feat(memory,conversation): 记忆富化/证据包、时间线幂等字段与对话分段全链路
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?
This commit is contained in:
25
api/app/features/memory/enrichment_pipeline.py
Normal file
25
api/app/features/memory/enrichment_pipeline.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""Enrichment 共享:去重键与 object_json 规范化(sync/async 共用)。"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
|
||||
|
||||
def dedupe_key(f: dict) -> tuple:
|
||||
s = f.get("subject") or ""
|
||||
p = f.get("predicate") or ""
|
||||
o = f.get("object_json")
|
||||
try:
|
||||
oj = json.dumps(o, sort_keys=True, ensure_ascii=False) if o is not None else ""
|
||||
except (TypeError, ValueError):
|
||||
oj = str(o)
|
||||
return (str(s), str(p), oj)
|
||||
|
||||
|
||||
def normalize_object_json(obj: Any) -> dict | list | None:
|
||||
if obj is None:
|
||||
return None
|
||||
if isinstance(obj, (dict, list)):
|
||||
return obj
|
||||
return {"value": obj}
|
||||
Reference in New Issue
Block a user