Doc QA

Answer questions grounded in a set of documents (RAG), with citations.

Ninadnj Updated

File contents

doc_qa

Retrieval-augmented question answering over a folder of documents.

How it works

  1. Load .txt / .md / .pdf files from the given path.
  2. Chunk them with overlap and rank chunks against the question (BM25).
  3. Answer only from the retrieved passages and cite the source file for each claim. If the answer isn't in the documents, say so.

Guidance for the model

  • Ground every statement in the retrieved context; never invent facts.
  • Keep answers concise and include the [source] for each fact.
  • If the context does not contain the answer, reply that it is not in the documents.

Ninadnj/mcp-skills-kit/tree/main/skills/doc_qa commit a35035f4ca

Frequently asked questions

npx skillmds@latest add ninadnj/doc-qa