colcaroliandClaude Opus 5
97568ba90e
Vectors from two different embedding models are not comparable — Titan v2 has 1024 dimensions where nomic-embed-text has 768 — and _cosine_similarity zips them, so a mismatch produced quietly meaningless scores rather than an error. Nothing forced a re-embed either: sync_local_kb only looked at the content hash, so switching models left every cached vector in place. local_knowledge_docs now records the model each vector came from, and a row is re-embedded when its content hash OR its model differs. Saving a new LOCAL_KB_EMBEDDING_MODEL from the settings panel starts a background pass over every file; the knowledge base panel also has a button for it. While that pass runs, the per-request sync steps aside so no file is embedded twice. The panel now shows what the embedding model is doing: model name, vector size, how many files are embedded with the current model, how many are still on an older one, a progress bar while a pass runs, and the last error. A "接続テスト" button embeds one short string so a broken or unreachable model can be told apart from one that is merely slow to warm up. Also read TAVILY_API_KEY from os.environ at call time. It was imported as a config constant, which is evaluated before load_into_env() runs, so a key saved from the settings panel was stored but never used — not even after a restart. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
68 lines
2.3 KiB
Python
68 lines
2.3 KiB
Python
import logging
|
|
import os
|
|
|
|
import httpx
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
TAVILY_SEARCH_URL = "https://api.tavily.com/search"
|
|
|
|
|
|
def _api_key() -> str | None:
|
|
"""GUIの設定画面から実行時に変更できるよう、起動時定数ではなく都度 os.environ を見に行く。
|
|
|
|
app.core.config の定数は import 時に評価されるため、DBに保存した値を
|
|
settings_store.load_into_env() が os.environ に入れても反映されない。
|
|
"""
|
|
return os.environ.get("TAVILY_API_KEY") or None
|
|
|
|
|
|
WEB_SEARCH_TOOL = {
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"description": "最新情報・事実確認・知らない固有名詞など、自分の知識だけでは答えられない可能性があるときにWebを検索する。"
|
|
"ただし、システムプロンプトに提示されたローカルナレッジベースの資料で回答できる場合は使わないこと。",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {"type": "string", "description": "検索したい内容を表す検索クエリ"},
|
|
},
|
|
"required": ["query"],
|
|
},
|
|
},
|
|
}
|
|
|
|
|
|
async def search_web(query: str, max_results: int = 5) -> list[dict]:
|
|
"""Tavily APIでWeb検索する。結果は [{title, url, content}, ...]。失敗時は空リスト。"""
|
|
api_key = _api_key()
|
|
if not api_key:
|
|
logger.warning("TAVILY_API_KEY is not set; skipping web search")
|
|
return []
|
|
|
|
try:
|
|
async with httpx.AsyncClient(timeout=15.0) as client:
|
|
response = await client.post(
|
|
TAVILY_SEARCH_URL,
|
|
json={
|
|
"api_key": api_key,
|
|
"query": query,
|
|
"max_results": max_results,
|
|
},
|
|
)
|
|
response.raise_for_status()
|
|
data = response.json()
|
|
except Exception:
|
|
logger.exception("Tavily search failed for query=%r", query)
|
|
return []
|
|
|
|
results = []
|
|
for item in data.get("results", []):
|
|
results.append({
|
|
"title": item.get("title") or "",
|
|
"url": item.get("url") or "",
|
|
"content": item.get("content") or "",
|
|
})
|
|
return results
|