Forwarded from Yohannes Haile (Yohannes Haile)
βThe undocumented life is not worth livingβ
β Socrates, Influencer
β Socrates, Influencer
π2
This shows mom's resilience has no limits.β€οΈβ€οΈ still she is young but she achieve her dreams
β€5
π«‘Project update on #DAY2
I have been working on :
Loading & explored 9.6 million real CFPB customer complaintsπ€§π€§π€§
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 β
Next up: building the embedding pipeline to turn these complaints into searchable AI vectors! π₯
It seems easy but it is not.It needs careful consideration of the data.
I have been working on :
Loading & explored 9.6 million real CFPB customer complaintsπ€§π€§π€§
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 β
Next up: building the embedding pipeline to turn these complaints into searchable AI vectors! π₯
It seems easy but it is not.It needs careful consideration of the data.
β€4
Good night famsπ€π«‘
Don't forget to restβΊοΈπ
Let us say this word of the night βΊοΈβΊοΈπ
https://t.me/Luna_moonmam/2793
Don't forget to restβΊοΈπ
Let us say this word of the night βΊοΈβΊοΈπ
https://t.me/Luna_moonmam/2793
Telegram
Luna's pathwayπ€
For the people who struggle alone.
For the people who carry responsibilities nobody sees.
For the people who take the blame to protect others.
For the people who stay silent while their efforts go unnoticed.
For the people who hold teams together whileβ¦
For the people who carry responsibilities nobody sees.
For the people who take the blame to protect others.
For the people who stay silent while their efforts go unnoticed.
For the people who hold teams together whileβ¦
β€1
Simret.exe
π«‘Project update on #DAY2 I have been working on : Loading & explored 9.6 million real CFPB customer complaintsπ€§π€§π€§ Analyzed complaint distribution across 21 product categories Built a text cleaning pipeline (boilerplate removal, normalization) Set up CI/CDβ¦
#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.
βοΈβοΈtrust the process
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.
βοΈβοΈtrust the process
β‘3
This media is not supported in your browser
VIEW IN TELEGRAM
I have no boundaries how much I love pheven_teklayβ€οΈππ her voice her thoughts βΊοΈπ€
This one I found on my gallery like a remainder βΊοΈ
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. πΆββοΈπ«
This one I found on my gallery like a remainder βΊοΈ
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. πΆββοΈπ«
β€3
Forwarded from Opportunity Alertsπ’
#Opportunity_Alertsπ£
πPaid Internship Opportunity: Join Mastercard Foundation Associates Program 2026 for Young Africansπ
β¨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:
πΉHands-on professional experience
πΉMentorship and career support
πΉLeadership and employability skills development
πΉProfessional networking opportunities
πΉPathways to employment or entrepreneurship
Who Can Apply?
πΈRecent graduates with 0β2 years of experience
πΈMastercard Foundation Scholars Program alumni
πΈAlumni of Mastercard Foundation programs
πΈYoung people aged 18β35
πΈApplicants from Ethiopia, Kenya, Uganda, Rwanda, Tanzania, South Sudan, & Burundi
π Durations: 12 Months
πApply: https://bit.ly/sclrs26
"If this isn't for you, please share it with others who might be interested."π
Follow usπfor more opportunities
@opportunity_alerts
πPaid Internship Opportunity: Join Mastercard Foundation Associates Program 2026 for Young Africansπ
β¨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:
πΉHands-on professional experience
πΉMentorship and career support
πΉLeadership and employability skills development
πΉProfessional networking opportunities
πΉPathways to employment or entrepreneurship
Who Can Apply?
πΈRecent graduates with 0β2 years of experience
πΈMastercard Foundation Scholars Program alumni
πΈAlumni of Mastercard Foundation programs
πΈYoung people aged 18β35
πΈApplicants from Ethiopia, Kenya, Uganda, Rwanda, Tanzania, South Sudan, & Burundi
π Durations: 12 Months
πApply: https://bit.ly/sclrs26
Follow usπfor more opportunities
@opportunity_alerts
β€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 generatingβ¦
Todayβs work takes a lot of my energy π€§π€§π€§
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.
π 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 π΄ π₯± fams
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.
π 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 π΄ π₯± fams
π₯4π1
Forwarded from BΟ
ΙΎΤΞ±Ι³-Ops (BΟ
ΙΎΤΞ±Ι³ | Ψ¨Ψ±ΩΨ§Ω :))
Some people wait for opportunities. Bosses create them :)
β€1π1
#DAY4 of the project
Todayβs task am doing is that still not finished π yetπππ€§ but it is RAG pipeline and prompt engineer it is for guiding the LLM in easy way.
βοΈπ€grind until you finished
Todayβs task am doing is that still not finished π yetπππ€§ but it is RAG pipeline and prompt engineer it is for guiding the LLM in easy way.
βοΈπ€grind until you finished
π₯3
β³ The waiting time building an AI databaseπββοΈ
Right now my pc is quietly doing something cool in the background.π€§π€§ππ
It is indexing 1.37 million π€§complaint chunks into a vector database so RAG chatbot can search through nearly half a million real customer complaints in seconds.
This is a one time process. Once it finishes every search takes less than a second.π€
Current progress: 40% and counting.
Sometimes building something great just requires patience. βοΈ
#DAY4
Right now my pc is quietly doing something cool in the background.π€§π€§ππ
It is indexing 1.37 million π€§complaint chunks into a vector database so RAG chatbot can search through nearly half a million real customer complaints in seconds.
This is a one time process. Once it finishes every search takes less than a second.π€
Current progress: 40% and counting.
Sometimes building something great just requires patience. βοΈ
#DAY4
π₯6π1
Simret.exe
β³ The waiting time building an AI databaseπββοΈ Right now my pc is quietly doing something cool in the background.π€§π€§ππ It is indexing 1.37 million π€§complaint chunks into a vector database so RAG chatbot can search through nearly half a million real customerβ¦
Let my pc do the job
Let us rest good night π΄ π₯± π famsπ€
Let us rest good night π΄ π₯± π famsπ€
π1
Forwarded from The Opcode
Hey Opicoders
Big news. Today, someone from the community introduced Alphabet to founders and teams from several AI startups during an event. No invite. No setup from me. Just a person who believed in the project enough to talk about it in a room full of people building real things. That alone is something I did not expect this week.
And it gets better. I also got selected to represent Alphabet Programming Language at the Tesfa AI startup showcase. Real stage. Real investors in the room. Real partners. Real VIP guests whose names I cannot even share yet. On top of that, I will be pitching to Tesfa AI and the AAU Startup Center, which could open even more doors for the project.
If you have followed this channel for a while, you already know what Alphabet is. For those who do not, it is the project I have been building for years. A real compiled programming language. Not a toy. Not a translation layer. A full language with its own bytecode VM written in C++, its own compiler, its own package manager, its own browser IDE. And it works in 5 natural languages. English. Amharic. Spanish. French. German. Same code. Same output. Only the keywords change. People can build software in their own language.
I am not going to lie. I am nervous. Public speaking is one thing. Public speaking about a project you have poured your whole life into is another thing entirely. But I would rather feel this weight than feel nothing. I would rather be nervous about a real stage than comfortable about nothing happening. That is the bet I made when I started this thing.
So here is what I need from you, Opicoders. Moral support. Genuine engagement. When I post the pitch materials, when I share the demo, when I tell you the showcase dates, I need you to show up. Comment. Share. Send the link to one person who might care. That is how this works. Not from one person screaming into a channel. From a community that decides to lift one of its own.
I am excited to see more people start using Alphabet and experience how it can make coding easier by allowing them to build software in their own language. This is just the beginning. Stay tuned. More updates coming soon.
Thank you for being here.
Big news. Today, someone from the community introduced Alphabet to founders and teams from several AI startups during an event. No invite. No setup from me. Just a person who believed in the project enough to talk about it in a room full of people building real things. That alone is something I did not expect this week.
And it gets better. I also got selected to represent Alphabet Programming Language at the Tesfa AI startup showcase. Real stage. Real investors in the room. Real partners. Real VIP guests whose names I cannot even share yet. On top of that, I will be pitching to Tesfa AI and the AAU Startup Center, which could open even more doors for the project.
If you have followed this channel for a while, you already know what Alphabet is. For those who do not, it is the project I have been building for years. A real compiled programming language. Not a toy. Not a translation layer. A full language with its own bytecode VM written in C++, its own compiler, its own package manager, its own browser IDE. And it works in 5 natural languages. English. Amharic. Spanish. French. German. Same code. Same output. Only the keywords change. People can build software in their own language.
I am not going to lie. I am nervous. Public speaking is one thing. Public speaking about a project you have poured your whole life into is another thing entirely. But I would rather feel this weight than feel nothing. I would rather be nervous about a real stage than comfortable about nothing happening. That is the bet I made when I started this thing.
So here is what I need from you, Opicoders. Moral support. Genuine engagement. When I post the pitch materials, when I share the demo, when I tell you the showcase dates, I need you to show up. Comment. Share. Send the link to one person who might care. That is how this works. Not from one person screaming into a channel. From a community that decides to lift one of its own.
I am excited to see more people start using Alphabet and experience how it can make coding easier by allowing them to build software in their own language. This is just the beginning. Stay tuned. More updates coming soon.
Thank you for being here.
π₯5π1
If anyone got interested check this out .And send us the link for registration πππ on the comment belowππ