aman2k4

im working on something very similar.

https://www.5outapp.com/

Im working on https://www.5outapp.com/

An app to track your groceries, to save money and eat healthy.

I think healthiest food is cooked at home and people are eating out and doing takeaways . So I am planning to build tools and features which help people to cook more at home.

yeah when i noticed this, it blew my mind.

Ok, thanks for the feedback. Will think of something else

I’m using AWS textract for scanning grocery receipts and i find it does it very well and fast. Can you say which performance metric you have in mind?

You meant in the web version? it is supposed to look like a blank box in the rectangle grocery bill shape, but i suppose the design can be a bit better there. Thanks for the feedback.

I am using AWS Textract + LLM (OpenAI/Claude) to read grocery receipts for <https://www.5outapp.com>

So far, I have collected over 500 receipts from around 10 countries with 30 different supermarkets in 5 different languages.

What has worked for me so far is having control over OCR and processing (for formatting/structuring) separately. I don't have the figures to provide a cost structure, but I'm looking for other solutions to improve both speed and accuracy. Also, I need to figure out a way to put a metric around accuracy. I will definitely give this a shot. Thanks a lot.

Saw something similar a couple of weeks ago on HN.

https://news.ycombinator.com/item?id=40455478

IMO, comments with an upvote are the most powerful feature of such a system.

I live in Europe and have moved to more than 10 cities in my life. It always takes so much time for me to reach the point where I can confidently say that I know a city well. I wish I could make friends with people who have been residents of the city for a longer period. I've tried using Meetup to meet people, but it often full of newcomers.

What is your genuine opinion about Indian startup culture ?

yeah using chain of thoughts to tackle it. This is relatively simple

Cool, i should try it..so far i have been working with rephrasing the work experiences description to fit a job description using GPT3.5 api. Still have not engineered the prompt to get reasonable output.For tools and skills , i have a prefilled dictionary which more or less represent my expertises. task of GPT is select top n skills/tools and put them in final result.

This is exactly what i have been working on for few weeks but not been able to get a good final results. I want to make sure that AI is not overselling my skills or completely deviating from my current experiences/skill set when trying to tailor resume for a job post.