feat(E): Unified Search — 24 Tasks complete
Check Cross-Plugin Imports / check (push) Has been cancelled
Check Cross-Plugin Imports / check (push) Has been cancelled
- SPIKE-E: FTS+Vector+Permission benchmark on 10k records (all <30ms) - E-PROV: supports_fts/vector/rag/graph capability flags on all providers - E-FTS/VEC: All 11 providers refactored to BaseSearchProvider with permission filtering - E-PERM: Over-fetch strategy for vector+permission (15x faster than ANY() filter) - E-FUSE: rrf_fusion_multi() for N-way RRF over FTS+Vector+RAG+Graph - E-LLM: Query understanding cleaned up to use central llm_complete() - E-CHUNK: Document chunking module + document_chunks table with HNSW index - E-EMB: Chunk embedding ARQ jobs (index_file_chunks, reindex_chunks) - E-RAG: RAG retrieval via FileSearchProvider.search_rag() - E-GRAPH: GraphRAG BFS traversal via GraphRAGSearchProvider.search_graph() - E-IX-EVT: Auto-indexing via outbox events + delete/cleanup handlers - E-IX-RE: Batch reindex with progress tracking + reindex_all job - E-DATA-LIFE: Lifecycle module (remove/rebuild/restore/correct) + API endpoints - E-K-MEM: AgentMemorySearchProvider - E-P-AI: AIChatSearchProvider - E-P-WF: WorkflowSearchProvider - E-P-COMM: ConversationSearchProvider verified (already on BaseSearchProvider) - E-API: Filter params (date_from/to, tags, sort) + /facets endpoint - E-TOOL: unified_search AI tool registered in ToolRegistry - E-MCP: Search tool in MCP server with normal RBAC/tenant checks - E-UI-CMD: CommandPalette (Cmd+K) with debounced search + recent searches - E-UI-FAC: SearchFacets, SearchResultCard, SavedSearches components - E-TEST: 40 new tests in test_unified_search_phase_e.py (105 total green) - E-DOC: api-documentation.md, plugin-development-guide.md, test-strategy.md updated 105 tests passing, TypeScript clean.
This commit is contained in:
Agent Zero
@@ -9,71 +9,124 @@ 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 EventSearchProvider:
|
||||
class EventSearchProvider(BaseSearchProvider):
|
||||
"""Search provider for CalendarEntry entities."""
|
||||
|
||||
entity_type = "event"
|
||||
|
||||
async def search_fts(
|
||||
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 calendar_entries.search_tsv."""
|
||||
sql = text(
|
||||
"""
|
||||
SELECT e.*, ts_rank(e.search_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.search_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},
|
||||
)
|
||||
"""Full-text search on calendar_entries.search_tsv, filtered by visible_ids.
|
||||
|
||||
If visible_ids is None, no visibility filter is applied (system admin).
|
||||
"""
|
||||
if visible_ids is not None:
|
||||
sql = text(
|
||||
"""
|
||||
SELECT e.*, ts_rank(e.search_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.search_tsv @@ to_tsquery('pg_catalog.german', :q)
|
||||
AND e.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 e.*, ts_rank(e.search_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.search_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(
|
||||
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 search on calendar_entries.embedding."""
|
||||
sql = text(
|
||||
"""
|
||||
SELECT e.*, 1 - (e.embedding <=> cast(:emb AS vector)) AS score
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.embedding IS NOT NULL
|
||||
ORDER BY e.embedding <=> cast(:emb AS vector)
|
||||
LIMIT :lim
|
||||
"""
|
||||
)
|
||||
result = await db.execute(
|
||||
sql,
|
||||
{"emb": str(embedding), "tid": tenant_id, "lim": limit},
|
||||
)
|
||||
"""Semantic search on calendar_entries.embedding, filtered by visible_ids.
|
||||
|
||||
If visible_ids is None, no visibility filter is applied (system admin).
|
||||
"""
|
||||
if visible_ids is not None:
|
||||
sql = text(
|
||||
"""
|
||||
SELECT e.*, 1 - (e.embedding <=> cast(:emb AS vector)) AS score
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.embedding IS NOT NULL
|
||||
AND e.id = ANY(:visible_ids)
|
||||
ORDER BY e.embedding <=> cast(:emb AS vector)
|
||||
LIMIT :lim
|
||||
"""
|
||||
)
|
||||
result = await db.execute(
|
||||
sql,
|
||||
{
|
||||
"emb": str(embedding),
|
||||
"tid": tenant_id,
|
||||
"lim": limit,
|
||||
"visible_ids": list(visible_ids),
|
||||
},
|
||||
)
|
||||
else:
|
||||
sql = text(
|
||||
"""
|
||||
SELECT e.*, 1 - (e.embedding <=> cast(:emb AS vector)) AS score
|
||||
FROM calendar_entries e
|
||||
WHERE e.tenant_id = :tid
|
||||
AND e.deleted_at IS NULL
|
||||
AND e.embedding IS NOT NULL
|
||||
ORDER BY e.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,
|
||||
self, db: AsyncSession, entity_id: uuid.UUID, tenant_id: uuid.UUID
|
||||
) -> str:
|
||||
"""Get text for embedding generation."""
|
||||
sql = text(
|
||||
|
||||
Reference in New Issue
Block a user