#๐Ÿ”’ can anyone here help me with system design for a project?

38 messages ยท Page 1 of 1 (latest)

edgy forumBOT
#

@neat sable

Python help channel opened

Remember to:

  • Ask your Python question, not if you can ask or if there's an expert who can help.
  • Show a code sample as text (rather than a screenshot) and the error message, if you've got one.
  • Explain what you expect to happen and what actually happens.

:warning: Do not pip install anything that isn't related to your question, especially if asked to over DMs.

neat sable
#

going for a hackathon, have my idea down, i need a way to systematically build it, I have made a few MVP's before but it was usually hap hazard as i added or removed features as i needed but now that i am with a team i need this to be robust

#

a slide from the ideation ppt i had sent to the hackathon's hosts

hexed flax
hexed flax
#

If its manually entered by a person, what is AI going to do?

neat sable
# hexed flax > With growing investor, customer, and regulatory expectations, businesses are r...

okay essentially, i am aiming this project for MSE's which are scaling up their business to international trade, and as ESG compliance is often a hurdle as they don't have a put together department at this point, I would take their unstructured data, fill in the gaps in data and then create a report which compares the company's current metrics, in the different ESG frameworks like GRI etc.

neat sable
hexed flax
neat sable
#

it talks about why i am doing what i am doing

hexed flax
hexed flax
neat sable
# hexed flax Thats fine. I don't need it. Unless it mentions where this reported data is goin...

hey man i am back and it is a little more clearer now i am taking unstructured file formats, currently limited to excel sheets, pdfs or images, what ever falls under teh scope of NLP and OCR, from there, it will have a normalization step, to get it to fit to an ESG framework (I am going with GRI), I will tag the normalized data into ESG categories given by the GRI framework, and then do assign a score, assigning of the score and coming up with a forumla is something my teammate is doing, and i will use that as a pivot to suggest recommendations on reforms to make in the company, and for the sake of querying i wanted to implement a RAG framework with the GRI's frameworks documentation as the retrival database

#

how does it sound?

hexed flax
#

But... what you've said so far is just the technical implementation and it does sound, OK

#

But I don't understand the "why" behind it

neat sable
#

oh well, the topic for the hackathon was to build some thing that would be akin toa breakthrough in a slow industry can be technical or non technical and must have some AI component and be ESG compliant, so I thought why not build something that makes these reports...

neat sable
hexed flax
#

If you fail to answer that, then yes, I don't see the value in creating reports that nobody will read.

neat sable
#

i currently feel that they spend more time creating the report than they do innovating on ways to actually bring down stuff like emissions, so this could help them have more time on their hands

hexed flax
neat sable
hexed flax
neat sable
# hexed flax > that way people can use test data too Who is "people"?

well since its being built for a hackthon in mind right now, i guess the judges, but if I stick at it, I want it to be a service like lets say, accessible to the internal ESG teams and for external users maybe consulatants and sustainability advisors, and regulators and investors too can send the information they documented before investing in a company in case they want to cross check the authenticity of the data

hexed flax
neat sable
#

so do you think i have the technical pipelines down? or are there any suggestions?@hexed flax

hexed flax
neat sable
neat sable
#

@hexed flax

edgy forumBOT
#
Python help channel closed

This help channel has been closed and it's no longer possible to send messages here. If your question wasn't answered, feel free to create a new post in #1035199133436354600. To maximize your chances of getting a response, check out this guide on asking good questions.