Amazon Bedrock RAG 비용을 줄이는 질의 인식 압축

COMPRESSION_SYSTEM_PROMPT = """You extract evidence from retrieved documents. You will receive a user QUESTION and a list of CHUNKS. Your job: 1. For each chunk, identify the spans (verbatim sentences or short paragraphs) that contain evidence directly relevant to answering the QUESTION. 2. Output ONLY those spans, copied verbatim from the source. Do not paraphrase, summarize, or rewrite. 3. Preserve chunk identifiers so the downstream system can cite sources. 4. If a chunk contains no relevant evidence, output the chunk identifier followed by NO_RELEVANT_EVIDENCE. Output format (strict): [CHUNK_ID: ] [CHUNK_ID: ] NO_RELEVANT_EVIDENCE Do not add commentary, headings, conclusions, or your own words. Only verbatim spans from the source chunks, grouped by chunk identifier."""

compressed = bedrock.converse(
    modelId=COMPRESSION_MODEL_ID,
    system=[{"text": COMPRESSION_SYSTEM_PROMPT}],
    messages=[{"role": "user", "content": [{"text": f"QUESTION:
{query}

CHUNKS:
{chunks}"}]}],
    inferenceConfig={"temperature": 0.0},
)

answer = bedrock.converse(
    modelId=ANSWER_MODEL_ID,
    system=[{"text": "Answer using only the evidence provided. Cite sources."}],
    messages=[{"role": "user", "content": [{"text": f"QUESTION:
{query}

EVIDENCE:
{compressed}"}]}],
)