Use cases¶
Interactive evidence review¶
Use the Streamlit UI when you want to review evidence in a browser:
evidence-fetcher-ui
Search from the sidebar, mark results as more, less, irrelevant, or
unsure, then rerank the current list or expand the search with a
feedback-refined query.
See Streamlit UI sample for a step-by-step walkthrough of the sample app.
Text-based feedback workflow¶
Use interactive CLI mode when you want the same feedback loop in a terminal:
evidence-fetcher "retrieval augmented generation evaluation" --interactive
Interactive mode performs the initial search, then lets you mark displayed results, request a local rerank, or explicitly expand retrieval with a refined query.
Programmatic retrieval¶
Use the Python API when you want normalized evidence in another application or experiment:
from evidence_fetcher import fetch_evidence
evidence = fetch_evidence("retrieval augmented generation evaluation")
Review caution¶
Interactive Information Retrieval is useful for condensing large search result sets into a smaller set of promising evidence. The same feedback loop can also drift into cherry-picking if users only reward sources that support an expected answer.
Use reranking and expansion as prioritization aids, not as proof that the top results are the whole story. For questions where balance matters, keep checking contrary, ambiguous, and low-confidence evidence before drawing a conclusion.