e4bf0710c7
数据库 - 新增迁移 0003：timeline_events.memory_source_id 外键 → memory_sources，便于按 ingest 源做时间线幂等 后端 - 记忆 - 新增 ingest 后 LLM 富化（摘要/事实/时间线），可配置开关与最大字符数 - 新增证据包组装：合并 chunk、摘要、事实、时间线、故事等检索结果；支持空 query 时是否仍带 rolling 等开关 - repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展；文档 memory-retrieval.md 更新 后端 - 对话 WS - 增加 PING/PONG；分段 ASR 日志与空音频处理；转写失败与「无助手回复」错误提示更明确 - 助手多段回复持久化使用统一分隔符，与分段逻辑一致 后端 - Agent - reply_limits：按 [SPLIT] 与段落拆段，并保证非空 fallback，供 WS 与 TTS 多段下发 后端 - 回忆录任务 - transcript ingest 记录 source_id；任务成功结?
104 lines
2.9 KiB
Python
104 lines
2.9 KiB
Python
"""LLM JSON 输出校验（memory 富化）。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
from typing import Any, TypeVar
|
||
|
||
from pydantic import BaseModel, Field, field_validator
|
||
|
||
TModel = TypeVar("TModel", bound=BaseModel)
|
||
|
||
|
||
class ExtractedFactItem(BaseModel):
|
||
fact_type: str = "event"
|
||
subject: str | None = None
|
||
predicate: str | None = None
|
||
object_json: Any = None
|
||
confidence: float = Field(default=0.75, ge=0.0, le=1.0)
|
||
source_chunk_id: str | None = None
|
||
|
||
@field_validator("fact_type", mode="before")
|
||
@classmethod
|
||
def _coerce_fact_type(cls, v: object) -> str:
|
||
ft = str(v or "event").strip() or "event"
|
||
if ft not in ("person", "event", "relation", "place", "milestone"):
|
||
return "event"
|
||
return ft
|
||
|
||
|
||
class FactsExtractionPayload(BaseModel):
|
||
facts: list[ExtractedFactItem] = Field(default_factory=list)
|
||
|
||
|
||
class SessionSummaryPayload(BaseModel):
|
||
summary: str = ""
|
||
|
||
|
||
class RollingSummaryPayload(BaseModel):
|
||
rolling_summary: str = ""
|
||
|
||
|
||
class TimelineEventItem(BaseModel):
|
||
event_year: int | None = None
|
||
event_date: str | None = None
|
||
title: str = ""
|
||
description: str | None = None
|
||
source_fact_ids: list[str] = Field(default_factory=list)
|
||
|
||
@field_validator("source_fact_ids", mode="before")
|
||
@classmethod
|
||
def _coerce_sf(cls, v: object) -> list[str]:
|
||
if v is None:
|
||
return []
|
||
if isinstance(v, str):
|
||
return [v] if v else []
|
||
if isinstance(v, list):
|
||
return [str(x) for x in v if x]
|
||
return []
|
||
|
||
|
||
class TimelineEventsPayload(BaseModel):
|
||
events: list[TimelineEventItem] = Field(default_factory=list)
|
||
|
||
|
||
def parse_json_payload(raw: str, model: type[TModel]) -> TModel | None:
|
||
"""解析 invoke_json_object 返回的 JSON 字符串。"""
|
||
from app.features.memoir.memoir_images.json_payload import extract_json_payload
|
||
|
||
try:
|
||
cleaned = extract_json_payload(raw)
|
||
data = json.loads(cleaned)
|
||
return model.model_validate(data)
|
||
except (json.JSONDecodeError, ValueError, TypeError):
|
||
return None
|
||
|
||
|
||
def facts_payload_to_dicts(payload: FactsExtractionPayload) -> list[dict]:
|
||
out: list[dict] = []
|
||
for item in payload.facts:
|
||
d = item.model_dump()
|
||
scid = d.get("source_chunk_id")
|
||
if scid is not None and not isinstance(scid, str):
|
||
d["source_chunk_id"] = str(scid)
|
||
out.append(d)
|
||
return out
|
||
|
||
|
||
def timeline_payload_to_dicts(payload: TimelineEventsPayload) -> list[dict]:
|
||
out: list[dict] = []
|
||
for ev in payload.events:
|
||
title = (ev.title or "").strip()
|
||
if not title:
|
||
continue
|
||
out.append(
|
||
{
|
||
"event_year": ev.event_year,
|
||
"event_date": ev.event_date,
|
||
"title": title,
|
||
"description": ev.description,
|
||
"source_fact_ids": ev.source_fact_ids or [],
|
||
}
|
||
)
|
||
return out[:20]
|