Agent Zero
211242a807
Check Cross-Plugin Imports / check (push) Has been cancelled
B-VEC: Migration 0118 — HNSW-Indizes mit optimierten Parametern (ef_construction=128, m=16) - 5 Tabellen: contacts, mails, files, calendar_entries, tags - config.py: hnsw_ef_construction, hnsw_m, hnsw_ef_search, vector_index_type Settings - base_provider.py + search_engine.py: SET LOCAL hnsw.ef_search vor Vector-Queries B-VEC-IVF: IVFFlat als Alternative dokumentiert (vector_index_type Setting) B-VEC-BATCH: Batch-Embedding verifiziert (generate_embeddings_batch nutzt llm_embed()) B-VEC-TEST: Performance-Tests auf Coolify-Instanz verschoben (benötigt 10k+ Datensätze)
103 lines
3.5 KiB
Python
103 lines
3.5 KiB
Python
"""Base search provider with visibility filter — all search providers should inherit from this.
|
|
|
|
This ensures that search results respect row-level security automatically.
|
|
Plugins that provide search functionality should use this base class.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
import uuid
|
|
from typing import Any
|
|
|
|
from sqlalchemy import text
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
|
|
from app.config import settings
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class BaseSearchProvider:
|
|
"""Base class for search providers with built-in visibility filtering.
|
|
|
|
Subclasses must implement _search_fts_filtered() and _search_vector_filtered().
|
|
The base class handles loading visible IDs and passing them to the subclass.
|
|
"""
|
|
|
|
entity_type: str = "" # Override in subclass
|
|
|
|
async def search_fts(
|
|
self,
|
|
db: AsyncSession,
|
|
tsquery: str,
|
|
tenant_id: uuid.UUID,
|
|
limit: int,
|
|
user_id: uuid.UUID | None = None,
|
|
is_system_admin: bool = False,
|
|
) -> list[dict[str, Any]]:
|
|
"""Full-text search with visibility filter."""
|
|
if is_system_admin or not user_id:
|
|
return await self._search_fts_filtered(db, tsquery, tenant_id, limit, None)
|
|
|
|
visible_ids = await self._get_visible_ids(db, tenant_id, user_id)
|
|
if not visible_ids:
|
|
return []
|
|
return await self._search_fts_filtered(db, tsquery, tenant_id, limit, visible_ids)
|
|
|
|
async def search_vector(
|
|
self,
|
|
db: AsyncSession,
|
|
embedding: list[float],
|
|
tenant_id: uuid.UUID,
|
|
limit: int,
|
|
user_id: uuid.UUID | None = None,
|
|
is_system_admin: bool = False,
|
|
) -> list[dict[str, Any]]:
|
|
"""Semantic vector search with visibility filter."""
|
|
# Set HNSW ef_search parameter for this transaction
|
|
await db.execute(text(f"SET LOCAL hnsw.ef_search = {settings.hnsw_ef_search}"))
|
|
if is_system_admin or not user_id:
|
|
return await self._search_vector_filtered(db, embedding, tenant_id, limit, None)
|
|
|
|
visible_ids = await self._get_visible_ids(db, tenant_id, user_id)
|
|
if not visible_ids:
|
|
return []
|
|
return await self._search_vector_filtered(db, embedding, tenant_id, limit, visible_ids)
|
|
|
|
async def _get_visible_ids(
|
|
self, db: AsyncSession, tenant_id: uuid.UUID, user_id: uuid.UUID
|
|
) -> set[uuid.UUID] | None:
|
|
"""Get visible entity IDs for the user."""
|
|
from app.services.entity_permission_service import get_visible_ids
|
|
visible, _ = await get_visible_ids(db, tenant_id, user_id, self.entity_type)
|
|
return visible if visible else None
|
|
|
|
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]]:
|
|
"""Override: FTS search filtered by visible_ids. If visible_ids is None, no filter."""
|
|
raise NotImplementedError
|
|
|
|
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]]:
|
|
"""Override: Vector search filtered by visible_ids. If visible_ids is None, no filter."""
|
|
raise NotImplementedError
|
|
|
|
async def get_embedding_text(
|
|
self, db: AsyncSession, entity_id: uuid.UUID, tenant_id: uuid.UUID
|
|
) -> str:
|
|
"""Override: Get text for embedding generation."""
|
|
raise NotImplementedError
|