クエリ書き換えとHyDE

def transform_query(raw, history):
    # Resolve references, expand, decompose, or hypothesize
    # BEFORE embedding and retrieving.
    return rewrite(raw, history)

def rewrite_query(raw):
    prompt = (
        'Rewrite the user question into a clear, standalone search '
        'query optimized for document retrieval. Keep key entities.\n'
        'Question: ' + raw
    )
    return llm(prompt, temperature=0).strip()

def condense(history, follow_up):
    prompt = (
        'Given the conversation, rewrite the follow-up as a standalone '
        'question with all references resolved.\nConversation:\n' +
        render(history) + '\nFollow-up: ' + follow_up
    )
    return llm(prompt, temperature=0).strip()

def expand(query, n=3):
    prompt = (
        'List ' + str(n) + ' alternative phrasings of this query using '
        'synonyms and domain terms, one per line.\n' + query
    )
    variants = parse_lines(llm(prompt, temperature=0.5))
    return [query] + variants

def multi_query(raw, n=4):
    queries = expand(raw, n)
    rankings = [dense_retrieve(q, 30) for q in queries]
    fused = rrf(*rankings)
    return dedup(fused)

def decompose_and_retrieve(question):
    subs = parse_lines(llm(
        'Break this into independent sub-questions, one per line.\n' +
        question, temperature=0))
    evidence = {s: rerank(s, dense_retrieve(s, 30))[:3] for s in subs}
    return evidence  # generator synthesizes the final answer

def hyde(query):
    hypo = llm(
        'Write a short passage that would answer this question, as if '
        'from a reference document.\nQuestion: ' + query,
        temperature=0.3)
    return dense_retrieve_by_vector(embed(hypo), k=30)  # embed the answer

# Robustness: average several hypothetical docs to reduce variance
def hyde_avg(query, n=3):
    vecs = [embed(llm(HYDE_PROMPT + query, temperature=0.5))
            for _ in range(n)]
    centroid = sum(vecs) / n
    return dense_retrieve_by_vector(centroid, 30)

def hyde_hybrid(query):
    a = dense_retrieve_by_vector(embed(hyde_doc(query)), 30)
    b = dense_retrieve(query, 30)          # raw-query fallback
    return dedup(rrf(a, b))                 # robust to bad hypotheticals

def route_transform(query, history, qtype):
    q = condense(history, query) if history else query
    if qtype == 'multi_hop': return decompose_and_retrieve(q)
    if qtype == 'mismatch':  return hyde_hybrid(q)
    if qtype == 'vocab_gap': return multi_query(q)
    return dense_retrieve(q, 30)

def eval_transform(name, fn, eval_set):
    return {
        'recall@10': recall_at_k(eval_set, retriever=fn, k=10),
        'answer_acc': answer_accuracy(eval_set, retriever=fn),
        'extra_latency_ms': transform_latency(fn),
    }