AT-AI21 · Generative AI
Question Answering from PDFs
Upload PDFs and ask questions; answers come from the documents with page references.
- Suits
- Sem 5–8
- Branches
- CSE, ISE, AIML
- Type
- Software
How it works
The uploaded PDFs are split into small passages and each passage is converted into a vector that captures its meaning, stored in a vector database. When you ask a question, the most relevant passages are retrieved and given to a language model, which writes the answer using only those passages. The page numbers of the sources are shown with the answer.
What it does
- Document search
- Cited answers
- Chat page
Built with
Python, LLM, vector store
What you get
- Working software with full source code
- Steps to install and run it on your laptop
- Rough report and explanation of the working
- Live demo on video call before the final payment
Good to know
- Features are as listed here. Anything extra is quoted separately.
- Runs on a normal laptop unless we tell you otherwise.
- Full reports and PPTs are not included.
Similar projects
- AT-CS17AI Study Assistant from Your Own NotesUpload notes or the syllabus and a chatbot answers only from them.
- AT-CS18AI Mock Interview PlatformAsks interview questions by voice, listens to the answers and gives a score with feedback.
- AT-CS19Multi-Agent AI Report WriterSeparate AI agents research, write and review a report on a given topic.
- AT-CS20AI Legal Document SimplifierExplains agreements and notices in simple language and marks risky clauses.