feat: H-WIKI-SEARCH — WikiSearchProvider created and registered in wiki/plugin.py on_activate, FTS + vector search on wiki_articles

2026-08-20 22:02:16 +02:00
parent 864824d8cd
commit 883e22e9b1
2 changed files with 172 additions and 1 deletions
@@ -0,0 +1,156 @@
+"""Wiki search provider — searches wiki articles via FTS and vector."""
+
+from __future__ import annotations
+
+import logging
+import uuid
+from typing import Any
+
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.plugins.builtins.unified_search.base_provider import BaseSearchProvider
+
+logger = logging.getLogger(__name__)
+
+
+class WikiSearchProvider(BaseSearchProvider):
+    """Search provider for WikiArticle entities."""
+
+    entity_type = "wiki_article"
+
+    async def _search_fts_filtered(
+        self,
+        db: AsyncSession,
+        tsquery: str,
+        tenant_id: uuid.UUID,
+        limit: int,
+        visible_ids: set[uuid.UUID] | None,
+    ) -> list[dict[str, Any]]:
+        """Full-text search on wiki_articles title + content."""
+        if visible_ids is not None:
+            sql = text(
+                """
+                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
+                       a.category_id, a.tenant_id,
+                       ts_rank(
+                           to_tsvector('pg_catalog.german',
+                               coalesce(a.title, '') || ' ' ||
+                               coalesce(a.content, '') || ' ' ||
+                               coalesce(a.summary, '')
+                           ),
+                           to_tsquery('pg_catalog.german', :q)
+                       ) AS rank
+                FROM wiki_articles a
+                WHERE a.tenant_id = :tid
+                  AND a.deleted_at IS NULL
+                  AND a.status = 'published'
+                  AND to_tsvector('pg_catalog.german',
+                      coalesce(a.title, '') || ' ' ||
+                      coalesce(a.content, '') || ' ' ||
+                      coalesce(a.summary, '')
+                  ) @@ to_tsquery('pg_catalog.german', :q)
+                  AND a.id = ANY(:visible_ids)
+                ORDER BY rank DESC
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {"q": tsquery, "tid": tenant_id, "lim": limit, "visible_ids": list(visible_ids)},
+            )
+        else:
+            sql = text(
+                """
+                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
+                       a.category_id, a.tenant_id,
+                       ts_rank(
+                           to_tsvector('pg_catalog.german',
+                               coalesce(a.title, '') || ' ' ||
+                               coalesce(a.content, '') || ' ' ||
+                               coalesce(a.summary, '')
+                           ),
+                           to_tsquery('pg_catalog.german', :q)
+                       ) AS rank
+                FROM wiki_articles a
+                WHERE a.tenant_id = :tid
+                  AND a.deleted_at IS NULL
+                  AND a.status = 'published'
+                  AND to_tsvector('pg_catalog.german',
+                      coalesce(a.title, '') || ' ' ||
+                      coalesce(a.content, '') || ' ' ||
+                      coalesce(a.summary, '')
+                  ) @@ to_tsquery('pg_catalog.german', :q)
+                ORDER BY rank DESC
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {"q": tsquery, "tid": tenant_id, "lim": limit},
+            )
+        rows = result.mappings().all()
+        return [dict(r) for r in rows]
+
+    async def _search_vector_filtered(
+        self,
+        db: AsyncSession,
+        embedding: list[float],
+        tenant_id: uuid.UUID,
+        limit: int,
+        visible_ids: set[uuid.UUID] | None,
+    ) -> list[dict[str, Any]]:
+        """Semantic vector search on wiki_articles.embedding."""
+        emb_str = f"[{','.join(str(x) for x in embedding)}]"
+        if visible_ids is not None:
+            sql = text(
+                """
+                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
+                       a.category_id, a.tenant_id,
+                       1 - (a.embedding <=> cast(:emb AS vector)) AS similarity
+                FROM wiki_articles a
+                WHERE a.tenant_id = :tid
+                  AND a.deleted_at IS NULL
+                  AND a.status = 'published'
+                  AND a.embedding IS NOT NULL
+                  AND a.id = ANY(:visible_ids)
+                ORDER BY a.embedding <=> cast(:emb AS vector)
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {"emb": emb_str, "tid": tenant_id, "lim": limit, "visible_ids": list(visible_ids)},
+            )
+        else:
+            sql = text(
+                """
+                SELECT a.id, a.title, a.slug, a.summary, a.content, a.status,
+                       a.category_id, a.tenant_id,
+                       1 - (a.embedding <=> cast(:emb AS vector)) AS similarity
+                FROM wiki_articles a
+                WHERE a.tenant_id = :tid
+                  AND a.deleted_at IS NULL
+                  AND a.status = 'published'
+                  AND a.embedding IS NOT NULL
+                ORDER BY a.embedding <=> cast(:emb AS vector)
+                LIMIT :lim
+                """
+            )
+            result = await db.execute(
+                sql,
+                {"emb": emb_str, "tid": tenant_id, "lim": limit},
+            )
+        rows = result.mappings().all()
+        return [dict(r) for r in rows]
+
+    def to_search_result(self, entity: dict) -> dict[str, Any]:
+        """Convert a wiki article dict to a search result."""
+        return {
+            "entity_type": "wiki_article",
+            "entity_id": str(entity.get("id", "")),
+            "title": entity.get("title", ""),
+            "description": entity.get("summary", "") or (entity.get("content", "")[:200] if entity.get("content") else ""),
+            "url": f"/wiki?article={entity.get('slug', '')}",
+            "tenant_id": str(entity.get("tenant_id", "")),
+        }
@@ -1,8 +1,11 @@
-"""Wiki plugin — knowledge articles, categories, versioning (H-WIKI, H-VER)."""
+"""Wiki plugin — knowledge articles, categories, versioning (H-WIKI, H-VER).""
 from __future__ import annotations
+import logging
 from app.plugins.base import BasePlugin
 from app.plugins.manifest import FrontendMenuItem, FrontendPageRoute, PluginManifest, PluginRouteDef

+logger = logging.getLogger(__name__)
+
 class WikiPlugin(BasePlugin):
    manifest = PluginManifest(
        name="wiki",
@@ -17,3 +20,15 @@ class WikiPlugin(BasePlugin):
        menu_items=[FrontendMenuItem(label_key="wiki.menu.wiki", label="Wiki", path="/wiki", icon="BookOpen")],
        page_routes=[FrontendPageRoute(path="/wiki", component="@/pages/Wiki")],
    )
+
+    async def on_activate(self, db, service_container, event_bus) -> None:
+        """Register wiki search provider on activation."""
+        await super().on_activate(db, service_container, event_bus)
+        try:
+            from app.plugins.builtins.unified_search.provider_registry import get_search_registry
+            from app.plugins.builtins.unified_search.providers.wiki_provider import WikiSearchProvider
+            registry = get_search_registry()
+            registry.register(WikiSearchProvider())
+            logger.info("Registered WikiSearchProvider")
+        except Exception:
+            logger.exception("Failed to register WikiSearchProvider")