AI Micro-Internship · ~240 min · builder
Chat with your documents (build a mini RAG app)
RAG — retrieval-augmented generation — is in nearly every AI job description this year. Build an app that answers questions from 3+ real documents with citations, and prove it refuses questions the documents can’t answer.
Steps
- 01Pick 3+ real documents you care about (syllabus PDFs, college prospectus, NCERT chapters, game rules).
- 02Build a doc-Q&A app: code it with AI help (LangChain/LlamaIndex or plain embeddings), or use Flowise/Langflow — but you must wire it yourself, not just upload to NotebookLM.
- 03Make answers cite which document/section they came from.
- 04Test with 6 questions: 4 answerable from the docs, 2 traps that aren’t. Push the code to a public repo.
Tools: An AI coding assistant, A free LLM API or Flowise/Langflow, GitHub
Your submission
Submit your docs description, the public repo, a screenshot of it running, and the 6 test transcripts (including trap behaviour).