Posted 1 year ago.

I started experimenting with LLMs last year, in an attempt to create a tool that generated subject lines for emails based on email content.

Started with a basic wrapper around OpenAI. Graduated further into understanding the ecosystem of tools available, experimenting with HuggingFace transformers, further into self-hosting LLMs like Bert, Roberta, NLLB, for some NLP experiments, training and fine-tuning these models, Langchain, StreamLit, diving a little bit into Pinecone.

Built this last weekend - - an interface to an LLM that does a retrieval augmented generation leveraging my kid's school text books. Initially started with 6th grade books for him, but later extended it to all textbooks that I could find online, and built a basic MaterialUI-based UI to allow him to interact with the model.

I was pleasantly surprised by the output and it seems to be able to do its job so far, and has helped him with 3 sessions of homework so far.

Give it a spin and see if it works for you!



image 22image 23




Thanks Tanay for hosting this and sharing it, Would you share some details around the tech stack that you used? From your blog post, it seems you might not be using OpenAI. So curious about the stack. Thanks!


I am interested in building a commercial version of similar eco system for class 11th and 12th students for their competative exam like JEE and NEET .feel free to WhatsApp me on 9900502685. if you have interest in the same .we can build solution together .


Im not gonna ask for the scode but im curious to know how it performs on math as its non trivial (except if using openani api)



I have startup recognized company and we are into AI and I would like to collaborate with you. It interested please get in touch with me at [email protected]

Best wishes

Add new comment

Submitted by tanay on Mon, 06/26/2023 - 08:59