Simret.exe
120 subscribers
396 photos
14 videos
146 links
It’s just a chill space where I share my dev moments, ML/backend projects, and things I learn along the way. I started this to stay committed and grow with others. If you vibe with that, open your laptop and let’s figure out tech together πŸ’»πŸ§šβ€β™€οΈ
Download Telegram
TIKVAH-SPORT
α‹¨αŒ¨α‹‹α‰³ αŠ αˆ°αˆ‹αˆˆα ! 4:00 αˆαˆ¨αŠ•αˆ³α‹­ ከ αˆ΄αŠ”αŒ‹αˆ @tikvahethsport @kidusyoftahe
The second half started 😴😴😴
It is hard to guess who will win
Good night fam🫑🫑
Good morning ppls 🫑🫑🀝🀝
Have a productive day ☺️
πŸ”₯1
🫑😁New challenge this week!

Building a Retrieval Augmented Generation (RAG) system that can answer questions from customer complaint data using semantic search and LLMs.

The goal is to transform thousands of customer complaints into meaningful insights that help teams better understand customer pain points.

This week project will lead me to learn more about vector databases, embeddings, retrieval systems, and AI-powered question answering.

😎DAY 1

#AI #RAG #MachineLearning #LLM #GenerativeAI
❀2
Here is the real LeoπŸ‘πŸ½βœŒπŸΏ
https://t.me/leotriesdesign/787
❀3
Simret.exe
🫑😁New challenge this week! Building a Retrieval Augmented Generation (RAG) system that can answer questions from customer complaint data using semantic search and LLMs. The goal is to transform thousands of customer complaints into meaningful insights that…
This phase needs a deep understanding of the setup you really have to know which packages to install and how to balance dependencies if you don't want to cry later! 😁

The next step is running EDA on a massive customer complaint dataset across credit cards, personal loans, and money transfers. I hope it isn’t going to be too hard! 🀞✌️

Good night everyone! 😴✨
❀2
Good morning my Habesha ppl☺️😎
Let us continue the thing we started 🀝🀝
Have wonderful Thursday ☺️
❀1
Forwarded from Opportunity Hub
DevOps - αŒ«αŠαŠ“ αŠ α‹αˆ«αŒ…
😁3
✨Today's New concept

Approximate Nearest Neighbor (ANN) algorithms make similarity search much faster by finding vectors that are close enough to the nearest neighbors without checking every vector in the database.

#DAY2 of the project
πŸ”₯3
Forwarded from Yohannes Haile (Yohannes Haile)
β€œThe undocumented life is not worth living”
β€” Socrates, Influencer
😁2
This shows mom's resilience has no limits.❀️❀️ still she is young but she achieve her dreams
❀5
🫑Project update on #DAY2

I have been working on :

Loading & explored 9.6 million real CFPB customer complaints🀧🀧🀧

Analyzed complaint distribution across 21 product categories

Built a text cleaning pipeline (boilerplate removal, normalization)

Set up CI/CD with GitHub Actions β€” 7 tests passing βœ…

Next up: building the embedding pipeline to turn these complaints into searchable AI vectors! πŸ”₯

It seems easy but it is not.It needs careful consideration of the data.
❀4
Good morning everyone 🫑🫑☺️☺️
I don't know how the week went πŸ€”πŸ˜
And Friday comes😁😁
Any ways Have a productive day 🫑
Enkuwan adersachu for sene Michael πŸ™
❀6
Simret.exe
🫑Project update on #DAY2 I have been working on : Loading & explored 9.6 million real CFPB customer complaints🀧🀧🀧 Analyzed complaint distribution across 21 product categories Built a text cleaning pipeline (boilerplate removal, normalization) Set up CI/CD…
#DAY3 of the project

Yesterday what I did was that cleaning and organising the complaint letters. So the next part is teaching the AI how to read and remember them.It is going to be implementing text chunking , choosing an embedding model and also generating vector embedding for each chunk.

✌️✌️trust the process
⚑3
This media is not supported in your browser
VIEW IN TELEGRAM
I have no boundaries how much I love pheven_teklay❀️😘😘 her voice her thoughts ☺️🀐

This one I found on my gallery like a remainder ☺️

People will always have opinions and labels, but your peace is your responsibility. Guard your energy like a soldier, heal your soul like a doctor, and keep moving forward. πŸšΆβ€β™€οΈπŸ’«
❀3
#Opportunity_AlertsπŸ“£

🌟Paid Internship Opportunity: Join Mastercard Foundation Associates Program 2026 for Young Africans🌟

✨Are you a recent graduate looking for paid work experience, mentorship, and career development opportunities? The Mastercard Foundation Associates Program is offering a 12-month paid internship for young people across East Africa.

What You'll Gain:
πŸ”ΉHands-on professional experience
πŸ”ΉMentorship and career support
πŸ”ΉLeadership and employability skills development
πŸ”ΉProfessional networking opportunities
πŸ”ΉPathways to employment or entrepreneurship

Who Can Apply?
πŸ”ΈRecent graduates with 0–2 years of experience
πŸ”ΈMastercard Foundation Scholars Program alumni
πŸ”ΈAlumni of Mastercard Foundation programs
πŸ”ΈYoung people aged 18–35
πŸ”ΈApplicants from Ethiopia, Kenya, Uganda, Rwanda, Tanzania, South Sudan, & Burundi

πŸ“…Durations: 12 Months

πŸ”—Apply: https://bit.ly/sclrs26

"If this isn't for you, please share it with others who might be interested."πŸ™

Follow usπŸ‘‡for more opportunities
@opportunity_alerts
❀1
Simret.exe
#DAY3 of the project Yesterday what I did was that cleaning and organising the complaint letters. So the next part is teaching the AI how to read and remember them.It is going to be implementing text chunking , choosing an embedding model and also generating…
Today’s work takes a lot of my energy 🀧🀧🀧

I taught AI to understand complaints not just read them.I took 12,000 real customer complaints and converted them into numbers using a model called "all-MiniLM-L6-v2." Each complaint chunk becomes 384 numbers that capture its meaning. Similar complaints produce similar numbers so the AI can find relevant ones even when the exact words don't match.

πŸ”œ Next: step connecting this to a language model so it can actually answer questions like "Why are customers unhappy with Credit Cards?" using real complaint evidence.

#RAG #projectupdate #DAY3

Good night 😴 πŸ₯± fams
πŸ”₯4πŸ‘1