Our project is a Research Paper Answer Bot based on Retrieval-Augmented Generation. Users can upload research papers, which are extracted page by page, divided into chunks, converted into embeddings, and stored in ChromaDB. When a user asks a question, the question is converted into an embedding and relevant chunks are retrieved using similarity, MMR, or hybrid retrieval. These chunks are passed as context to the language model, which generates a grounded answer. The system also provides the paper and page information so the answer can be verified.
Built With
- chromadb
- rag
Log in or sign up for Devpost to join the conversation.