group_fqcd_jr/app/service/knowledge_tool_service.py

from typing import Protocol

from app.core.config import get_settings
from app.core.contracts import RequestContext
from app.core.knowledge_contracts import KnowledgeQuery, KnowledgeSearchResult
from app.infrastructure.db import SessionFactory
from app.infrastructure.milvus_knowledge_adapter import MilvusKnowledgeClient
from app.service.knowledge_authority import KnowledgeMysqlAuthority
from app.service.knowledge_config import KnowledgeRuntimeConfig
from app.service.knowledge_retrieval_service import KnowledgeRetrievalService
from app.service.model_gateway import DatabaseModelGateway


class EmbeddingGateway(Protocol):
    async def embed(self, *, endpoint_code: str, text: str, timeout_ms: int) -> list[float]: ...


class DatabaseEmbeddingAdapter:
    def __init__(
        self, endpoint_code: str, timeout_ms: int, *, gateway: EmbeddingGateway
    ) -> None:
        self._endpoint_code = endpoint_code
        self._timeout_ms = timeout_ms
        self._gateway = gateway

    async def embed(self, text: str) -> list[float]:
        return await self._gateway.embed(
            endpoint_code=self._endpoint_code, text=text, timeout_ms=self._timeout_ms
        )


async def query_knowledge_tool(
    arguments: KnowledgeQuery, context: RequestContext
) -> KnowledgeSearchResult:
    settings = get_settings()
    if not settings.knowledge_embedding_endpoint_code:
        return KnowledgeSearchResult(
            degraded=True, degradation_reason="embedding_endpoint_unconfigured"
        )
    # 知识向量端点与默认聊天端点隔离，避免回答模型被误用于检索。
    embedder = DatabaseEmbeddingAdapter(
        settings.knowledge_embedding_endpoint_code,
        settings.knowledge_embedding_timeout_ms,
        gateway=DatabaseModelGateway(),
    )
    # 兼容旧测试替身；真实 Settings 会优先提供本地/远程统一解析后的地址。
    milvus_uri = getattr(settings, "resolved_milvus_uri", settings.milvus_uri)
    vector_store = MilvusKnowledgeClient(milvus_uri, token=settings.milvus_token or None)
    # 权威元数据只读回查，确保对客答案始终来自已发布、有效的知识条目。
    async with SessionFactory() as session:
        authority = KnowledgeMysqlAuthority(session)
        service = KnowledgeRetrievalService(
            embedder, vector_store, KnowledgeRuntimeConfig(), authority
        )
        return await service.search(arguments, context)