) is the default model: small enough to run on an ordinary laptop
Python + CustomTkinter for the desktop interface

How it fits together:

On startup the app asks Ollama which models are installed (/api/tags) and fills the model dropdown, so swapping models takes one click. If Ollama isn't running, it says so in plain language.
Each request builds a prompt from the dish, price, ingredients, menu category, tone and content-type rules (for example, "under 60 words, 2-3 emojis, 5 hashtags" for Instagram), then streams the answer token by token from Ollama's /api/generate endpoint.
Generation runs on a background thread, so the interface never freezes and the Stop button works mid-sentence.
For menu batches, a CSV reader merges rows that belong to the same dish and combines their sizes and prices into one prompt, then generates dish by dish and shows progress as 3/15.

What didn't work, honestly: I first added Urdu and Roman Urdu, because much of the local audience writes that way. The 3B model couldn't do it. It mixed in Chinese and Punjabi characters and produced broken sentences. I tried a stricter prompt, and then added automatic detection of the wrong script with retries, but the real fix is a bigger model. Instead of shipping poor output, I shipped English only. That's a real trade-off of local-first AI: you give up some model size in exchange for cost and privacy, and a larger local model is my next step for Urdu.

Why Does Open Innovation Matter?

Costs stay near zero. There is no per-request API fee, so generating content for a 40-dish menu costs only electricity. That is what makes a very low price workable for a small restaurant. With a paid API, every dish regenerated is a cost I'd have to pass on.
It works offline. I built and tested this on an unreliable internet connection, and the app kept working because nothing in the core flow needs the network. For a small business with patchy connectivity, that is a real feature, not a nice-to-have.
Customer data stays private. Menus, prices and promotional plans never leave the laptop, and there is nothing to sign up for.
No lock-in. I can swap models, change the prompts and add rules like "never invent discounts" without waiting for a vendor, and I won't be hit by pricing or policy changes later.

A closed API would have been easier to start with, but it would have made the business model harder: a running cost per customer, a mandatory internet connection and a third party holding every client's data.

My First User

I showed MenuCraft AI to the owner of a local pizza shop and ran their menu through it. Generating the content took about 2 minutes.

Their reaction was that it was amazing, and they were especially impressed that it works without internet. They said they would pay around Rs. 500 for one week it.

Their first request was to add more languages, which is why a larger local model for Urdu and Roman Urdu is the top item in my next steps.

Next Steps

Add a larger local model for proper Urdu and Roman Urdu content (the first thing my first user asked for)
.docx export for printed menus
Package the app as a single .exe so owners can install it without touching Python

First Post

Khadija Shafaqat — Wed, 14 Oct 2026 19:02:21 +0000

🚀 Hello, Dev Community!

I'm excited to be here and share my journey as a Robotics & AI student!

I'm passionate about exploring technology, building creative projects, and learning new skills. So far, I've worked on an ultrasonic smart walking stick, a hand gesture recognition system, Conway's Game of Life, and a Forensic Investigation game.

I'm currently exploring Python, C++, Arduino, AI, and computer vision while improving my problem-solving and development skills.

My goal is to build innovative projects, participate in hackathons, collaborate with fellow developers, and learn from the amazing tech community.

I'm still learning, experimenting, and growing, and I'm excited to share my progress along the way. 💻🤖

Let's connect, learn, and build something amazing together!

Robotics #ArtificialIntelligence #Programming #BuildInPublic #DeveloperCommunity