🚀 My First Dev.to Post + My First RAG Project: InsightFetch

Hey everyone! 👋

This is my very first post on Dev.to, and I'm excited to share my first Retrieval-Augmented Generation (RAG) project built using LangChain.

Introducing InsightFetch

InsightFetch is a simple web application that lets you learn from any webpage by asking questions in natural language.

Just provide one or more URLs, and the app will:

*Extract the content from the webpages

*Split the text into chunks

*Generate embeddings using Hugging Face

*Store them in a FAISS vector database

*Use LangChain with the Groq API (Llama 3.1 8B Instant) to answer your questions based on the provided content

Tech Stack

• Python


• Streamlit


• LangChain


• Groq (Llama 3.1 8B Instant)


• Hugging Face Embeddings


• FAISS


• Unstructured URL Loader

Try it out

InsightFetch: https://insightfetch.streamlit.app/

I'd love to hear what you think!

This project taught me a lot about how RAG pipelines work—from document loading and chunking to embeddings, vector search, and retrieval-based question answering.

Since I'm still learning, I'm sure there are many things I can improve. If you have any suggestions, best practices, or ideas for new features, I'd really appreciate your feedback. Every suggestion will help me learn and build better projects.

Thank you for taking the time to read my first post. I hope to share more of my learning journey and future projects here!

Happy coding!