def run_pipeline_test(
    question: str,
    line_df_in: pd.DataFrame,
    page_df_in: pd.DataFrame,
    page_df_emb_in: pd.DataFrame,
    top_k: int = 3,
    client=client,
) -> dict:
    """Run both retrievers + generation on one question; return a summary dict."""
    parsed_q = get_keywords_from_question(question, client=client)
    retrieved_emb_df, _ = retrieve_pages_by_similarity(
        page_df_emb_in, line_df_in, question, top_k=top_k, client=client,
    )
    retrieved_kw_df, filtered_lines_kw = retrieve_pages(
        page_df_in, line_df_in, parsed_q.keywords, top_k=top_k,
    )
    # If keyword retrieval finds nothing, fall back to the whole doc so generation
    # still runs (small PDFs only: would not scale to a real corpus).
    lines_for_generation = (
        filtered_lines_kw if len(filtered_lines_kw) > 0 else line_df_in
    )
    answer = llm_answer_with_evidence(
        question, lines_for_generation, client=client,
    )
    return {
        "question": question,
        "keywords": parsed_q.keywords,
        "emb_top3": retrieved_emb_df["page_num"].tolist(),
        "kw_top3": (
            retrieved_kw_df["page_num"].tolist()
            if len(retrieved_kw_df) > 0 else "(no kw match)"
        ),
        "answer_excerpt": (answer.answer[:80] + ("..." if len(answer.answer) > 80 else "")),
        "cite_page": answer.start_page_num,
    }