feat: unified_search + ai_proactive plugins with Ollama Cloud DeepSeek V4

- unified_search: Hybride Suche (PostgreSQL FTS + pgvector + RRF Fusion) - 5 Search Providers (Contact, Company, Mail, File, Event) - KI Query Understanding (Fuzzy, Facetten via LiteLLM) - DMS Text-Extraction (PDF, DOCX, XLSX, PPTX) - Embedding Pipeline (ollama/nomic-embed-text, 768 Dim) - Background Jobs für Indexierung - Plugin-basierte Provider Registry - ai_proactive: Proaktiver KI-Agent - Context-Tracking (Frontend → Backend → Event Bus) - Proactive Engine mit LLM Suggestion-Generierung - SSE Real-time Push an Frontend - 6 AI Tools für Tool Registry - Rate-Limiting + User Settings - Deep Analysis Background Jobs - Frontend Integration: - useAIContext Hook, SuggestionSidebar, SuggestionBadge - ProactiveAISettings Page, Search API Client - Globale Suche auf neue API umgestellt - Tests: test_unified_search.py + test_ai_proactive.py (alle bestanden) - Config: Ollama Cloud DeepSeek V4 als Default, konfigurierbar - Dependencies: PyMuPDF, python-docx, python-pptx, pgvector - Bugfixes: notification type_key length, migration IF NOT EXISTS
2026-07-18 11:21:51 +02:00
parent 4c9295de21
commit 8cebb4f4e9
52 changed files with 6493 additions and 41 deletions
@@ -0,0 +1,111 @@
+"""DMS File search provider."""
+
+from __future__ import annotations
+
+import logging
+import uuid
+from typing import Any
+
+from sqlalchemy import text
+from sqlalchemy.ext.asyncio import AsyncSession
+
+logger = logging.getLogger(__name__)
+
+
+class FileSearchProvider:
+    """Search provider for DMS File entities."""
+
+    entity_type = "file"
+
+    async def search_fts(
+        self,
+        db: AsyncSession,
+        tsquery: str,
+        tenant_id: uuid.UUID,
+        limit: int,
+    ) -> list[dict[str, Any]]:
+        """Full-text search on files.content_tsv."""
+        sql = text(
+            """
+            SELECT f.*, ts_rank(f.content_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
+            FROM files f
+            WHERE f.tenant_id = :tid
+              AND f.deleted_at IS NULL
+              AND f.content_tsv @@ 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(
+        self,
+        db: AsyncSession,
+        embedding: list[float],
+        tenant_id: uuid.UUID,
+        limit: int,
+    ) -> list[dict[str, Any]]:
+        """Semantic search on files.embedding."""
+        sql = text(
+            """
+            SELECT f.*, 1 - (f.embedding <=> cast(:emb AS vector)) AS score
+            FROM files f
+            WHERE f.tenant_id = :tid
+              AND f.deleted_at IS NULL
+              AND f.embedding IS NOT NULL
+            ORDER BY f.embedding <=> cast(:emb AS vector)
+            LIMIT :lim
+            """
+        )
+        result = await db.execute(
+            sql,
+            {"emb": str(embedding), "tid": tenant_id, "lim": limit},
+        )
+        rows = result.mappings().all()
+        return [dict(r) for r in rows]
+
+    async def get_embedding_text(
+        self,
+        db: AsyncSession,
+        entity_id: uuid.UUID,
+        tenant_id: uuid.UUID,
+    ) -> str:
+        """Get text for embedding generation."""
+        sql = text(
+            """
+            SELECT name, content_text
+            FROM files
+            WHERE id = :eid AND tenant_id = :tid
+            """
+        )
+        result = await db.execute(sql, {"eid": entity_id, "tid": tenant_id})
+        row = result.mappings().first()
+        if not row:
+            return ""
+        name = row.get("name", "") or ""
+        content = row.get("content_text", "") or ""
+        return f"{name} {content[:5000]}"
+
+    def to_search_result(self, entity: object) -> dict[str, Any]:
+        """Convert file to search result dict."""
+        if isinstance(entity, dict):
+            name = entity.get("name", "")
+            content = entity.get("content_text", "") or ""
+            entity_id = str(entity.get("id", ""))
+        else:
+            name = getattr(entity, "name", "")
+            content = getattr(entity, "content_text", "") or ""
+            entity_id = str(getattr(entity, "id", ""))
+        return {
+            "entity_type": self.entity_type,
+            "entity_id": entity_id,
+            "title": name,
+            "snippet": content[:200],
+            "score": 0.0,
+            "data": {},
+        }