I finally finished

Link: https://searifxr.github.io/ResearchBase/

Learn along with me everyone!

I am almost done with the RAG pipeline for ResearchBase.
For ResearchBase to use the AI model, I needed the LLM to be hosted in the cloud as my GPU can’t handle ts shi😭.

But also I learnt really how a RAG pipeline is built and what are all the processes behind it. This is truly project based learning at its peak.

For those who don’t know what a RAG pipeline is

A RAG pipeline is an alternative method some applications use to have AI responses.

Usually, if you use hugging face, transformers and models are installed locally in the CPU. But if you start using it, it will fry your GPU if it’s not good enough.

So alternatively, most applications use a RAG pipeline with an API key to access a model that runs on a server.

Then with a little bit of data indexing, converting that data into vector db*, chunking the top K results, feeding those top K results into the LLM for context, and a bit of prompt engineering, you get a fully fledged response from the AI.

Now you are caught up with me!

The more you know.

*Vector DB: A vector database is a specialized database that stores and indexes data as high-dimensional vectors (arrays of numbers). Instead of using exact keyword matches, it allows AI applications to search for information based on semantic meaning, context, and similarity.

Check out more info on RAG pipelines from Nvidia

Folk

==========================================
It worked.. after AI generated a test file and fixed my dotenv issue 😭

I have been working on this RAG pipeline for so long.

Just wanted to experience how a normal dev was in the BC era (before chat 😭 😭 ). I don’t know why the post is saying that I only have a 1h 50m logged even though on hacktime it says 2h 26m, but I am more than ready to ship this and just get started on another project omg..

I geniunely don’t know if this would run, I haven’t been vibecoding for the past 30 mins, js only using stackoverflow. This is prolly not going to work but if this does, I am the literal goat.

Follow me for more posts about my sanity 😭
Good Night Everyone!

I am trying to get a research internship at universities, but I am not smart enough to understand the research papers over topics like biology and CS 😭 😭 😭

The main psychology behind landing a research internship from cold emailing a professor is to mention their work. Boost their pride by showing you know and have read their work.

But the hardest part is just that… I can’t understand the weird math symbols nor some of the concepts 😭

That’s why I am creating ResearchBase, an application that uses a RAG pipeline + highly specific prompt engineering so that you don’t have to go to Gemini or Chat and have multiple attempts in trying to get the answer you want.

UPDATES===========================

• Created an Electron JS application
• Have an upload feature that only takes in PDFs

Follow along for more updates!