立法院質詢語意+關鍵字檢索
tw_search_ly_interpellations
台灣專屬MIT
**關鍵字 / Keywords**: 立委質詢 立法院 質詢紀錄 legislature interpellation question parliamentary Taiwan LY
立法院質詢語意檢索 (~12k 質詢, 事由+說明合併向量).
Args:
query: 自然語言 (e.g. "長照經費", "兒少安置")
legislator_contains: 質詢委員字串 (e.g. "王婉諭")
term: 屆別
session: 會期
limit: top-K (1..100)
Returns:
{n_corpus, n_returned, query, hits: [{屆, 質詢委員, 質詢編號,
刊登日期, 事由, 說明, similarity}, ...]}輸入 schema
{
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"legislator_contains": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Legislator Contains"
},
"term": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Term"
},
"session": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Session"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
},
"mode": {
"default": "hybrid",
"title": "Mode",
"type": "string"
}
},
"required": [
"query"
],
"title": "tw_search_ly_interpellationsArguments",
"type": "object"
}呼叫方式
配置好 Twinkle Hub 的 MCP client 後,agent 會看到 tw_search_ly_interpellations。直接讓它呼叫即可,例如:
# Ask Claude / any MCP client: 請用 tw_search_ly_interpellations 處理 "…"。 # It will call: tw_search_ly_interpellations(input="…")
尚未設定 Client?
Claude Desktop 約 3 分鐘即可完成設定 — 下載 .mcpb 檔案並雙擊即可,或參閱文件中的各 Client 安裝步驟。
查看使用者設定文件