I developed an MVP of

I developed an MVP of a RAG application for querying PDF documents.

The flow is simple: the user uploads a PDF, the system extracts and splits the text into chunks, generates embeddings, stores them in Chroma, and when a question is asked, retrieves the most relevant information so the AI can respond with context.

For this project, I used React, Node.js, Express, LangChain, Gemini, and Chroma Cloud.

The main goal was to better understand concepts such as chunking, embeddings, vector search, and the integration of AI models with vector databases. This is a first version, but it serves as a foundation for more advanced RAG applications in the future.