Loading article…
RAG for documentary archives: how retrieval-augmented generation works
6 min readUpdated May 27, 2026
Questions
TRY IT IN PAPERCUTS
RAG chat over your interview archive in PaperCuts
Related reading
Semantic search explained: why keyword search fails for interview archives
Embedding-based semantic search finds passages by meaning rather than by matching words. Here is what an embedding is in plain terms, how the search works, and where it still misses things.
Grounded LLM generation: what it means and where it still goes wrong
A grounded language model is constrained to produce output traceable to specific source chunks. Here is what grounding means in practice, why it produces usable output, and where the model can still hallucinate.
Character profiles in documentary: what to include and when to write them
A documentary character profile gives directors a view of who they have across all interview hours. Here is what to include, what to leave out, and when in the production timeline it pays to write one.