Files
leocrm/app/plugins/builtins/unified_search/providers/company_provider.py
T
Agent Zero 3d9b76cea4
Check Cross-Plugin Imports / check (push) Has been cancelled
feat(E): Unified Search — 24 Tasks complete
- 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.
2026-08-14 01:34:58 +02:00

177 lines
6.0 KiB
Python

"""Company search provider — queries contacts with type='company'."""
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 CompanySearchProvider(BaseSearchProvider):
"""Search provider for Company entities (contacts with type='company')."""
entity_type = "contact"
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 contacts.search_tsv where type='company', 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 c.*, ts_rank(c.search_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
FROM contacts c
WHERE c.tenant_id = :tid
AND c.deleted_at IS NULL
AND c.type = 'company'
AND c.search_tsv @@ to_tsquery('pg_catalog.german', :q)
AND c.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 c.*, ts_rank(c.search_tsv, to_tsquery('pg_catalog.german', :q)) AS rank
FROM contacts c
WHERE c.tenant_id = :tid
AND c.deleted_at IS NULL
AND c.type = 'company'
AND c.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_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 contacts.embedding where type='company', 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 c.*, 1 - (c.embedding <=> cast(:emb AS vector)) AS score
FROM contacts c
WHERE c.tenant_id = :tid
AND c.deleted_at IS NULL
AND c.type = 'company'
AND c.embedding IS NOT NULL
AND c.id = ANY(:visible_ids)
ORDER BY c.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 c.*, 1 - (c.embedding <=> cast(:emb AS vector)) AS score
FROM contacts c
WHERE c.tenant_id = :tid
AND c.deleted_at IS NULL
AND c.type = 'company'
AND c.embedding IS NOT NULL
ORDER BY c.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 displayname, name, email_1, email_2, phone_1, website,
mailing_city, tags, vat_code
FROM contacts
WHERE id = :eid AND tenant_id = :tid AND type = 'company'
"""
)
result = await db.execute(sql, {"eid": entity_id, "tid": tenant_id})
row = result.mappings().first()
if not row:
return ""
parts = [
row.get("displayname", ""),
row.get("name", ""),
row.get("email_1", ""),
row.get("phone_1", ""),
row.get("website", ""),
row.get("mailing_city", ""),
row.get("tags", ""),
]
return " ".join(str(p) for p in parts if p)
def to_search_result(self, entity: object) -> dict[str, Any]:
"""Convert company to search result dict."""
if isinstance(entity, dict):
name = entity.get("name", "") or entity.get("displayname", "")
email = entity.get("email_1", "") or ""
entity_id = str(entity.get("id", ""))
else:
name = getattr(entity, "name", "") or getattr(entity, "displayname", "")
email = getattr(entity, "email_1", "") or ""
entity_id = str(getattr(entity, "id", ""))
return {
"entity_type": self.entity_type,
"entity_id": entity_id,
"title": name,
"snippet": email[:200],
"score": 0.0,
"data": {"type": "company"},
}