Compare commits
3 Commits
0ec08185f9
...
b5649cc218
| Author | SHA1 | Date |
|---|---|---|
Bifang
|
b5649cc218 | |
|
Bifang
|
f857a90977 | |
|
Bifang
|
b7d4cc8782 |
|
|
@ -2,12 +2,18 @@ import json
|
|||
import logging
|
||||
import re
|
||||
import sys
|
||||
from typing import List, Optional
|
||||
from enum import Enum
|
||||
from typing import Any, List, Optional
|
||||
|
||||
from openai import OpenAI
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
from meeting_memory.config import config
|
||||
from meeting_memory.prompts import extract_entities as prompt_extract_entities
|
||||
from meeting_memory.prompts import extract_facts as prompt_extract_facts
|
||||
from meeting_memory.prompts import resolve_entities as prompt_dedupe_nodes
|
||||
from meeting_memory.prompts import resolve_facts as prompt_dedupe_edges
|
||||
from meeting_memory.prompts import summarize_entity as prompt_summarize
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
|
@ -17,52 +23,96 @@ client = OpenAI(
|
|||
)
|
||||
|
||||
|
||||
class EntityType(str, Enum):
|
||||
DEPARTMENT = 'Department'
|
||||
PROJECT = 'Project'
|
||||
METRIC = 'Metric'
|
||||
PERSON = 'Person'
|
||||
SYSTEM = 'System'
|
||||
DOCUMENT = 'Document'
|
||||
PARTICIPANT = 'participant'
|
||||
UNKNOWN = 'Unknown'
|
||||
|
||||
|
||||
# Normalization map: legacy LLM output → canonical type
|
||||
_ENTITY_TYPE_ALIASES = {
|
||||
'组织': 'Department',
|
||||
'organization': 'Department',
|
||||
'部门': 'Department',
|
||||
'指标': 'Metric',
|
||||
'kpi': 'Metric',
|
||||
'项目': 'Project',
|
||||
}
|
||||
|
||||
|
||||
def _canonical_entity_type(raw: str) -> str:
|
||||
normalized = raw.strip()
|
||||
if normalized in _ENTITY_TYPE_ALIASES:
|
||||
return _ENTITY_TYPE_ALIASES[normalized]
|
||||
for member in EntityType:
|
||||
if member.value.lower() == normalized.lower():
|
||||
return member.value
|
||||
return EntityType.UNKNOWN.value
|
||||
|
||||
|
||||
def _neo4j_labels(entity_type: str) -> list[str]:
|
||||
canonical = _canonical_entity_type(entity_type)
|
||||
labels = ['Entity']
|
||||
if canonical != EntityType.UNKNOWN.value:
|
||||
labels.append(canonical)
|
||||
return labels
|
||||
|
||||
|
||||
class Entity(BaseModel):
|
||||
name: str
|
||||
entity_type: str
|
||||
description: str = ""
|
||||
entity_type: str = EntityType.UNKNOWN.value
|
||||
description: str = ''
|
||||
|
||||
|
||||
class Relation(BaseModel):
|
||||
subject: str
|
||||
subject_type: str
|
||||
predicate: str
|
||||
object: str
|
||||
object_type: str
|
||||
description: str = ""
|
||||
fact: str = ""
|
||||
source_entity_name: str
|
||||
target_entity_name: str
|
||||
relation_type: str
|
||||
fact: str = ''
|
||||
valid_at: str = ''
|
||||
invalid_at: str = ''
|
||||
evidence: str = ''
|
||||
qualifiers: List[str] = Field(default_factory=list)
|
||||
evidence: str = ""
|
||||
confidence: float = 0.0
|
||||
valid_at: str = ""
|
||||
invalid_at: str = ""
|
||||
|
||||
|
||||
class ActionItem(BaseModel):
|
||||
task: str
|
||||
assignee: str = ""
|
||||
deadline: str = ""
|
||||
status: str = "待办"
|
||||
priority: str = "中"
|
||||
assignee: str = ''
|
||||
deadline: str = ''
|
||||
status: str = '待办'
|
||||
priority: str = '中'
|
||||
|
||||
|
||||
class Decision(BaseModel):
|
||||
content: str
|
||||
proposer: str = ""
|
||||
status: str = "已决"
|
||||
proposer: str = ''
|
||||
status: str = '已决'
|
||||
|
||||
|
||||
class MeetingMetric(BaseModel):
|
||||
metric_name: str
|
||||
value: str
|
||||
target: str = ""
|
||||
owner: str = ""
|
||||
trend: str = ""
|
||||
target: str = ''
|
||||
owner: str = ''
|
||||
trend: str = ''
|
||||
unit: str = ''
|
||||
|
||||
|
||||
class DepartmentInfo(BaseModel):
|
||||
name: str
|
||||
description: str = ''
|
||||
projects: List[str] = Field(default_factory=list)
|
||||
|
||||
|
||||
class MeetingExtraction(BaseModel):
|
||||
title: str
|
||||
date: str = ""
|
||||
date: str = ''
|
||||
participants: List[str] = Field(default_factory=list)
|
||||
agenda: List[str] = Field(default_factory=list)
|
||||
entities: List[Entity] = Field(default_factory=list)
|
||||
|
|
@ -70,15 +120,282 @@ class MeetingExtraction(BaseModel):
|
|||
action_items: List[ActionItem] = Field(default_factory=list)
|
||||
decisions: List[Decision] = Field(default_factory=list)
|
||||
metrics: List[MeetingMetric] = Field(default_factory=list)
|
||||
summary: str = ""
|
||||
departments: List[DepartmentInfo] = Field(default_factory=list)
|
||||
summary: str = ''
|
||||
|
||||
|
||||
def _call_llm(
|
||||
messages: list[dict],
|
||||
response_model: type | None = None,
|
||||
stream: bool = False,
|
||||
max_tokens: int | None = None,
|
||||
) -> Any:
|
||||
kwargs = {
|
||||
'model': config.llm.model,
|
||||
'messages': messages,
|
||||
'max_tokens': max_tokens or config.llm.max_tokens,
|
||||
'temperature': config.llm.temperature,
|
||||
}
|
||||
if response_model is not None:
|
||||
kwargs['response_format'] = {'type': 'json_object'}
|
||||
if stream:
|
||||
kwargs['stream'] = True
|
||||
|
||||
if not stream:
|
||||
response = client.chat.completions.create(**kwargs)
|
||||
content = response.choices[0].message.content
|
||||
if content is None:
|
||||
raise ValueError('LLM returned empty response')
|
||||
return content
|
||||
|
||||
kwargs['stream'] = True
|
||||
response = client.chat.completions.create(**kwargs)
|
||||
chunks: List[str] = []
|
||||
print('\n[LLM] 开始流式输出：')
|
||||
for event in response:
|
||||
if not event.choices:
|
||||
continue
|
||||
delta = event.choices[0].delta.content
|
||||
if not delta:
|
||||
continue
|
||||
chunks.append(delta)
|
||||
sys.stdout.write(delta)
|
||||
sys.stdout.flush()
|
||||
print('\n[LLM] 输出结束')
|
||||
return ''.join(chunks)
|
||||
|
||||
|
||||
def _try_parse_json(content: str) -> dict | list:
|
||||
try:
|
||||
return json.loads(content)
|
||||
except json.JSONDecodeError:
|
||||
logger.warning('JSON parsing failed; trying to repair extracted block')
|
||||
match = re.search(r'\{.*\}|\[.*\]', content, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
return json.loads(match.group())
|
||||
except json.JSONDecodeError as exc:
|
||||
logger.error('Repaired JSON still failed to parse: %s', exc)
|
||||
raise
|
||||
|
||||
|
||||
def _normalize_string(name: str) -> str:
|
||||
return re.sub(r'[\s]+', ' ', name.strip().lower())
|
||||
|
||||
|
||||
def _format_episodes_for_context(episodes: list[dict] | None) -> str:
|
||||
if not episodes:
|
||||
return ''
|
||||
return '\n'.join(
|
||||
f'[Episode {i}] {ep.get("content", "")}'
|
||||
for i, ep in enumerate(episodes)
|
||||
)
|
||||
|
||||
|
||||
# ===== Step 1: 实体节点抽取 =====
|
||||
|
||||
def extract_entities_from_text(
|
||||
text: str,
|
||||
previous_episodes: list[dict] | None = None,
|
||||
entity_types: list[dict] | None = None,
|
||||
stream: bool = False,
|
||||
) -> list[dict]:
|
||||
context = {
|
||||
'episode_content': text,
|
||||
'previous_episodes': previous_episodes or [],
|
||||
'entity_types': entity_types or [],
|
||||
}
|
||||
messages = prompt_extract_entities(context)
|
||||
content = _call_llm(messages, stream=stream)
|
||||
try:
|
||||
data = _try_parse_json(content)
|
||||
except Exception as exc:
|
||||
logger.error('Failed to parse entity extraction result: %s', exc)
|
||||
return []
|
||||
if isinstance(data, dict):
|
||||
data = data.get('entities', data.get('extracted_entities', []))
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
result = []
|
||||
for item in data:
|
||||
if isinstance(item, dict) and item.get('name', '').strip():
|
||||
result.append({
|
||||
'name': item['name'].strip(),
|
||||
'entity_type': item.get('entity_type', 'Entity'),
|
||||
'description': item.get('description', ''),
|
||||
'evidence': item.get('evidence', ''),
|
||||
})
|
||||
return result
|
||||
|
||||
|
||||
# ===== Step 2: 实体去重 =====
|
||||
|
||||
def resolve_entities_against_graph(
|
||||
extracted: list[dict],
|
||||
existing: list[dict],
|
||||
episode_content: str = '',
|
||||
) -> list[dict]:
|
||||
if not existing:
|
||||
return extracted
|
||||
|
||||
context = {
|
||||
'extracted_entities': extracted,
|
||||
'existing_entities': existing,
|
||||
'episode_content': episode_content,
|
||||
}
|
||||
messages = prompt_dedupe_nodes(context)
|
||||
content = _call_llm(messages)
|
||||
try:
|
||||
data = _try_parse_json(content)
|
||||
except Exception as exc:
|
||||
logger.warning('LLM dedup failed, keeping all extracted: %s', exc)
|
||||
return extracted
|
||||
|
||||
if isinstance(data, dict):
|
||||
data = data.get('entity_resolutions', data.get('resolutions', []))
|
||||
|
||||
extracted_by_id = {i: e for i, e in enumerate(extracted)}
|
||||
existing_by_id = {c.get('candidate_id'): c for c in existing}
|
||||
|
||||
for resolution in (data if isinstance(data, list) else []):
|
||||
if not isinstance(resolution, dict):
|
||||
continue
|
||||
rid = resolution.get('id')
|
||||
dup_id = resolution.get('duplicate_candidate_id', -1)
|
||||
if rid is None or rid not in extracted_by_id:
|
||||
continue
|
||||
if dup_id >= 0 and dup_id in existing_by_id:
|
||||
extracted_by_id[rid]['_resolved_to'] = existing_by_id[dup_id]
|
||||
extracted_by_id[rid]['name'] = resolution.get('name', extracted_by_id[rid]['name'])
|
||||
|
||||
return [e for e in extracted_by_id.values() if '_resolved_to' not in e]
|
||||
|
||||
|
||||
# ===== Step 3: 事实关系抽取 =====
|
||||
|
||||
def extract_facts_from_text(
|
||||
text: str,
|
||||
entities: list[dict],
|
||||
reference_time: str = '',
|
||||
previous_episodes: list[dict] | None = None,
|
||||
stream: bool = False,
|
||||
) -> list[dict]:
|
||||
if len(entities) < 2:
|
||||
return []
|
||||
|
||||
context = {
|
||||
'episode_content': text,
|
||||
'entities': entities,
|
||||
'reference_time': reference_time,
|
||||
'previous_episodes': previous_episodes or [],
|
||||
}
|
||||
messages = prompt_extract_facts(context)
|
||||
content = _call_llm(messages, stream=stream)
|
||||
try:
|
||||
data = _try_parse_json(content)
|
||||
except Exception as exc:
|
||||
logger.error('Failed to parse fact extraction result: %s', exc)
|
||||
return []
|
||||
|
||||
if isinstance(data, dict):
|
||||
data = data.get('edges', data.get('facts', data.get('relations', [])))
|
||||
|
||||
if not isinstance(data, list):
|
||||
return []
|
||||
|
||||
entity_names = {_normalize_string(e.get('name', '')) for e in entities}
|
||||
result = []
|
||||
for item in data:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
src = _normalize_string(item.get('source_entity_name', ''))
|
||||
tgt = _normalize_string(item.get('target_entity_name', ''))
|
||||
if src not in entity_names or tgt not in entity_names:
|
||||
continue
|
||||
if src == tgt:
|
||||
continue
|
||||
result.append({
|
||||
'source_entity_name': item['source_entity_name'],
|
||||
'target_entity_name': item['target_entity_name'],
|
||||
'relation_type': item.get('relation_type', '关联'),
|
||||
'fact': item.get('fact', ''),
|
||||
'valid_at': item.get('valid_at', ''),
|
||||
'invalid_at': item.get('invalid_at', ''),
|
||||
'evidence': item.get('evidence', ''),
|
||||
'qualifiers': item.get('qualifiers', []),
|
||||
'confidence': item.get('confidence', 0.0),
|
||||
})
|
||||
return result
|
||||
|
||||
|
||||
# ===== Step 4: 事实去重/矛盾检测 =====
|
||||
|
||||
def resolve_facts_against_graph(
|
||||
new_fact: dict,
|
||||
existing_facts: list[dict],
|
||||
invalidation_candidates: list[dict],
|
||||
) -> dict:
|
||||
if not existing_facts:
|
||||
return {'is_duplicate': False, 'is_contradicted': False, 'resolved': new_fact}
|
||||
|
||||
context = {
|
||||
'new_fact': new_fact.get('fact', ''),
|
||||
'existing_facts': existing_facts,
|
||||
'invalidation_candidates': invalidation_candidates,
|
||||
}
|
||||
messages = prompt_dedupe_edges(context)
|
||||
content = _call_llm(messages)
|
||||
try:
|
||||
data = _try_parse_json(content)
|
||||
except Exception as exc:
|
||||
logger.warning('Fact dedup failed, treating as new: %s', exc)
|
||||
return {'is_duplicate': False, 'is_contradicted': False, 'resolved': new_fact}
|
||||
|
||||
if not isinstance(data, dict):
|
||||
return {'is_duplicate': False, 'is_contradicted': False, 'resolved': new_fact}
|
||||
return {
|
||||
'is_duplicate': len(data.get('duplicate_facts', [])) > 0,
|
||||
'is_contradicted': len(data.get('contradicted_facts', [])) > 0,
|
||||
'resolved': new_fact,
|
||||
'duplicate_facts': data.get('duplicate_facts', []),
|
||||
'contradicted_facts': data.get('contradicted_facts', []),
|
||||
}
|
||||
|
||||
|
||||
# ===== Step 5: 实体摘要 =====
|
||||
|
||||
def extract_entity_summary(
|
||||
entity_name: str,
|
||||
episodes: list[str],
|
||||
existing_summary: str = '',
|
||||
previous_episodes: list[dict] | None = None,
|
||||
) -> str:
|
||||
context = {
|
||||
'entity_name': entity_name,
|
||||
'episodes': episodes,
|
||||
'existing_summary': existing_summary,
|
||||
'previous_episodes': previous_episodes or [],
|
||||
}
|
||||
messages = prompt_summarize(context)
|
||||
content = _call_llm(messages, max_tokens=1024)
|
||||
try:
|
||||
data = _try_parse_json(content)
|
||||
except Exception:
|
||||
logger.warning('Failed to parse summary, using empty')
|
||||
return ''
|
||||
if isinstance(data, dict):
|
||||
return data.get('summary', '')
|
||||
return ''
|
||||
|
||||
|
||||
# ===== 统一入口（兼容原有接口） =====
|
||||
|
||||
EXTRACTION_SYSTEM_PROMPT = """
|
||||
你是一个专业的会议知识抽取助手。你的任务是从中文会议记录中抽取结构化事实，尤其要抽出更细粒度、更有语义深度的关系。
|
||||
|
||||
输出要求：
|
||||
1. 只输出一个 JSON 对象，不要输出解释文字。
|
||||
2. 关系抽取不要停留在“部门汇报了工作”这种浅层描述，要尽可能向下细化到：
|
||||
2. 关系抽取不要停留在"部门汇报了工作"这种浅层描述，要尽可能向下细化到：
|
||||
- 责任归属
|
||||
- 目标值 / 当前值 / 趋势
|
||||
- 约束条件
|
||||
|
|
@ -99,51 +416,9 @@ EXTRACTION_SYSTEM_PROMPT = """
|
|||
"""
|
||||
|
||||
|
||||
def _call_llm(system: str, user: str, stream: bool = False) -> str:
|
||||
if not stream:
|
||||
response = client.chat.completions.create(
|
||||
model=config.llm.model,
|
||||
messages=[
|
||||
{"role": "system", "content": system},
|
||||
{"role": "user", "content": user},
|
||||
],
|
||||
max_tokens=config.llm.max_tokens,
|
||||
temperature=config.llm.temperature,
|
||||
)
|
||||
content = response.choices[0].message.content
|
||||
if content is None:
|
||||
raise ValueError("LLM returned empty response")
|
||||
return content
|
||||
|
||||
response = client.chat.completions.create(
|
||||
model=config.llm.model,
|
||||
messages=[
|
||||
{"role": "system", "content": system},
|
||||
{"role": "user", "content": user},
|
||||
],
|
||||
max_tokens=config.llm.max_tokens,
|
||||
temperature=config.llm.temperature,
|
||||
stream=True,
|
||||
)
|
||||
|
||||
chunks: List[str] = []
|
||||
print("\n[LLM] 开始抽取，流式输出中：")
|
||||
for event in response:
|
||||
if not event.choices:
|
||||
continue
|
||||
delta = event.choices[0].delta.content
|
||||
if not delta:
|
||||
continue
|
||||
chunks.append(delta)
|
||||
sys.stdout.write(delta)
|
||||
sys.stdout.flush()
|
||||
print("\n[LLM] 抽取输出结束")
|
||||
return "".join(chunks)
|
||||
|
||||
|
||||
def extract_meeting_info(text: str, stream: bool = False) -> MeetingExtraction:
|
||||
user_prompt = f"""
|
||||
请从下面会议记录中提取结构化信息，并重点做“深层关系抽取”。
|
||||
请从下面会议记录中提取结构化信息，并重点做"深层关系抽取"和"层次结构识别"。
|
||||
|
||||
输出 JSON 字段：
|
||||
- title
|
||||
|
|
@ -151,28 +426,32 @@ def extract_meeting_info(text: str, stream: bool = False) -> MeetingExtraction:
|
|||
- participants
|
||||
- agenda
|
||||
- entities: name, entity_type, description
|
||||
- entity_type 请使用: Department（部门）、Project（项目）、Metric（指标）、Person（人物）、System（系统）、Document（文档）
|
||||
- relations:
|
||||
- subject
|
||||
- subject_type
|
||||
- predicate
|
||||
- object
|
||||
- object_type
|
||||
- description
|
||||
- fact
|
||||
- qualifiers
|
||||
- evidence
|
||||
- confidence
|
||||
- valid_at
|
||||
- invalid_at
|
||||
- source_entity_name: 源实体名称
|
||||
- target_entity_name: 目标实体名称
|
||||
- relation_type: 关系类型（如 HAS_PROJECT、HAS_METRIC、负责、汇报、目标值、推进、依赖）
|
||||
- fact: 一句自然语言事实描述
|
||||
- valid_at（可选）
|
||||
- invalid_at（可选）
|
||||
- evidence: 原文证据
|
||||
- qualifiers: 限定条件列表
|
||||
- confidence: 0~1
|
||||
- action_items: task, assignee, deadline, status, priority
|
||||
- decisions: content, proposer, status
|
||||
- metrics: metric_name, value, target, owner, trend
|
||||
- metrics: metric_name, value, target, owner, trend, unit
|
||||
- departments: [{{"name": "部门名称", "description": "", "projects": ["项目名1", "项目名2"]}}]
|
||||
- summary
|
||||
|
||||
层次关系规则：
|
||||
1. Department 管辖 Project → relation_type 用 HAS_PROJECT
|
||||
2. Project 拥有 Metric → relation_type 用 HAS_METRIC
|
||||
3. 其他事实关系（负责、汇报、目标值等）直接用 relation_type 表达
|
||||
|
||||
关系抽取规则：
|
||||
1. 不要只抽“汇报了工作”这种会议动作，要尽量继续下钻出具体事实。
|
||||
2. 如果一句话里同时包含“主体 + 指标 + 当前值 + 目标值 + 负责人 + 趋势”，应拆成多条关系或在 qualifiers 中保留这些细节。
|
||||
3. 对于“要求、部署、负责、依赖、影响、约束、目标、风险”类信息优先保留。
|
||||
1. 不要只抽"汇报了工作"这种会议动作，要尽量继续下钻出具体事实。
|
||||
2. 如果一句话里同时包含"主体 + 指标 + 当前值 + 目标值 + 负责人 + 趋势"，应拆成多条关系或在 qualifiers 中保留这些细节。
|
||||
3. 对于"要求、部署、负责、依赖、影响、约束、目标、风险"类信息优先保留。
|
||||
4. fact 必须是一句完整、自然、可检索的事实描述。
|
||||
5. qualifiers 用于补充数值、范围、状态、条件、截止时间、优先级等信息。
|
||||
6. evidence 用原文中的关键词短句，不要太长。
|
||||
|
|
@ -181,54 +460,43 @@ def extract_meeting_info(text: str, stream: bool = False) -> MeetingExtraction:
|
|||
会议记录如下：
|
||||
{text}
|
||||
"""
|
||||
content = _call_llm(EXTRACTION_SYSTEM_PROMPT, user_prompt, stream=stream)
|
||||
content = _call_llm([
|
||||
{'role': 'system', 'content': EXTRACTION_SYSTEM_PROMPT},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
], stream=stream)
|
||||
data = _try_parse_json(content)
|
||||
data = _normalize_meeting_data(data)
|
||||
return MeetingExtraction(**data)
|
||||
|
||||
|
||||
def _try_parse_json(content: str) -> dict:
|
||||
try:
|
||||
return json.loads(content)
|
||||
except json.JSONDecodeError:
|
||||
logger.warning("JSON parsing failed; trying to repair extracted block")
|
||||
match = re.search(r"\{.*\}", content, re.DOTALL)
|
||||
if match:
|
||||
try:
|
||||
return json.loads(match.group())
|
||||
except json.JSONDecodeError as exc:
|
||||
logger.error("Repaired JSON still failed to parse: %s", exc)
|
||||
raise
|
||||
|
||||
|
||||
def _normalize_meeting_data(data: dict) -> dict:
|
||||
if not isinstance(data, dict):
|
||||
return {}
|
||||
|
||||
return {
|
||||
"title": _as_str(data.get("title")),
|
||||
"date": _as_str(data.get("date")),
|
||||
"participants": _as_str_list(data.get("participants")),
|
||||
"agenda": _as_str_list(data.get("agenda")),
|
||||
"entities": _normalize_entities(data.get("entities")),
|
||||
"relations": _normalize_relations(data.get("relations")),
|
||||
"action_items": _normalize_action_items(data.get("action_items")),
|
||||
"decisions": _normalize_decisions(data.get("decisions")),
|
||||
"metrics": _normalize_metrics(data.get("metrics")),
|
||||
"summary": _as_str(data.get("summary")),
|
||||
'title': _as_str(data.get('title')),
|
||||
'date': _as_str(data.get('date')),
|
||||
'participants': _as_str_list(data.get('participants')),
|
||||
'agenda': _as_str_list(data.get('agenda')),
|
||||
'entities': _normalize_entities(data.get('entities')),
|
||||
'relations': _normalize_relations(data.get('relations')),
|
||||
'action_items': _normalize_action_items(data.get('action_items')),
|
||||
'decisions': _normalize_decisions(data.get('decisions')),
|
||||
'metrics': _normalize_metrics(data.get('metrics')),
|
||||
'departments': _normalize_departments(data.get('departments')),
|
||||
'summary': _as_str(data.get('summary')),
|
||||
}
|
||||
|
||||
|
||||
def _as_str(value) -> str:
|
||||
if value is None:
|
||||
return ""
|
||||
return ''
|
||||
if isinstance(value, str):
|
||||
return value
|
||||
return str(value)
|
||||
|
||||
|
||||
def _as_float(value) -> float:
|
||||
if value is None or value == "":
|
||||
if value is None or value == '':
|
||||
return 0.0
|
||||
try:
|
||||
numeric = float(value)
|
||||
|
|
@ -244,7 +512,7 @@ def _as_str_list(value) -> List[str]:
|
|||
key_text = _as_str(key)
|
||||
value_text = _as_str(item)
|
||||
if key_text and value_text:
|
||||
items.append(f"{key_text}: {value_text}")
|
||||
items.append(f'{key_text}: {value_text}')
|
||||
elif key_text:
|
||||
items.append(key_text)
|
||||
elif value_text:
|
||||
|
|
@ -262,50 +530,38 @@ def _normalize_entities(value) -> List[dict]:
|
|||
for entity in value:
|
||||
if not isinstance(entity, dict):
|
||||
continue
|
||||
items.append(
|
||||
{
|
||||
"name": _as_str(entity.get("name")),
|
||||
"entity_type": _as_str(entity.get("entity_type")),
|
||||
"description": _as_str(entity.get("description")),
|
||||
}
|
||||
)
|
||||
items.append({
|
||||
'name': _as_str(entity.get('name')),
|
||||
'entity_type': _as_str(entity.get('entity_type')),
|
||||
'description': _as_str(entity.get('description')),
|
||||
})
|
||||
return items
|
||||
|
||||
|
||||
def _normalize_relations(value) -> List[dict]:
|
||||
if not isinstance(value, list):
|
||||
return []
|
||||
|
||||
items = []
|
||||
for relation in value:
|
||||
if not isinstance(relation, dict):
|
||||
continue
|
||||
|
||||
subject = _as_str(relation.get("subject"))
|
||||
predicate = _as_str(relation.get("predicate"))
|
||||
obj = _as_str(relation.get("object"))
|
||||
description = _as_str(relation.get("description"))
|
||||
fact = _as_str(relation.get("fact"))
|
||||
|
||||
if not fact and subject and predicate and obj:
|
||||
fact = f"{subject} {predicate} {obj}"
|
||||
|
||||
items.append(
|
||||
{
|
||||
"subject": subject,
|
||||
"subject_type": _as_str(relation.get("subject_type")),
|
||||
"predicate": predicate,
|
||||
"object": obj,
|
||||
"object_type": _as_str(relation.get("object_type")),
|
||||
"description": description,
|
||||
"fact": fact,
|
||||
"qualifiers": _as_str_list(relation.get("qualifiers")),
|
||||
"evidence": _as_str(relation.get("evidence")),
|
||||
"confidence": _as_float(relation.get("confidence")),
|
||||
"valid_at": _as_str(relation.get("valid_at")),
|
||||
"invalid_at": _as_str(relation.get("invalid_at")),
|
||||
}
|
||||
)
|
||||
source = _as_str(relation.get('source_entity_name') or relation.get('subject', ''))
|
||||
target = _as_str(relation.get('target_entity_name') or relation.get('object', ''))
|
||||
rtype = _as_str(relation.get('relation_type') or relation.get('predicate', ''))
|
||||
fact = _as_str(relation.get('fact'))
|
||||
if not fact and source and rtype and target:
|
||||
fact = f'{source} {rtype} {target}'
|
||||
items.append({
|
||||
'source_entity_name': source,
|
||||
'target_entity_name': target,
|
||||
'relation_type': rtype,
|
||||
'fact': fact,
|
||||
'qualifiers': _as_str_list(relation.get('qualifiers')),
|
||||
'evidence': _as_str(relation.get('evidence')),
|
||||
'confidence': _as_float(relation.get('confidence')),
|
||||
'valid_at': _as_str(relation.get('valid_at')),
|
||||
'invalid_at': _as_str(relation.get('invalid_at')),
|
||||
})
|
||||
return items
|
||||
|
||||
|
||||
|
|
@ -316,15 +572,13 @@ def _normalize_action_items(value) -> List[dict]:
|
|||
for action in value:
|
||||
if not isinstance(action, dict):
|
||||
continue
|
||||
items.append(
|
||||
{
|
||||
"task": _as_str(action.get("task")),
|
||||
"assignee": _as_str(action.get("assignee")),
|
||||
"deadline": _as_str(action.get("deadline")),
|
||||
"status": _as_str(action.get("status")) or "待办",
|
||||
"priority": _as_str(action.get("priority")) or "中",
|
||||
}
|
||||
)
|
||||
items.append({
|
||||
'task': _as_str(action.get('task')),
|
||||
'assignee': _as_str(action.get('assignee')),
|
||||
'deadline': _as_str(action.get('deadline')),
|
||||
'status': _as_str(action.get('status')) or '待办',
|
||||
'priority': _as_str(action.get('priority')) or '中',
|
||||
})
|
||||
return items
|
||||
|
||||
|
||||
|
|
@ -335,13 +589,11 @@ def _normalize_decisions(value) -> List[dict]:
|
|||
for decision in value:
|
||||
if not isinstance(decision, dict):
|
||||
continue
|
||||
items.append(
|
||||
{
|
||||
"content": _as_str(decision.get("content")),
|
||||
"proposer": _as_str(decision.get("proposer")),
|
||||
"status": _as_str(decision.get("status")) or "已决",
|
||||
}
|
||||
)
|
||||
items.append({
|
||||
'content': _as_str(decision.get('content')),
|
||||
'proposer': _as_str(decision.get('proposer')),
|
||||
'status': _as_str(decision.get('status')) or '已决',
|
||||
})
|
||||
return items
|
||||
|
||||
|
||||
|
|
@ -352,13 +604,30 @@ def _normalize_metrics(value) -> List[dict]:
|
|||
for metric in value:
|
||||
if not isinstance(metric, dict):
|
||||
continue
|
||||
items.append(
|
||||
{
|
||||
"metric_name": _as_str(metric.get("metric_name")),
|
||||
"value": _as_str(metric.get("value")),
|
||||
"target": _as_str(metric.get("target")),
|
||||
"owner": _as_str(metric.get("owner")),
|
||||
"trend": _as_str(metric.get("trend")),
|
||||
}
|
||||
)
|
||||
items.append({
|
||||
'metric_name': _as_str(metric.get('metric_name')),
|
||||
'value': _as_str(metric.get('value')),
|
||||
'target': _as_str(metric.get('target')),
|
||||
'owner': _as_str(metric.get('owner')),
|
||||
'trend': _as_str(metric.get('trend')),
|
||||
'unit': _as_str(metric.get('unit')),
|
||||
})
|
||||
return items
|
||||
|
||||
|
||||
def _normalize_departments(value) -> List[dict]:
|
||||
if not isinstance(value, list):
|
||||
return []
|
||||
items = []
|
||||
for dept in value:
|
||||
if not isinstance(dept, dict):
|
||||
continue
|
||||
name = _as_str(dept.get('name'))
|
||||
if not name:
|
||||
continue
|
||||
items.append({
|
||||
'name': name,
|
||||
'description': _as_str(dept.get('description')),
|
||||
'projects': _as_str_list(dept.get('projects')),
|
||||
})
|
||||
return items
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load Diff
|
|
@ -1,9 +1,18 @@
|
|||
import hashlib
|
||||
import logging
|
||||
from typing import Callable, Optional
|
||||
from typing import Callable, List, Optional
|
||||
|
||||
from meeting_memory.config import config
|
||||
from meeting_memory.extractor import MeetingExtraction, extract_meeting_info
|
||||
from meeting_memory.extractor import (
|
||||
MeetingExtraction,
|
||||
extract_entities_from_text,
|
||||
extract_facts_from_text,
|
||||
extract_meeting_info as monolithic_extract,
|
||||
)
|
||||
from meeting_memory.extractor import (
|
||||
resolve_entities_against_graph,
|
||||
resolve_facts_against_graph,
|
||||
)
|
||||
from meeting_memory.graph_store import graph_store
|
||||
from meeting_memory.meeting_state import MeetingStateStore
|
||||
from meeting_memory.raw_store import raw_meeting_store
|
||||
|
|
@ -15,8 +24,9 @@ ProgressCallback = Callable[[int, int, str], None]
|
|||
|
||||
|
||||
class MeetingProcessor:
|
||||
|
||||
def process_meeting_file(self, filepath: str, force: bool = False) -> Optional[str]:
|
||||
with open(filepath, "r", encoding="utf-8") as file_obj:
|
||||
with open(filepath, 'r', encoding='utf-8') as file_obj:
|
||||
text = file_obj.read()
|
||||
return self.process_meeting_text(text, force=force)
|
||||
|
||||
|
|
@ -26,147 +36,313 @@ class MeetingProcessor:
|
|||
force: bool = False,
|
||||
interactive: bool = True,
|
||||
progress_callback: Optional[ProgressCallback] = None,
|
||||
use_multistep_extraction: bool = True,
|
||||
) -> Optional[str]:
|
||||
def report(step: int, message: str) -> None:
|
||||
def report(step: int, total: int, message: str) -> None:
|
||||
if progress_callback:
|
||||
progress_callback(step, 7, message)
|
||||
print(f"[{step}/7] {message}")
|
||||
progress_callback(step, total, message)
|
||||
print(f'[{step}/{total}] {message}')
|
||||
|
||||
report(1, "计算内容哈希")
|
||||
if use_multistep_extraction:
|
||||
return self._process_multistep(text, force, interactive, report)
|
||||
else:
|
||||
return self._process_monolithic(text, force, interactive, report)
|
||||
|
||||
def _process_monolithic(
|
||||
self, text: str, force: bool, interactive: bool,
|
||||
report: Callable,
|
||||
) -> Optional[str]:
|
||||
total_steps = 7
|
||||
report(1, total_steps, '计算内容哈希')
|
||||
content_hash = self._compute_content_hash(text)
|
||||
|
||||
if not force and state_store.has_content_hash(content_hash):
|
||||
logger.info("Duplicate content hash skipped: %s", content_hash[:12])
|
||||
logger.info('Duplicate content hash skipped: %s', content_hash[:12])
|
||||
return None
|
||||
|
||||
if not force:
|
||||
report(2, "Neo4j 语义相似去重检索")
|
||||
report(2, total_steps, 'Neo4j 语义相似去重检索')
|
||||
similar = graph_store.find_similar_episode(text, threshold=0.92)
|
||||
if similar:
|
||||
meta = similar["metadata"]
|
||||
meta = similar['metadata']
|
||||
if not interactive:
|
||||
logger.info(
|
||||
"Skipped similar meeting in non-interactive mode: %s",
|
||||
meta.get("title", ""),
|
||||
)
|
||||
logger.info('Skipped similar meeting: %s', meta.get('title', ''))
|
||||
return None
|
||||
|
||||
print(
|
||||
f"\n发现相似会议：{meta.get('title', '')} ({meta.get('date', '')}) "
|
||||
f"相似度 {similar['score']:.2%}"
|
||||
)
|
||||
print(f'\n发现相似会议：{meta.get("title", "")} ({meta.get("date", "")}) 相似度 {similar["score"]:.2%}')
|
||||
while True:
|
||||
choice = input("选择 [s]跳过 / [o]覆盖（默认 s）：").strip().lower() or "s"
|
||||
if choice == "s":
|
||||
logger.info("Skipped similar meeting: %s", meta.get("title", ""))
|
||||
choice = input('选择 [s]跳过 / [o]覆盖（默认 s）：').strip().lower() or 's'
|
||||
if choice == 's':
|
||||
logger.info('Skipped similar meeting: %s', meta.get('title', ''))
|
||||
return None
|
||||
if choice == "o":
|
||||
if choice == 'o':
|
||||
force = True
|
||||
break
|
||||
print("请输入 s 或 o。")
|
||||
print('请输入 s 或 o。')
|
||||
else:
|
||||
report(2, "跳过语义去重，按覆盖模式继续")
|
||||
report(2, total_steps, '跳过语义去重，按覆盖模式继续')
|
||||
|
||||
report(3, "调用大模型抽取结构化信息")
|
||||
meeting_data = self._extract(text)
|
||||
report(3, total_steps, '调用大模型抽取结构化信息（单步模式）')
|
||||
meeting_data = self._extract_monolithic(text)
|
||||
if not meeting_data:
|
||||
logger.error("Failed to extract meeting information")
|
||||
logger.error('Failed to extract meeting information')
|
||||
return None
|
||||
|
||||
data_dict = meeting_data.model_dump()
|
||||
data_dict["_content_hash"] = content_hash
|
||||
data_dict["_graph_meeting_id"] = graph_store.meeting_id(data_dict)
|
||||
return self._finish_pipeline(data_dict, content_hash, text, force, interactive, report, total_steps)
|
||||
|
||||
report(4, "检查标题和日期重复")
|
||||
def _process_multistep(
|
||||
self, text: str, force: bool, interactive: bool,
|
||||
report: Callable,
|
||||
) -> Optional[str]:
|
||||
total_steps = 10
|
||||
report(1, total_steps, '计算内容哈希')
|
||||
content_hash = self._compute_content_hash(text)
|
||||
|
||||
if not force and state_store.has_content_hash(content_hash):
|
||||
logger.info('Duplicate content hash skipped: %s', content_hash[:12])
|
||||
return None
|
||||
|
||||
if not force:
|
||||
report(2, total_steps, 'Neo4j 语义相似去重检索')
|
||||
similar = graph_store.find_similar_episode(text, threshold=0.92)
|
||||
if similar:
|
||||
meta = similar['metadata']
|
||||
if not interactive:
|
||||
logger.info('Skipped similar meeting: %s', meta.get('title', ''))
|
||||
return None
|
||||
print(f'\n发现相似会议：{meta.get("title", "")} ({meta.get("date", "")}) 相似度 {similar["score"]:.2%}')
|
||||
while True:
|
||||
choice = input('选择 [s]跳过 / [o]覆盖（默认 s）：').strip().lower() or 's'
|
||||
if choice == 's':
|
||||
logger.info('Skipped similar meeting: %s', meta.get('title', ''))
|
||||
return None
|
||||
if choice == 'o':
|
||||
force = True
|
||||
break
|
||||
print('请输入 s 或 o。')
|
||||
else:
|
||||
report(2, total_steps, '跳过语义去重，按覆盖模式继续')
|
||||
|
||||
# Step 3: 提取标题、日期、参与人等元信息
|
||||
report(3, total_steps, '抽取会议元信息（标题、日期、参与者等）')
|
||||
meta_info = self._extract_monolithic(text, stream=interactive)
|
||||
if not meta_info:
|
||||
logger.error('Failed to extract meeting metadata')
|
||||
return None
|
||||
data_dict = meta_info.model_dump()
|
||||
data_dict['_content_hash'] = content_hash
|
||||
data_dict['_graph_meeting_id'] = graph_store.meeting_id(data_dict)
|
||||
data_dict['_original_text'] = text
|
||||
|
||||
# Step 4: 抽取实体节点（LLM 调用 1）
|
||||
report(4, total_steps, '第 1 步实体抽取：识别会议中提及的实体')
|
||||
use_stream = interactive
|
||||
previous_episodes = self._get_previous_episodes_context(data_dict)
|
||||
extracted_entities = extract_entities_from_text(
|
||||
text, previous_episodes=previous_episodes, stream=use_stream
|
||||
)
|
||||
logger.info('Extracted %d entities from meeting', len(extracted_entities))
|
||||
if not extracted_entities:
|
||||
logger.warning('No entities extracted, aborting')
|
||||
return None
|
||||
|
||||
# Step 5: 实体去重（与已有图谱对比 + LLM 裁决）
|
||||
report(5, total_steps, '实体去重：与图谱中已有实体对比')
|
||||
resolved_entities = self._dedup_entities(extracted_entities, text)
|
||||
data_dict['entities'] = resolved_entities
|
||||
logger.info('After dedup: %d entities remain', len(resolved_entities))
|
||||
|
||||
# Step 6: 抽取事实关系（LLM 调用 2）
|
||||
report(6, total_steps, '事实抽取：提取实体间的结构化关系')
|
||||
reference_time = data_dict.get('date', '')
|
||||
extracted_facts = extract_facts_from_text(
|
||||
text, resolved_entities,
|
||||
reference_time=reference_time,
|
||||
previous_episodes=previous_episodes,
|
||||
stream=use_stream,
|
||||
)
|
||||
logger.info('Extracted %d facts from meeting', len(extracted_facts))
|
||||
|
||||
# Step 7: 事实去重与矛盾检测
|
||||
report(7, total_steps, '事实解析：去重与矛盾检测')
|
||||
resolved_facts = self._dedup_facts(extracted_facts, data_dict)
|
||||
data_dict['relations'] = resolved_facts
|
||||
logger.info('After dedup: %d facts remain', len(resolved_facts))
|
||||
|
||||
# Step 8: 检查标题和日期重复
|
||||
report(8, total_steps, '检查标题和日期重复')
|
||||
should_skip = self._handle_duplicate(data_dict, force=force, interactive=interactive)
|
||||
if should_skip:
|
||||
return None
|
||||
|
||||
meeting_title = data_dict.get("title", "")
|
||||
meeting_date = data_dict.get("date", "")
|
||||
meeting_title = data_dict.get('title', '')
|
||||
meeting_date = data_dict.get('date', '')
|
||||
|
||||
report(5, "归档原始会议文本")
|
||||
# Step 9: 归档 + 合并行动项/指标
|
||||
report(9, total_steps, '归档和状态合并')
|
||||
raw_path = raw_meeting_store.save(text, title=meeting_title, date=meeting_date)
|
||||
data_dict["_original_text"] = text
|
||||
data_dict["_original_text_path"] = raw_path
|
||||
data_dict['_original_text_path'] = raw_path
|
||||
|
||||
meeting_filename = f"{graph_store.meeting_id(data_dict)}.md"
|
||||
|
||||
report(6, "合并行动项和指标状态")
|
||||
data_dict["action_items"] = state_store.merge_action_items(
|
||||
data_dict.get("action_items", []),
|
||||
meeting_title,
|
||||
meeting_date,
|
||||
meeting_filename,
|
||||
meeting_filename = f'{graph_store.meeting_id(data_dict)}.md'
|
||||
data_dict['action_items'] = state_store.merge_action_items(
|
||||
data_dict.get('action_items', []),
|
||||
meeting_title, meeting_date, meeting_filename,
|
||||
)
|
||||
data_dict["metrics"] = state_store.merge_metrics(
|
||||
data_dict.get("metrics", []),
|
||||
meeting_title,
|
||||
meeting_date,
|
||||
meeting_filename,
|
||||
data_dict['metrics'] = state_store.merge_metrics(
|
||||
data_dict.get('metrics', []),
|
||||
meeting_title, meeting_date, meeting_filename,
|
||||
)
|
||||
|
||||
state_store.add_content_hash(content_hash, meeting_title, meeting_date, meeting_filename)
|
||||
state_store.save()
|
||||
|
||||
report(7, "写入 Neo4j 图谱和检索数据")
|
||||
# Step 10: 写入 Neo4j
|
||||
report(10, total_steps, '写入 Neo4j 图谱')
|
||||
graph_store.upsert_meeting_subgraph(data_dict)
|
||||
|
||||
logger.info("Meeting processed: %s", meeting_title)
|
||||
logger.info('Meeting processed (multi-step): %s', meeting_title)
|
||||
return raw_path
|
||||
|
||||
def _get_previous_episodes_context(self, data_dict: dict) -> list:
|
||||
meeting_title = data_dict.get('title', '')
|
||||
meeting_date = data_dict.get('date', '')
|
||||
series_info = state_store.get_series_info(meeting_title)
|
||||
if not series_info:
|
||||
return []
|
||||
processed = series_info.get('processed_titles', [])
|
||||
if not processed:
|
||||
return []
|
||||
rows = graph_store.run_query('''
|
||||
MATCH (m:Meeting)
|
||||
WHERE m.title IN $titles
|
||||
OPTIONAL MATCH (m)-[:HAS_EPISODE]->(ep:Episode)
|
||||
RETURN m.title AS title, m.date AS date, ep.summary AS summary, ep.content AS content
|
||||
ORDER BY m.date DESC
|
||||
LIMIT 3
|
||||
''', titles=processed[-3:])
|
||||
return [{'content': r.get('content', r.get('summary', '')), 'timestamp': r.get('date', '')} for r in rows]
|
||||
|
||||
def _dedup_entities(self, extracted: list, text: str) -> list:
|
||||
try:
|
||||
existing = graph_store.get_entities_map()
|
||||
if not existing:
|
||||
return extracted
|
||||
existing_list = [
|
||||
{
|
||||
'candidate_id': i,
|
||||
'name': v['name'],
|
||||
'entity_type': v.get('entity_type', ''),
|
||||
'summary': v.get('summary', '') or v.get('description', ''),
|
||||
}
|
||||
for i, v in enumerate(existing.values())
|
||||
]
|
||||
return resolve_entities_against_graph(extracted, existing_list, episode_content=text)
|
||||
except Exception as exc:
|
||||
logger.warning('Entity dedup failed, keeping all extracted: %s', exc)
|
||||
return extracted
|
||||
|
||||
def _dedup_facts(self, facts: list, data_dict: dict) -> list:
|
||||
resolved = []
|
||||
for fact in facts:
|
||||
try:
|
||||
source = fact.get('source_entity_name', '')
|
||||
target = fact.get('target_entity_name', '')
|
||||
existing = graph_store.get_facts_between(source, target)
|
||||
if not existing:
|
||||
resolved.append(fact)
|
||||
continue
|
||||
result = resolve_facts_against_graph(fact, existing, [])
|
||||
if isinstance(result, dict) and result.get('is_duplicate'):
|
||||
logger.debug('Skipped duplicate fact: %s', fact.get('fact', ''))
|
||||
continue
|
||||
resolved.append(fact)
|
||||
except Exception as exc:
|
||||
logger.warning('Fact dedup failed, keeping: %s', exc)
|
||||
resolved.append(fact)
|
||||
return resolved
|
||||
|
||||
def _finish_pipeline(
|
||||
self, data_dict: dict, content_hash: str, text: str,
|
||||
force: bool, interactive: bool, report: Callable, total_steps: int,
|
||||
) -> Optional[str]:
|
||||
data_dict['_content_hash'] = content_hash
|
||||
data_dict['_graph_meeting_id'] = graph_store.meeting_id(data_dict)
|
||||
|
||||
report(4, total_steps, '检查标题和日期重复')
|
||||
should_skip = self._handle_duplicate(data_dict, force=force, interactive=interactive)
|
||||
if should_skip:
|
||||
return None
|
||||
|
||||
meeting_title = data_dict.get('title', '')
|
||||
meeting_date = data_dict.get('date', '')
|
||||
|
||||
report(5, total_steps, '归档原始会议文本')
|
||||
raw_path = raw_meeting_store.save(text, title=meeting_title, date=meeting_date)
|
||||
data_dict['_original_text'] = text
|
||||
data_dict['_original_text_path'] = raw_path
|
||||
|
||||
meeting_filename = f'{graph_store.meeting_id(data_dict)}.md'
|
||||
|
||||
report(6, total_steps, '合并行动项和指标状态')
|
||||
data_dict['action_items'] = state_store.merge_action_items(
|
||||
data_dict.get('action_items', []), meeting_title, meeting_date, meeting_filename,
|
||||
)
|
||||
data_dict['metrics'] = state_store.merge_metrics(
|
||||
data_dict.get('metrics', []), meeting_title, meeting_date, meeting_filename,
|
||||
)
|
||||
state_store.add_content_hash(content_hash, meeting_title, meeting_date, meeting_filename)
|
||||
state_store.save()
|
||||
|
||||
report(7, total_steps, '写入 Neo4j 图谱和检索数据')
|
||||
graph_store.upsert_meeting_subgraph(data_dict)
|
||||
|
||||
logger.info('Meeting processed: %s', meeting_title)
|
||||
return raw_path
|
||||
|
||||
def _handle_duplicate(self, data_dict: dict, force: bool, interactive: bool = True) -> bool:
|
||||
title = data_dict.get("title", "")
|
||||
date = data_dict.get("date", "")
|
||||
title = data_dict.get('title', '')
|
||||
date = data_dict.get('date', '')
|
||||
existing = graph_store.get_meeting(title, date)
|
||||
|
||||
if not existing:
|
||||
return False
|
||||
|
||||
if force:
|
||||
logger.info("Duplicate meeting found; overwriting in force mode: %s", title)
|
||||
logger.info('Duplicate meeting found; overwriting in force mode: %s', title)
|
||||
self._remove_old(data_dict, existing)
|
||||
return False
|
||||
|
||||
if not interactive:
|
||||
logger.info("Skipped duplicate meeting in non-interactive mode: %s", title)
|
||||
logger.info('Skipped duplicate meeting in non-interactive mode: %s', title)
|
||||
return True
|
||||
|
||||
print(f"\n发现重复会议：{title} ({date})")
|
||||
print(f'\n发现重复会议：{title} ({date})')
|
||||
while True:
|
||||
choice = input("选择 [s]跳过 / [o]覆盖（默认 s）：").strip().lower() or "s"
|
||||
if choice == "s":
|
||||
logger.info("Skipped duplicate meeting: %s", title)
|
||||
choice = input('选择 [s]跳过 / [o]覆盖（默认 s）：').strip().lower() or 's'
|
||||
if choice == 's':
|
||||
logger.info('Skipped duplicate meeting: %s', title)
|
||||
return True
|
||||
if choice == "o":
|
||||
if choice == 'o':
|
||||
self._remove_old(data_dict, existing)
|
||||
return False
|
||||
print("请输入 s 或 o。")
|
||||
print('请输入 s 或 o。')
|
||||
|
||||
def _remove_old(self, data_dict: dict, existing: Optional[dict] = None) -> None:
|
||||
meeting_id = graph_store.meeting_id(data_dict)
|
||||
graph_store.remove_meeting_subgraph(meeting_id)
|
||||
|
||||
new_hash = data_dict.get("_content_hash", "")
|
||||
new_hash = data_dict.get('_content_hash', '')
|
||||
if new_hash:
|
||||
state_store.remove_content_hash(new_hash)
|
||||
|
||||
if existing:
|
||||
old_hash = existing.get("content_hash", "")
|
||||
old_hash = existing.get('content_hash', '')
|
||||
if old_hash and old_hash != new_hash:
|
||||
state_store.remove_content_hash(old_hash)
|
||||
|
||||
logger.info("Removed old meeting artifacts: %s", data_dict.get("title", ""))
|
||||
logger.info('Removed old meeting artifacts: %s', data_dict.get('title', ''))
|
||||
|
||||
def _compute_content_hash(self, text: str) -> str:
|
||||
normalized = text.strip().replace("\r\n", "\n")
|
||||
return hashlib.sha256(normalized.encode("utf-8")).hexdigest()
|
||||
normalized = text.strip().replace('\r\n', '\n')
|
||||
return hashlib.sha256(normalized.encode('utf-8')).hexdigest()
|
||||
|
||||
def _extract(self, text: str) -> Optional[MeetingExtraction]:
|
||||
def _extract_monolithic(self, text: str, *, stream: bool = True) -> Optional[MeetingExtraction]:
|
||||
try:
|
||||
return extract_meeting_info(text, stream=True)
|
||||
return monolithic_extract(text, stream=stream)
|
||||
except Exception as exc:
|
||||
logger.error("LLM extraction failed: %s", exc)
|
||||
logger.error('LLM extraction failed: %s', exc)
|
||||
return None
|
||||
|
||||
def query(self, question: str, top_k: int = 3) -> str:
|
||||
|
|
@ -174,10 +350,10 @@ class MeetingProcessor:
|
|||
|
||||
def stats(self) -> dict:
|
||||
return {
|
||||
"graph": graph_store.get_stats(),
|
||||
"state": state_store.get_stats(),
|
||||
"raw_dir": config.storage.raw_dir,
|
||||
"state_path": config.state_path,
|
||||
'graph': graph_store.get_stats(),
|
||||
'state': state_store.get_stats(),
|
||||
'raw_dir': config.storage.raw_dir,
|
||||
'state_path': config.state_path,
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,5 @@
|
|||
from .extract_nodes import extract_entities
|
||||
from .extract_edges import extract_facts
|
||||
from .dedupe_nodes import resolve_entities
|
||||
from .dedupe_edges import resolve_facts
|
||||
from .summarize_nodes import summarize_entity
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
from typing import Any
|
||||
|
||||
|
||||
def resolve_facts(context: dict[str, Any]) -> list[dict]:
|
||||
existing_facts = context.get('existing_facts', [])
|
||||
new_fact = context.get('new_fact', '')
|
||||
invalidation_candidates = context.get('invalidation_candidates', [])
|
||||
|
||||
existing_text = '\n'.join(
|
||||
f' [idx={i}] {f.get("fact", "")}' for i, f in enumerate(existing_facts)
|
||||
)
|
||||
|
||||
invalidation_text = '\n'.join(
|
||||
f' [idx={i + len(existing_facts)}] {f.get("fact", "")}'
|
||||
for i, f in enumerate(invalidation_candidates)
|
||||
)
|
||||
|
||||
user_prompt = f"""
|
||||
<已有事实>
|
||||
{existing_text}
|
||||
</已有事实>
|
||||
|
||||
<事实失效候选>
|
||||
{invalidation_text}
|
||||
</事实失效候选>
|
||||
|
||||
<新事实>
|
||||
{new_fact}
|
||||
</新事实>
|
||||
|
||||
注意：idx 编号是连续的——已有事实从 0 开始，失效候选紧随其后。
|
||||
|
||||
任务：
|
||||
1. **重复检测**：如果<新事实>与<已有事实>中的某条描述的是完全相同的客观事实，返回该 idx。
|
||||
2. **矛盾检测**：如果<新事实>与<已有事实>或<失效候选>中的某条相互矛盾（如状态已更新、数值已变更），返回该 idx。
|
||||
|
||||
返回格式：
|
||||
{{"duplicate_facts": [idx列表], "contradicted_facts": [idx列表]}}
|
||||
如果没有重复或矛盾，返回空列表。
|
||||
|
||||
示例：
|
||||
- 新事实："张三负责宽带运维项目" vs 已有："张三负责宽带运维" → 重复（相同事实）
|
||||
- 新事实："宽带用户数当前值 8500" vs 已有："宽带用户数目标值 10000" → 不重复，不矛盾（数值维度不同）
|
||||
- 新事实："宽带用户数当前值 9000" vs 已有："宽带用户数 8000" → 矛盾（同一指标数值更新）
|
||||
"""
|
||||
return [
|
||||
{'role': 'system', 'content': '你是事实去重和矛盾检测助手。判断新事实与已有事实的关系。'},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
]
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
from typing import Any
|
||||
|
||||
|
||||
def resolve_entities(context: dict[str, Any]) -> list[dict]:
|
||||
extracted = context.get('extracted_entities', [])
|
||||
existing = context.get('existing_entities', [])
|
||||
episode_content = context.get('episode_content', '')
|
||||
|
||||
extracted_text = '\n'.join(
|
||||
f' [{i}] {e.get("name", "")}（{e.get("entity_type", "未知")}）：{e.get("description", "")}'
|
||||
for i, e in enumerate(extracted)
|
||||
)
|
||||
|
||||
existing_text = '\n'.join(
|
||||
f' [candidate_id={c.get("candidate_id", i)}] {c.get("name", "")}（{c.get("entity_type", "未知")}）：{c.get("summary", "")[:100]}'
|
||||
for i, c in enumerate(existing)
|
||||
)
|
||||
|
||||
user_prompt = f"""
|
||||
<当前会议内容>
|
||||
{episode_content}
|
||||
</当前会议内容>
|
||||
|
||||
<新抽取的实体>
|
||||
{extracted_text}
|
||||
</新抽取的实体>
|
||||
|
||||
<图谱中已有的实体>
|
||||
{existing_text}
|
||||
</图谱中已有的实体>
|
||||
|
||||
任务：判断<新抽取的实体>中的每一个是否与<图谱中已有的实体>中的某个是同一个真实世界对象。
|
||||
|
||||
判断标准：
|
||||
- **是重复**：两个名称指向同一个真实世界的人、组织、地点、项目、指标等。
|
||||
- **不是重复**：名称相似但指向不同实体（如两个同名但不同的人、同名的不同项目）。
|
||||
|
||||
对每个新抽取的实体，返回：
|
||||
- id: 对应新抽取实体列表中的序号
|
||||
- name: 实体的最佳名称（优先使用已有实体中的更完整名称）
|
||||
- duplicate_candidate_id: 匹配到的已有实体的 candidate_id，如果无匹配则填 -1
|
||||
|
||||
返回格式 JSON 数组：[{{"id": 0, "name": "张三", "duplicate_candidate_id": -1}}, ...]
|
||||
必须为新抽取的每个实体返回一条记录。id 从 0 开始连续编号。
|
||||
"""
|
||||
return [
|
||||
{'role': 'system', 'content': '你是实体去重助手。判断两个实体是否指向同一个真实世界对象。'},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
]
|
||||
|
|
@ -0,0 +1,66 @@
|
|||
from typing import Any
|
||||
|
||||
|
||||
def extract_facts(context: dict[str, Any]) -> list[dict]:
|
||||
previous = context.get('previous_episodes', [])
|
||||
current = context.get('episode_content', '')
|
||||
entities = context.get('entities', [])
|
||||
reference_time = context.get('reference_time', '')
|
||||
|
||||
previous_section = ''
|
||||
if previous:
|
||||
import json
|
||||
previous_section = f'\n<历史上下文>\n{json.dumps(previous, ensure_ascii=False)}\n</历史上下文>\n'
|
||||
|
||||
entities_text = '\n'.join(
|
||||
f' [{i}] {e.get("name", "")}（{e.get("entity_type", "未知")}）' for i, e in enumerate(entities)
|
||||
)
|
||||
|
||||
user_prompt = f"""
|
||||
{previous_section}
|
||||
<当前会议内容>
|
||||
{current}
|
||||
</当前会议内容>
|
||||
|
||||
<已抽取实体>
|
||||
{entities_text}
|
||||
</已抽取实体>
|
||||
|
||||
<参考时间>
|
||||
{reference_time}
|
||||
</参考时间>
|
||||
|
||||
抽取规则：
|
||||
1. 从<当前会议内容>中抽取上述<已抽取实体>之间的**事实关系**。
|
||||
2. 每条关系必须涉及两个**不同**的实体。
|
||||
3. 返回 JSON 数组，格式：
|
||||
[{{
|
||||
"source_entity_name": "源实体名称（必须来自上方的实体列表）",
|
||||
"target_entity_name": "目标实体名称（必须来自上方的实体列表）",
|
||||
"relation_type": "关系类型，如 负责、汇报、隶属于、参与、目标值、截止于、影响、依赖于",
|
||||
"fact": "一句自然语言的事实描述，保留原文中所有具体细节（数值、时间、地点等）",
|
||||
"valid_at": "该事实开始成立的时间（ISO 8601格式，如 2025-04-30T00:00:00Z），不明确则留空",
|
||||
"invalid_at": "该事实不再成立的时间，不明确则留空",
|
||||
"evidence": "原文中的关键证据短句",
|
||||
"qualifiers": ["限定条件列表，如数值、范围、状态、截止时间等"],
|
||||
"confidence": 置信度0到1之间
|
||||
}}]
|
||||
|
||||
4. relation_type 避免使用"关联""涉及"等空泛词，优先使用具体谓词：
|
||||
负责、汇报、目标值、当前值、低于、高于、要求、督导、推进、支撑、依赖、计划、完成、截止于、参与、隶属于、分管、协调、审批
|
||||
|
||||
5. 层次关系（结构隶属）使用以下固定 relation_type：
|
||||
HAS_PROJECT: 部门管辖项目（Department -> Project）
|
||||
HAS_METRIC: 项目拥有指标（Project -> Metric）
|
||||
PART_OF: 实体属于某个上级实体
|
||||
|
||||
6. 同一对实体之间可能既有层次关系（HAS_PROJECT）也有事实关系（负责、汇报），需要分别抽取。
|
||||
|
||||
7. fact 必须是一句完整的自然语言事实，保留所有具体信息（人名、数值、产品名、地点等）。
|
||||
|
||||
8. 如果根据上下文可以判断事实的开始/结束时间，填入 valid_at / invalid_at。
|
||||
"""
|
||||
return [
|
||||
{'role': 'system', 'content': '你是一个专业的事实关系抽取专家。从会议记录中抽取实体间的结构化事实关系。'},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
]
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
from typing import Any
|
||||
|
||||
|
||||
SYSTEM_PROMPT = (
|
||||
'你是会议纪要实体抽取专家。'
|
||||
'从会议记录中抽取明确的实体节点，包括部门（Department）、项目（Project）、指标（Metric）、人物（Person）、系统（System）、文档（Document）等。'
|
||||
'不要抽取抽象概念、情感、时间日期或泛泛的名词。'
|
||||
)
|
||||
|
||||
|
||||
def extract_entities(context: dict[str, Any]) -> list[dict]:
|
||||
previous = context.get('previous_episodes', [])
|
||||
current = context.get('episode_content', '')
|
||||
entity_types = context.get('entity_types', [])
|
||||
|
||||
entity_types_section = ''
|
||||
if entity_types:
|
||||
entity_types_section = '\n'.join(
|
||||
f' - {t["type"]}: {t["description"]}' for t in entity_types
|
||||
)
|
||||
else:
|
||||
entity_types_section = ' - 未限定类型，请根据上下文自行判断'
|
||||
|
||||
previous_section = ''
|
||||
if previous:
|
||||
import json
|
||||
previous_section = f'\n<历史上下文>\n{json.dumps(previous, ensure_ascii=False)}\n</历史上下文>\n'
|
||||
|
||||
user_prompt = f"""
|
||||
{previous_section}
|
||||
<当前会议内容>
|
||||
{current}
|
||||
</当前会议内容>
|
||||
|
||||
<实体类型>
|
||||
{entity_types_section}
|
||||
</实体类型>
|
||||
|
||||
抽取规则：
|
||||
1. 只抽取当前会议内容中**明确提及**的实体。
|
||||
2. 每个实体必须是有唯一标识的具体事物——人名、组织名、地名、项目名、指标名称等。
|
||||
3. 不要抽取：代词（他、她、它、这、那）、抽象概念（增长、改善、风险）、时间日期。
|
||||
4. 如果同一实体在不同来源中以不同名称出现（如简称/全称），保留最完整的形式。
|
||||
5. 必须返回 JSON 数组，格式：[{{"name": "实体名称", "entity_type": "类型", "description": "描述", "evidence": "原文证据"}}]
|
||||
6. description 写一段对该实体的简要描述（20字以内）。
|
||||
7. evidence 从原文中摘录提及该实体的关键短句。
|
||||
|
||||
注意：实体类型建议使用 Department（部门）、Project（项目）、Metric（指标）、Person（人物）、System（系统）、Document（文档）等。请确保：
|
||||
- 部门（Department）：会议中提到的具体部门名称，如"技术部"、"市场部"。
|
||||
- 项目（Project）：部门负责的具体项目名称。
|
||||
- 指标（Metric）：项目中提到的具体量化指标，如"响应时间"、"完成率"。
|
||||
"""
|
||||
return [
|
||||
{'role': 'system', 'content': SYSTEM_PROMPT},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
]
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
from typing import Any
|
||||
|
||||
|
||||
def summarize_entity(context: dict[str, Any]) -> list[dict]:
|
||||
entity_name = context.get('entity_name', '')
|
||||
existing_summary = context.get('existing_summary', '')
|
||||
episodes = context.get('episodes', [])
|
||||
previous = context.get('previous_episodes', [])
|
||||
|
||||
existing_section = ''
|
||||
if existing_summary:
|
||||
existing_section = f'\n<已有摘要>\n{existing_summary}\n</已有摘要>\n'
|
||||
|
||||
previous_section = ''
|
||||
if previous:
|
||||
import json
|
||||
previous_section = f'\n<历史内容>\n{json.dumps(previous, ensure_ascii=False)}\n</历史内容>\n'
|
||||
|
||||
episodes_text = '\n---\n'.join(episodes) if isinstance(episodes, list) else episodes
|
||||
|
||||
user_prompt = f"""
|
||||
{previous_section}
|
||||
<当前内容>
|
||||
{episodes_text}
|
||||
</当前内容>
|
||||
{existing_section}
|
||||
为实体 **{entity_name}** 生成一段信息密集的摘要。
|
||||
|
||||
规则：
|
||||
1. 只使用<当前内容>和<已有摘要>中的事实。不要推测。
|
||||
2. 保留所有实质性的人名、角色、地点、日期、数值。
|
||||
3. 用第三人称直接陈述事实。
|
||||
4. 不要使用"提及了""讨论了""指出"等元语言动词。直接陈述事实。
|
||||
5. 如果会议对已有信息做了更新，采用更新的说法。
|
||||
6. 摘要不超过 500 字。
|
||||
7. 返回 JSON：{{"summary": "摘要内容"}}
|
||||
"""
|
||||
return [
|
||||
{'role': 'system', 'content': '你是实体摘要助手。根据会议内容为实体生成信息密集的摘要。'},
|
||||
{'role': 'user', 'content': user_prompt},
|
||||
]
|
||||
|
|
@ -20,6 +20,7 @@ from meeting_memory.meeting_processor import meeting_processor, state_store
|
|||
logger = logging.getLogger(__name__)
|
||||
|
||||
STATIC_DIR = Path(__file__).resolve().parent / "static"
|
||||
STATIC_V2_DIR = Path(__file__).resolve().parent / "static_v2"
|
||||
RAW_DIR = Path(config.storage.raw_dir)
|
||||
IMPORT_JOBS = {}
|
||||
IMPORT_JOBS_LOCK = threading.Lock()
|
||||
|
|
@ -29,8 +30,22 @@ class GraphDemoHandler(SimpleHTTPRequestHandler):
|
|||
def __init__(self, *args, **kwargs):
|
||||
super().__init__(*args, directory=str(STATIC_DIR), **kwargs)
|
||||
|
||||
# ── Route: serve /static_v2/* from the v2 directory ──
|
||||
def translate_path(self, path):
|
||||
parsed = urlparse(path)
|
||||
raw = parsed.path
|
||||
|
||||
# Serve /static_v2/* from static_v2 directory
|
||||
if raw.startswith("/static_v2/"):
|
||||
rel = raw[len("/static_v2/"):]
|
||||
return str(STATIC_V2_DIR / rel)
|
||||
|
||||
return super().translate_path(path)
|
||||
|
||||
def do_GET(self):
|
||||
parsed = urlparse(self.path)
|
||||
|
||||
# API endpoints
|
||||
if parsed.path == "/api/dashboard":
|
||||
self._handle_dashboard()
|
||||
return
|
||||
|
|
@ -55,10 +70,16 @@ class GraphDemoHandler(SimpleHTTPRequestHandler):
|
|||
if parsed.path == "/api/import-status":
|
||||
self._handle_import_status(parsed.query)
|
||||
return
|
||||
|
||||
# Page routing — serve v2 HTML as default
|
||||
if parsed.path in ("/", "/index.html"):
|
||||
self.path = "/index.html"
|
||||
self.path = "/static_v2/index.html"
|
||||
elif parsed.path == "/graph":
|
||||
self.path = "/graph.html"
|
||||
self.path = "/static_v2/graph.html"
|
||||
elif parsed.path == "/graph.html":
|
||||
self.path = "/static_v2/graph.html"
|
||||
|
||||
# JS files (/app.js, /graph.js) resolve to STATIC_DIR via default translate_path
|
||||
super().do_GET()
|
||||
|
||||
def do_POST(self):
|
||||
|
|
@ -311,9 +332,9 @@ def _serialize_meeting(path: Path, include_content: bool = False):
|
|||
lines = raw_text.splitlines()
|
||||
for line in lines[:12]:
|
||||
if line.startswith('title: "'):
|
||||
title = line[len('title: "') : -1]
|
||||
title = line[len('title: "'):-1]
|
||||
elif line.startswith('date: "'):
|
||||
date = line[len('date: "') : -1]
|
||||
date = line[len('date: "'):-1]
|
||||
|
||||
content_start = 0
|
||||
for idx, line in enumerate(lines):
|
||||
|
|
@ -397,4 +418,4 @@ if __name__ == "__main__":
|
|||
format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
|
||||
datefmt="%H:%M:%S",
|
||||
)
|
||||
run_demo_server()
|
||||
run_demo_server()
|
||||
|
|
@ -85,7 +85,7 @@ function renderStats(graph = {}, state = {}) {
|
|||
{ label: "Neo4j", value: graph.enabled ? "在线" : "离线", icon: "⬡", color: graph.enabled ? "#34c759" : "#b3261e" },
|
||||
{ label: "会议", value: graph.meetings ?? 0, icon: "📋", color: "#4a90d9" },
|
||||
{ label: "实体", value: graph.entities ?? 0, icon: "◆", color: "#53c2da" },
|
||||
{ label: "关系", value: graph.facts ?? 0, icon: "↗", color: "#ff9500" },
|
||||
{ label: "关系", value: graph.relations ?? 0, icon: "↗", color: "#ff9500" },
|
||||
{ label: "行动项", value: state.action_items_tracked ?? 0, icon: "☐", color: "#7f8bff" },
|
||||
{ label: "指标", value: state.metrics_tracked ?? 0, icon: "📊", color: "#af52de" },
|
||||
];
|
||||
|
|
|
|||
|
|
@ -4,8 +4,7 @@ const graphNodeLimit = document.getElementById("graphNodeLimit");
|
|||
const graphEdgeLimit = document.getElementById("graphEdgeLimit");
|
||||
const graphSvg = document.getElementById("graphSvg");
|
||||
const graphMeta = document.getElementById("graphMeta");
|
||||
const graphDetail = document.getElementById("graphDetail");
|
||||
const relatedSearch = document.getElementById("relatedSearch");
|
||||
const detailPanel = document.getElementById("detailPanel");
|
||||
const graphTypeFilter = document.getElementById("graphTypeFilter");
|
||||
|
||||
let selectedEntityTypes = null;
|
||||
|
|
@ -76,35 +75,35 @@ async function loadGraphKinds() {
|
|||
}
|
||||
|
||||
function renderInspector(content) {
|
||||
graphDetail.innerHTML = content;
|
||||
detailPanel.innerHTML = content;
|
||||
}
|
||||
|
||||
async function loadRelated(query) {
|
||||
if (!query) {
|
||||
relatedSearch.innerHTML = "";
|
||||
return;
|
||||
}
|
||||
if (!query) return;
|
||||
const response = await fetch(`/api/search?q=${encodeURIComponent(query)}&limit=4`);
|
||||
const payload = await response.json();
|
||||
const results = payload.results || [];
|
||||
if (!results.length) {
|
||||
relatedSearch.innerHTML = empty("没有更多相关检索结果");
|
||||
detailPanel.insertAdjacentHTML("beforeend", `
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Related</p>
|
||||
<div class="empty-state">没有更多相关检索结果</div>
|
||||
</div>
|
||||
`);
|
||||
return;
|
||||
}
|
||||
relatedSearch.innerHTML = `
|
||||
<div class="panel-head">
|
||||
<div>
|
||||
<p class="eyebrow">Related</p>
|
||||
<h3>相关检索</h3>
|
||||
</div>
|
||||
detailPanel.insertAdjacentHTML("beforeend", `
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Related</p>
|
||||
<h3>相关检索</h3>
|
||||
${results.map((item) => `
|
||||
<article class="result-card">
|
||||
<strong>${h(item.title || item.kind || "结果")}</strong>
|
||||
<p>${h(item.text || "")}</p>
|
||||
</article>
|
||||
`).join("")}
|
||||
</div>
|
||||
${results.map((item) => `
|
||||
<article class="result-card">
|
||||
<strong>${h(item.title || item.kind || "结果")}</strong>
|
||||
<p>${h(item.text || "")}</p>
|
||||
</article>
|
||||
`).join("")}
|
||||
`;
|
||||
`);
|
||||
}
|
||||
|
||||
function renderGraph(payload) {
|
||||
|
|
@ -125,7 +124,6 @@ function renderGraph(payload) {
|
|||
if (!nodes.length) {
|
||||
graphSvg.innerHTML = "";
|
||||
renderInspector(empty("当前没有可显示的图谱数据"));
|
||||
relatedSearch.innerHTML = "";
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
@ -201,7 +199,6 @@ function renderGraph(payload) {
|
|||
text.setAttribute("y", r + 16);
|
||||
text.setAttribute("text-anchor", "middle");
|
||||
text.setAttribute("font-size", "11");
|
||||
text.setAttribute("fill", "#22264d");
|
||||
text.setAttribute("data-type", "node-label");
|
||||
text.textContent = truncate(node.label, TRUNCATE_LENGTH);
|
||||
g.appendChild(text);
|
||||
|
|
@ -392,36 +389,47 @@ function renderGraph(payload) {
|
|||
${node.date ? `<span class="chip">${h(node.date)}</span>` : ""}
|
||||
<span class="chip">关系 ${h(related.length)}</span>
|
||||
</div>`;
|
||||
} else if (kind === "fact") {
|
||||
body = `
|
||||
<p>${h(node.fact || node.description || "暂无描述")}</p>
|
||||
<div class="chip-row">
|
||||
${node.date ? `<span class="chip">${h(node.date)}</span>` : ""}
|
||||
<span class="chip">关系 ${h(related.length)}</span>
|
||||
</div>`;
|
||||
} else {
|
||||
const isMetric = (node.entity_type || "").toLowerCase() === "metric";
|
||||
body = `
|
||||
<p>${h(node.description || "暂无描述")}</p>
|
||||
<div class="chip-row">
|
||||
${node.entity_type ? `<span class="chip">${h(node.entity_type)}</span>` : ""}
|
||||
${node.date ? `<span class="chip">${h(node.date)}</span>` : ""}
|
||||
<span class="chip">关系 ${h(related.length)}</span>
|
||||
</div>`;
|
||||
</div>
|
||||
${isMetric ? `
|
||||
<div class="metric-fields">
|
||||
${node.current_value ? `<p><strong>当前值：</strong>${h(node.current_value)}</p>` : ""}
|
||||
${node.target ? `<p><strong>目标值：</strong>${h(node.target)}</p>` : ""}
|
||||
${node.unit ? `<p><strong>单位：</strong>${h(node.unit)}</p>` : ""}
|
||||
${node.trend ? `<p><strong>趋势：</strong>${h(node.trend)}</p>` : ""}
|
||||
</div>` : ""}`;
|
||||
}
|
||||
renderInspector(`
|
||||
<div class="detail-card">
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">${h(node.kind)}</p>
|
||||
<h3>${h(node.label)}</h3>
|
||||
${body}
|
||||
</div>
|
||||
${related.map((edge) => `
|
||||
<article class="result-card">
|
||||
<strong>${h(edge.source)} → ${h(edge.target)}</strong>
|
||||
<p>${h(edge.fact || edge.description || edge.predicate || "")}</p>
|
||||
</article>
|
||||
`).join("")}
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Relations</p>
|
||||
${related.length ? related.map((edge) => `
|
||||
<article class="result-card">
|
||||
<strong>${h(edge.source)} → ${h(edge.target)}</strong>
|
||||
<p>${h(edge.fact || edge.description || edge.predicate || "")}</p>
|
||||
</article>
|
||||
`).join("") : `<div class="empty-state">没有关联关系</div>`}
|
||||
</div>
|
||||
`);
|
||||
loadRelated(node.label).catch(() => relatedSearch.innerHTML = empty("相关检索加载失败"));
|
||||
loadRelated(node.label).catch(() => {
|
||||
detailPanel.insertAdjacentHTML("beforeend", `
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Related</p>
|
||||
<div class="empty-state">相关检索加载失败</div>
|
||||
</div>
|
||||
`);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
|
|
@ -432,7 +440,7 @@ function renderGraph(payload) {
|
|||
line?.classList.add("active");
|
||||
const edge = edges.find((item) => item.id === el.dataset.edgeId);
|
||||
renderInspector(`
|
||||
<div class="detail-card">
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Edge</p>
|
||||
<h3>${h(edge.source)} → ${h(edge.target)}</h3>
|
||||
<p>${h(edge.fact || edge.description || "暂无补充描述")}</p>
|
||||
|
|
@ -444,7 +452,14 @@ function renderGraph(payload) {
|
|||
</div>
|
||||
</div>
|
||||
`);
|
||||
loadRelated(`${edge.source} ${edge.predicate} ${edge.target}`).catch(() => relatedSearch.innerHTML = empty("相关检索加载失败"));
|
||||
loadRelated(`${edge.source} ${edge.predicate} ${edge.target}`).catch(() => {
|
||||
detailPanel.insertAdjacentHTML("beforeend", `
|
||||
<div class="detail-section">
|
||||
<p class="eyebrow">Related</p>
|
||||
<div class="empty-state">相关检索加载失败</div>
|
||||
</div>
|
||||
`);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
|
|
@ -514,4 +529,4 @@ graphForm?.addEventListener("submit", (event) => {
|
|||
});
|
||||
|
||||
loadGraphKinds().catch(() => {});
|
||||
fetchGraph().catch((error) => renderInspector(empty(`图谱加载失败: ${error}`)));
|
||||
fetchGraph().catch((error) => renderInspector(empty(`图谱加载失败: ${error}`)));
|
||||
|
|
@ -1,977 +0,0 @@
|
|||
:root {
|
||||
--primary: #5d67f5;
|
||||
--primary-2: #7f8bff;
|
||||
--primary-soft: #edf1ff;
|
||||
--accent: #53c2da;
|
||||
--bg: #f5f7ff;
|
||||
--bg-2: #fbfcff;
|
||||
--panel: rgba(255, 255, 255, 0.9);
|
||||
--panel-strong: rgba(255, 255, 255, 0.96);
|
||||
--border: rgba(212, 221, 247, 0.95);
|
||||
--text: #22264d;
|
||||
--muted: #68709d;
|
||||
--danger: #b3261e;
|
||||
--success: #11693c;
|
||||
--shadow: 0 12px 28px rgba(73, 81, 141, 0.08);
|
||||
--shadow-sm: 0 6px 16px rgba(73, 81, 141, 0.06);
|
||||
--radius-xl: 20px;
|
||||
--radius-lg: 16px;
|
||||
--radius-md: 12px;
|
||||
--radius-sm: 10px;
|
||||
}
|
||||
|
||||
* { box-sizing: border-box; }
|
||||
|
||||
html, body {
|
||||
margin: 0;
|
||||
min-height: 100%;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: "Segoe UI", "PingFang SC", "Microsoft YaHei", sans-serif;
|
||||
font-size: 13px;
|
||||
color: var(--text);
|
||||
background:
|
||||
radial-gradient(circle at 10% 10%, rgba(126, 186, 255, 0.16), transparent 24%),
|
||||
radial-gradient(circle at 88% 14%, rgba(132, 121, 255, 0.12), transparent 22%),
|
||||
linear-gradient(135deg, #f8faff 0%, var(--bg) 55%, var(--bg-2) 100%);
|
||||
}
|
||||
|
||||
a { color: inherit; text-decoration: none; }
|
||||
|
||||
button, input, textarea { font: inherit; }
|
||||
|
||||
.shell {
|
||||
display: grid;
|
||||
grid-template-columns: 220px minmax(0, 1fr);
|
||||
gap: 14px;
|
||||
min-height: 100vh;
|
||||
padding: 14px;
|
||||
}
|
||||
|
||||
.sidebar, .panel, .detail-modal::backdrop {
|
||||
backdrop-filter: blur(12px);
|
||||
}
|
||||
|
||||
.sidebar {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 10px;
|
||||
padding: 14px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 22px;
|
||||
background: linear-gradient(180deg, rgba(236, 243, 255, 0.92), rgba(255, 255, 255, 0.8));
|
||||
box-shadow: var(--shadow);
|
||||
}
|
||||
|
||||
.brand {
|
||||
display: flex;
|
||||
gap: 10px;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.brand-mark {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
display: grid;
|
||||
place-items: center;
|
||||
border-radius: 14px;
|
||||
color: #fff;
|
||||
font-size: 17px;
|
||||
font-weight: 800;
|
||||
background: linear-gradient(135deg, var(--primary), var(--primary-2));
|
||||
}
|
||||
|
||||
.brand-kicker, .eyebrow {
|
||||
margin: 0 0 3px;
|
||||
color: var(--primary);
|
||||
font-size: 10px;
|
||||
font-weight: 700;
|
||||
letter-spacing: 0.08em;
|
||||
text-transform: uppercase;
|
||||
}
|
||||
|
||||
.brand h1, .panel h3, .dialog-head h3 {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
.brand h1 { font-size: 18px; }
|
||||
|
||||
.nav {
|
||||
display: grid;
|
||||
gap: 6px;
|
||||
}
|
||||
|
||||
.nav-link {
|
||||
padding: 10px 12px;
|
||||
border: 1px solid transparent;
|
||||
border-radius: var(--radius-md);
|
||||
color: var(--muted);
|
||||
font-size: 13px;
|
||||
font-weight: 700;
|
||||
transition: 0.2s ease;
|
||||
}
|
||||
|
||||
.nav-link:hover, .nav-link.active {
|
||||
color: var(--primary);
|
||||
border-color: rgba(109, 123, 255, 0.16);
|
||||
background: rgba(255, 255, 255, 0.78);
|
||||
}
|
||||
|
||||
.side-card, .panel {
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius-xl);
|
||||
background: var(--panel);
|
||||
box-shadow: var(--shadow-sm);
|
||||
}
|
||||
|
||||
.panel { padding: 14px; }
|
||||
|
||||
.panel-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: start;
|
||||
gap: 10px;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
.panel h3 { font-size: 17px; }
|
||||
|
||||
.sidebar-shortcuts {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 6px;
|
||||
padding: 10px;
|
||||
margin-top: auto;
|
||||
}
|
||||
|
||||
.pill-link, .chip {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
min-height: 24px;
|
||||
padding: 0 9px;
|
||||
border-radius: 999px;
|
||||
font-size: 11px;
|
||||
font-weight: 700;
|
||||
}
|
||||
|
||||
.pill-link {
|
||||
background: rgba(255, 255, 255, 0.9);
|
||||
border: 1px solid var(--border);
|
||||
}
|
||||
|
||||
.chip {
|
||||
background: var(--primary-soft);
|
||||
color: var(--primary);
|
||||
}
|
||||
|
||||
.chip.status-done, .chip.status-completed { background: #edfdf4; color: var(--success); }
|
||||
.chip.status-pending, .chip.status-todo { background: #fff8e7; color: #b8860b; }
|
||||
.chip.status-in_progress, .chip.status-active { background: #e8f4fd; color: #4a90d9; }
|
||||
.chip.status-blocked { background: #fff4f2; color: var(--danger); }
|
||||
|
||||
.main {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 12px;
|
||||
min-height: 0;
|
||||
}
|
||||
|
||||
.main-toolbar {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
gap: 16px;
|
||||
padding: 16px 18px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 22px;
|
||||
background:
|
||||
radial-gradient(circle at top right, rgba(134, 144, 255, 0.12), transparent 28%),
|
||||
linear-gradient(180deg, rgba(255, 255, 255, 0.94), rgba(244, 248, 255, 0.96));
|
||||
box-shadow: var(--shadow);
|
||||
}
|
||||
|
||||
.main-toolbar h2 {
|
||||
margin: 0;
|
||||
font-size: 22px;
|
||||
}
|
||||
|
||||
.main-toolbar-actions {
|
||||
display: flex;
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
.btn, .icon-btn {
|
||||
border: none;
|
||||
cursor: pointer;
|
||||
transition: 0.2s ease;
|
||||
}
|
||||
|
||||
.btn {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
justify-content: center;
|
||||
min-height: 36px;
|
||||
padding: 0 14px;
|
||||
border-radius: 11px;
|
||||
font-size: 12px;
|
||||
font-weight: 700;
|
||||
color: #fff;
|
||||
background: linear-gradient(135deg, var(--primary), var(--primary-2));
|
||||
box-shadow: 0 8px 18px rgba(93, 103, 245, 0.18);
|
||||
}
|
||||
|
||||
.btn:hover, .icon-btn:hover { transform: translateY(-1px); }
|
||||
|
||||
.btn:disabled {
|
||||
opacity: 0.68;
|
||||
cursor: not-allowed;
|
||||
transform: none;
|
||||
}
|
||||
|
||||
.btn.ghost {
|
||||
color: var(--primary);
|
||||
background: rgba(255, 255, 255, 0.94);
|
||||
box-shadow: none;
|
||||
border: 1px solid var(--border);
|
||||
}
|
||||
|
||||
.stats-grid, .content-grid, .workspace-grid {
|
||||
display: grid;
|
||||
gap: 12px;
|
||||
}
|
||||
|
||||
.stats-grid { grid-template-columns: repeat(4, minmax(0, 1fr)); }
|
||||
|
||||
.highlight-card {
|
||||
padding: 0;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: var(--radius-lg);
|
||||
background: var(--panel-strong);
|
||||
box-shadow: var(--shadow-sm);
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.highlight-card .hc-bar {
|
||||
height: 4px;
|
||||
background: var(--card-accent);
|
||||
}
|
||||
|
||||
.highlight-card .eyebrow {
|
||||
padding: 12px 14px 0;
|
||||
}
|
||||
|
||||
.highlight-card strong {
|
||||
display: block;
|
||||
margin: 4px 0 2px;
|
||||
padding: 0 14px;
|
||||
font-size: 26px;
|
||||
color: var(--card-accent);
|
||||
}
|
||||
|
||||
.highlight-card p:last-child {
|
||||
padding: 0 14px 14px;
|
||||
margin: 0;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.dashboard-grid {
|
||||
grid-template-columns: minmax(330px, 1.1fr) minmax(340px, 1fr) minmax(220px, 0.72fr);
|
||||
align-items: start;
|
||||
}
|
||||
|
||||
.search-box, .import-form, .import-fieldset {
|
||||
display: grid;
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
.import-fieldset {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
border: 0;
|
||||
min-width: 0;
|
||||
}
|
||||
|
||||
.import-fieldset:disabled { opacity: 0.6; }
|
||||
|
||||
.search-box input, .graph-controls input, textarea, input[type="file"] {
|
||||
width: 100%;
|
||||
min-height: 38px;
|
||||
padding: 9px 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 11px;
|
||||
background: rgba(255, 255, 255, 0.94);
|
||||
color: var(--text);
|
||||
}
|
||||
|
||||
textarea {
|
||||
min-height: 138px;
|
||||
resize: vertical;
|
||||
}
|
||||
|
||||
.field-label {
|
||||
font-size: 11px;
|
||||
font-weight: 700;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.check-row {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.status-box {
|
||||
margin-top: 10px;
|
||||
padding: 10px 12px;
|
||||
border-radius: 12px;
|
||||
border: 1px solid var(--border);
|
||||
background: rgba(255, 255, 255, 0.76);
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.status-box[data-kind="error"] {
|
||||
color: var(--danger);
|
||||
background: #fff4f2;
|
||||
}
|
||||
|
||||
.status-box[data-kind="success"] {
|
||||
color: var(--success);
|
||||
background: #edfdf4;
|
||||
}
|
||||
|
||||
.progress-list, .search-results, .mini-stats, .card-list, .list-stack, .related-search {
|
||||
display: grid;
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
.progress-item, .mini-stat, .card, .list-item, .result-card, .detail-card {
|
||||
padding: 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 14px;
|
||||
background: rgba(255, 255, 255, 0.88);
|
||||
}
|
||||
|
||||
.progress-item {
|
||||
display: grid;
|
||||
grid-template-columns: 24px 1fr;
|
||||
gap: 8px;
|
||||
align-items: start;
|
||||
}
|
||||
|
||||
.progress-index {
|
||||
width: 24px;
|
||||
height: 24px;
|
||||
display: grid;
|
||||
place-items: center;
|
||||
border-radius: 999px;
|
||||
background: var(--primary-soft);
|
||||
color: var(--primary);
|
||||
font-size: 11px;
|
||||
font-weight: 700;
|
||||
}
|
||||
|
||||
.mini-stat {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 10px;
|
||||
padding: 10px 12px;
|
||||
}
|
||||
|
||||
.ms-icon {
|
||||
width: 32px;
|
||||
height: 32px;
|
||||
display: grid;
|
||||
place-items: center;
|
||||
border-radius: 10px;
|
||||
font-size: 15px;
|
||||
background: color-mix(in srgb, var(--stat-color) 14%, transparent);
|
||||
color: var(--stat-color);
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.ms-body strong {
|
||||
display: block;
|
||||
font-size: 16px;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
.ms-body p {
|
||||
margin: 0;
|
||||
font-size: 11px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.mini-stat strong, .card h4, .list-item strong, .result-card strong {
|
||||
display: block;
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
.card { cursor: pointer; }
|
||||
|
||||
.card:hover, .result-card:hover, .list-item:hover {
|
||||
border-color: rgba(120, 132, 255, 0.34);
|
||||
}
|
||||
|
||||
.content-grid { grid-template-columns: repeat(2, minmax(0, 1fr)); }
|
||||
|
||||
/* ── Meeting card ── */
|
||||
|
||||
.meeting-card {
|
||||
display: flex;
|
||||
gap: 10px;
|
||||
padding: 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 14px;
|
||||
background: rgba(255, 255, 255, 0.88);
|
||||
cursor: pointer;
|
||||
transition: 0.2s ease;
|
||||
}
|
||||
|
||||
.meeting-card:hover {
|
||||
border-color: rgba(120, 132, 255, 0.34);
|
||||
}
|
||||
|
||||
.mc-date {
|
||||
flex-shrink: 0;
|
||||
width: 44px;
|
||||
height: 44px;
|
||||
display: grid;
|
||||
place-items: center;
|
||||
border-radius: 10px;
|
||||
background: var(--primary-soft);
|
||||
color: var(--primary);
|
||||
font-size: 11px;
|
||||
font-weight: 700;
|
||||
text-align: center;
|
||||
line-height: 1.2;
|
||||
}
|
||||
|
||||
.mc-body h4 {
|
||||
margin: 0 0 4px;
|
||||
font-size: 13px;
|
||||
}
|
||||
|
||||
.mc-body p {
|
||||
margin: 0;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
display: -webkit-box;
|
||||
-webkit-line-clamp: 2;
|
||||
-webkit-box-orient: vertical;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
/* ── List item with priority dot ── */
|
||||
|
||||
.list-item {
|
||||
display: flex;
|
||||
gap: 10px;
|
||||
padding: 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 14px;
|
||||
background: rgba(255, 255, 255, 0.88);
|
||||
}
|
||||
|
||||
.li-priority {
|
||||
flex-shrink: 0;
|
||||
width: 4px;
|
||||
border-radius: 2px;
|
||||
background: var(--pri-color);
|
||||
}
|
||||
|
||||
.li-body {
|
||||
flex: 1;
|
||||
min-width: 0;
|
||||
}
|
||||
|
||||
.li-body strong {
|
||||
display: block;
|
||||
margin-bottom: 2px;
|
||||
}
|
||||
|
||||
.li-body p {
|
||||
margin: 0 0 6px;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
/* ── Metric card ── */
|
||||
|
||||
.metric-card {
|
||||
padding: 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 14px;
|
||||
background: rgba(255, 255, 255, 0.88);
|
||||
}
|
||||
|
||||
.mc-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
margin-bottom: 2px;
|
||||
}
|
||||
|
||||
.mc-head strong {
|
||||
display: block;
|
||||
}
|
||||
|
||||
.mc-value {
|
||||
font-size: 16px;
|
||||
font-weight: 700;
|
||||
color: var(--primary);
|
||||
}
|
||||
|
||||
.metric-card p {
|
||||
margin: 0 0 8px;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.mc-bar-track {
|
||||
height: 4px;
|
||||
border-radius: 2px;
|
||||
background: rgba(212, 221, 247, 0.5);
|
||||
margin-bottom: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.mc-bar-fill {
|
||||
height: 100%;
|
||||
border-radius: 2px;
|
||||
background: linear-gradient(90deg, var(--primary), var(--primary-2));
|
||||
transition: width 0.4s ease;
|
||||
}
|
||||
|
||||
/* ── Series card ── */
|
||||
|
||||
.series-card {
|
||||
display: flex;
|
||||
gap: 10px;
|
||||
align-items: center;
|
||||
padding: 12px;
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 14px;
|
||||
background: rgba(255, 255, 255, 0.88);
|
||||
}
|
||||
|
||||
.sc-count {
|
||||
flex-shrink: 0;
|
||||
width: 36px;
|
||||
height: 36px;
|
||||
display: grid;
|
||||
place-items: center;
|
||||
border-radius: 10px;
|
||||
font-size: 14px;
|
||||
font-weight: 700;
|
||||
background: var(--primary-soft);
|
||||
color: var(--primary);
|
||||
}
|
||||
|
||||
.sc-body strong {
|
||||
display: block;
|
||||
margin-bottom: 2px;
|
||||
}
|
||||
|
||||
.sc-body p {
|
||||
margin: 0;
|
||||
font-size: 12px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
/* ── Unified Import / Search panel ── */
|
||||
|
||||
.unified-panel {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.unified-tabs {
|
||||
display: flex;
|
||||
gap: 4px;
|
||||
margin-bottom: 12px;
|
||||
padding: 3px;
|
||||
border-radius: 11px;
|
||||
background: rgba(212, 221, 247, 0.3);
|
||||
}
|
||||
|
||||
.unified-tab {
|
||||
flex: 1;
|
||||
padding: 7px 12px;
|
||||
border: none;
|
||||
border-radius: 8px;
|
||||
font-size: 12px;
|
||||
font-weight: 700;
|
||||
cursor: pointer;
|
||||
background: transparent;
|
||||
color: var(--muted);
|
||||
transition: 0.2s ease;
|
||||
}
|
||||
|
||||
.unified-tab.active {
|
||||
background: #fff;
|
||||
color: var(--primary);
|
||||
box-shadow: 0 2px 6px rgba(73, 81, 141, 0.1);
|
||||
}
|
||||
|
||||
.unified-tab:hover:not(.active) {
|
||||
color: var(--text);
|
||||
}
|
||||
|
||||
.unified-pane.hidden {
|
||||
display: none;
|
||||
}
|
||||
|
||||
/* ── Result card with kind badge ── */
|
||||
|
||||
.result-card {
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.rc-kind {
|
||||
display: inline-block;
|
||||
padding: 1px 7px;
|
||||
border-radius: 4px;
|
||||
font-size: 10px;
|
||||
font-weight: 700;
|
||||
text-transform: uppercase;
|
||||
background: var(--primary-soft);
|
||||
color: var(--primary);
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
.empty-state {
|
||||
padding: 16px 14px;
|
||||
text-align: center;
|
||||
border: 1px dashed var(--border);
|
||||
border-radius: 14px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.detail-modal {
|
||||
width: min(820px, calc(100vw - 24px));
|
||||
border: 1px solid var(--border);
|
||||
border-radius: 20px;
|
||||
padding: 0;
|
||||
background: rgba(255, 255, 255, 0.97);
|
||||
box-shadow: var(--shadow);
|
||||
}
|
||||
|
||||
.detail-modal::backdrop {
|
||||
background: rgba(37, 44, 78, 0.28);
|
||||
}
|
||||
|
||||
.dialog-head {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
gap: 10px;
|
||||
padding: 16px 16px 6px;
|
||||
}
|
||||
|
||||
.dialog-meta { padding: 0 16px 6px; color: var(--muted); }
|
||||
|
||||
.dialog-content {
|
||||
margin: 0;
|
||||
padding: 0 16px 16px;
|
||||
white-space: pre-wrap;
|
||||
font-family: "Consolas", "Courier New", monospace;
|
||||
max-height: 60vh;
|
||||
overflow: auto;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.icon-btn {
|
||||
width: 30px;
|
||||
height: 30px;
|
||||
border-radius: 10px;
|
||||
background: rgba(242, 245, 255, 0.92);
|
||||
color: var(--primary);
|
||||
font-size: 20px;
|
||||
}
|
||||
|
||||
/* ── Graph page ── */
|
||||
|
||||
.graph-shell {
|
||||
height: 100vh;
|
||||
overflow: hidden;
|
||||
gap: 10px;
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.graph-shell .sidebar {
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.graph-shell .main {
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
.graph-shell .graph-layout {
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
.graph-shell .graph-layout .panel {
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.graph-layout {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr 300px;
|
||||
gap: 12px;
|
||||
flex: 1;
|
||||
min-height: 0;
|
||||
}
|
||||
|
||||
.graph-stage-panel {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
padding: 0;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.graph-stage {
|
||||
flex: 1;
|
||||
min-height: 0;
|
||||
position: relative;
|
||||
background:
|
||||
linear-gradient(180deg, rgba(251, 253, 255, 0.96), rgba(241, 246, 255, 0.94)),
|
||||
radial-gradient(circle at center, rgba(133, 196, 255, 0.08), transparent 36%);
|
||||
}
|
||||
|
||||
#graphSvg {
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
display: block;
|
||||
}
|
||||
|
||||
.detail-panel {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 8px;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.detail-panel .detail-card,
|
||||
.detail-panel .related-search {
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.detail-card {
|
||||
flex-shrink: 0;
|
||||
word-break: break-all;
|
||||
}
|
||||
|
||||
.detail-card strong {
|
||||
word-break: break-word;
|
||||
}
|
||||
|
||||
.related-search {
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.related-search .result-card {
|
||||
word-break: break-all;
|
||||
}
|
||||
|
||||
/* ── Graph toolbar ── */
|
||||
|
||||
.graph-toolbar { padding: 8px 12px; }
|
||||
|
||||
.graph-controls {
|
||||
display: flex;
|
||||
gap: 6px;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.graph-controls .search-input {
|
||||
flex: 1;
|
||||
min-height: 30px;
|
||||
padding: 6px 10px;
|
||||
}
|
||||
|
||||
.graph-controls label.field-label {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 2px;
|
||||
white-space: nowrap;
|
||||
font-size: 10px;
|
||||
}
|
||||
|
||||
.graph-controls label.field-label input {
|
||||
width: 44px;
|
||||
min-height: 26px;
|
||||
padding: 4px 6px;
|
||||
}
|
||||
|
||||
.graph-controls .btn {
|
||||
min-height: 30px;
|
||||
padding: 0 12px;
|
||||
font-size: 11px;
|
||||
}
|
||||
|
||||
.graph-toolbar-row {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
flex-wrap: wrap;
|
||||
gap: 6px;
|
||||
margin-top: 6px;
|
||||
}
|
||||
|
||||
.graph-actions {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 8px;
|
||||
font-size: 11px;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.graph-type-filter {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
align-items: center;
|
||||
gap: 4px 10px;
|
||||
}
|
||||
|
||||
.graph-type-filter label {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 3px;
|
||||
font-size: 11px;
|
||||
color: var(--muted);
|
||||
cursor: pointer;
|
||||
user-select: none;
|
||||
}
|
||||
|
||||
.graph-type-filter label input {
|
||||
margin: 0;
|
||||
accent-color: var(--primary);
|
||||
}
|
||||
|
||||
.graph-meta { font-size: 11px; color: var(--muted); }
|
||||
|
||||
/* ── Graph nodes & edges ── */
|
||||
|
||||
.graph-node { cursor: pointer; }
|
||||
|
||||
.graph-node circle {
|
||||
stroke: rgba(255, 255, 255, 0.85);
|
||||
stroke-width: 2;
|
||||
transition: filter 0.15s;
|
||||
}
|
||||
|
||||
.graph-node--meeting circle { fill: #4a90d9; }
|
||||
.graph-node--episode circle { fill: #34c759; }
|
||||
.graph-node--entity circle { fill: var(--accent); }
|
||||
.graph-node--fact circle { fill: #ff9500; }
|
||||
|
||||
.graph-node:hover circle { filter: brightness(1.2); }
|
||||
|
||||
.graph-node text {
|
||||
font-size: 11px;
|
||||
fill: var(--text);
|
||||
pointer-events: none;
|
||||
user-select: none;
|
||||
}
|
||||
|
||||
.graph-edge {
|
||||
stroke: rgba(120, 136, 194, 0.42);
|
||||
stroke-width: 1.6;
|
||||
cursor: pointer;
|
||||
transition: stroke 0.15s, stroke-width 0.15s;
|
||||
}
|
||||
|
||||
.edge-wrap:hover .graph-edge {
|
||||
stroke: rgba(120, 136, 194, 0.7);
|
||||
stroke-width: 2;
|
||||
}
|
||||
|
||||
.graph-edge.active {
|
||||
stroke: var(--primary);
|
||||
stroke-width: 2.4;
|
||||
}
|
||||
|
||||
.edge-wrap text {
|
||||
pointer-events: none;
|
||||
user-select: none;
|
||||
}
|
||||
|
||||
/* ── Legend ── */
|
||||
|
||||
.legend { font-size: 11px; color: var(--muted); }
|
||||
|
||||
.legend-dot {
|
||||
display: inline-block;
|
||||
width: 9px;
|
||||
height: 9px;
|
||||
border-radius: 50%;
|
||||
margin-right: 6px;
|
||||
}
|
||||
|
||||
.legend-dot.meeting { background: #4a90d9; }
|
||||
.legend-dot.episode { background: #34c759; }
|
||||
.legend-dot.entity { background: var(--accent); }
|
||||
.legend-dot.fact { background: #ff9500; }
|
||||
|
||||
.graph-shell .sidebar {
|
||||
gap: 8px;
|
||||
padding: 10px;
|
||||
}
|
||||
|
||||
.graph-shell .sidebar .legend {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 3px;
|
||||
font-size: 11px;
|
||||
padding: 0 4px;
|
||||
}
|
||||
|
||||
.graph-shell .sidebar .legend .eyebrow {
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
/* ── Graph controls overlay ── */
|
||||
|
||||
.zoom-reset-btn, .pause-btn {
|
||||
font-size: 11px;
|
||||
min-height: 28px;
|
||||
padding: 0 10px;
|
||||
}
|
||||
|
||||
.zoom-hint {
|
||||
font-size: 11px;
|
||||
color: var(--muted);
|
||||
padding: 4px 0;
|
||||
}
|
||||
|
||||
/* ── Responsive ── */
|
||||
|
||||
@media (max-width: 1240px) {
|
||||
.shell, .graph-shell, .dashboard-grid, .content-grid, .graph-layout, .stats-grid {
|
||||
grid-template-columns: 1fr;
|
||||
}
|
||||
|
||||
.sidebar { order: 2; }
|
||||
|
||||
.graph-shell { height: auto; overflow: auto; }
|
||||
}
|
||||
|
||||
@media (max-width: 720px) {
|
||||
.shell, .graph-shell {
|
||||
padding: 10px;
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
.sidebar, .panel { border-radius: 18px; }
|
||||
|
||||
.search-box { grid-template-columns: 1fr; }
|
||||
|
||||
.graph-stage { min-height: 250px; }
|
||||
|
||||
.graph-controls { flex-wrap: wrap; }
|
||||
|
||||
.graph-controls .search-input { min-width: 100%; }
|
||||
}
|
||||
|
|
@ -3,11 +3,12 @@
|
|||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Neo4j Graph Explorer</title>
|
||||
<link rel="stylesheet" href="/styles.css">
|
||||
<title>图谱浏览 — Meeting Memory</title>
|
||||
<link rel="stylesheet" href="/static_v2/styles.css">
|
||||
</head>
|
||||
<body>
|
||||
<div class="shell graph-shell">
|
||||
<!-- ====== Sidebar ====== -->
|
||||
<aside class="sidebar">
|
||||
<div class="brand">
|
||||
<div class="brand-mark">G</div>
|
||||
|
|
@ -18,25 +19,33 @@
|
|||
</div>
|
||||
|
||||
<nav class="nav">
|
||||
<a class="nav-link" href="/index.html">总览面板</a>
|
||||
<a class="nav-link active" href="/graph.html">图谱浏览</a>
|
||||
<a class="nav-link" href="/">总览面板</a>
|
||||
<a class="nav-link active" href="/graph">图谱浏览</a>
|
||||
</nav>
|
||||
|
||||
<div class="legend">
|
||||
<p class="eyebrow" style="margin-bottom:6px">图例</p>
|
||||
<p class="eyebrow">图例</p>
|
||||
<span><i class="legend-dot meeting"></i>会议</span>
|
||||
<span><i class="legend-dot episode"></i>片段</span>
|
||||
<span><i class="legend-dot entity"></i>实体</span>
|
||||
<span><i class="legend-dot fact"></i>事实</span>
|
||||
<span><i class="legend-dot edge"></i>关系</span>
|
||||
</div>
|
||||
</aside>
|
||||
|
||||
<!-- ====== Main ====== -->
|
||||
<main class="main">
|
||||
<div class="graph-toolbar panel">
|
||||
<!-- Graph Toolbar -->
|
||||
<div class="panel graph-toolbar">
|
||||
<form class="graph-controls" id="graphSearchForm">
|
||||
<input id="graphQueryInput" type="text" placeholder="搜索节点名称或关键词…" class="search-input">
|
||||
<label class="field-label">节点 <input id="graphNodeLimit" type="number" min="10" max="200" step="10" value="60"></label>
|
||||
<label class="field-label">关系 <input id="graphEdgeLimit" type="number" min="10" max="300" step="10" value="120"></label>
|
||||
<label class="field-label">
|
||||
节点
|
||||
<input id="graphNodeLimit" type="number" min="10" max="200" step="10" value="60">
|
||||
</label>
|
||||
<label class="field-label">
|
||||
关系
|
||||
<input id="graphEdgeLimit" type="number" min="10" max="300" step="10" value="120">
|
||||
</label>
|
||||
<button class="btn" type="submit">更新</button>
|
||||
</form>
|
||||
<div class="graph-toolbar-row">
|
||||
|
|
@ -47,18 +56,18 @@
|
|||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Graph Layout -->
|
||||
<div class="graph-layout">
|
||||
<!-- Graph Stage -->
|
||||
<div class="panel graph-stage-panel">
|
||||
<div class="graph-stage" id="graphStage">
|
||||
<svg id="graphSvg" viewBox="0 0 960 640" preserveAspectRatio="xMidYMid meet"></svg>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="panel detail-panel">
|
||||
<div class="detail-card" id="graphDetail">
|
||||
<div class="empty-state">点击节点或关系查看详情</div>
|
||||
</div>
|
||||
<div class="related-search" id="relatedSearch"></div>
|
||||
<!-- Detail Panel -->
|
||||
<div class="panel detail-panel" id="detailPanel">
|
||||
<div class="empty-state">点击节点或关系查看详情</div>
|
||||
</div>
|
||||
</div>
|
||||
</main>
|
||||
|
|
@ -66,4 +75,4 @@
|
|||
|
||||
<script src="/graph.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
</html>
|
||||
|
|
@ -3,11 +3,12 @@
|
|||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Meeting Memory Console</title>
|
||||
<link rel="stylesheet" href="/styles.css">
|
||||
<title>会议记忆中枢 — Meeting Memory</title>
|
||||
<link rel="stylesheet" href="/static_v2/styles.css">
|
||||
</head>
|
||||
<body>
|
||||
<div class="shell">
|
||||
<!-- ====== Sidebar ====== -->
|
||||
<aside class="sidebar">
|
||||
<div class="brand">
|
||||
<div class="brand-mark">M</div>
|
||||
|
|
@ -18,18 +19,20 @@
|
|||
</div>
|
||||
|
||||
<nav class="nav">
|
||||
<a class="nav-link active" href="/index.html">总览面板</a>
|
||||
<a class="nav-link" href="/graph.html">图谱浏览</a>
|
||||
<a class="nav-link active" href="/">总览面板</a>
|
||||
<a class="nav-link" href="/graph">图谱浏览</a>
|
||||
</nav>
|
||||
|
||||
<div class="side-card sidebar-shortcuts">
|
||||
<div class="sidebar-shortcuts">
|
||||
<a class="pill-link" href="#import-panel">导入会议</a>
|
||||
<a class="pill-link" href="#search-panel">知识检索</a>
|
||||
<a class="pill-link" href="/graph.html">图谱页</a>
|
||||
<a class="pill-link" href="/graph">图谱页</a>
|
||||
</div>
|
||||
</aside>
|
||||
|
||||
<!-- ====== Main ====== -->
|
||||
<main class="main">
|
||||
<!-- Toolbar -->
|
||||
<div class="main-toolbar">
|
||||
<div>
|
||||
<p class="eyebrow">Dashboard</p>
|
||||
|
|
@ -40,8 +43,10 @@
|
|||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Highlight Cards -->
|
||||
<section class="stats-grid" id="highlightGrid"></section>
|
||||
|
||||
<!-- Unified Panel: Import / Search / Stats -->
|
||||
<section class="panel unified-panel">
|
||||
<div class="unified-tabs">
|
||||
<button class="unified-tab active" data-tab="import">导入</button>
|
||||
|
|
@ -49,6 +54,7 @@
|
|||
<button class="unified-tab" data-tab="stats">统计</button>
|
||||
</div>
|
||||
|
||||
<!-- Import Pane -->
|
||||
<div class="unified-pane" id="unifiedImport">
|
||||
<form class="import-form" id="importForm">
|
||||
<fieldset id="importFieldset" class="import-fieldset">
|
||||
|
|
@ -73,6 +79,7 @@
|
|||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Search Pane -->
|
||||
<div class="unified-pane hidden" id="unifiedSearch">
|
||||
<form class="search-box" id="searchForm">
|
||||
<input id="searchInput" type="text" placeholder="搜索会议主题、负责人、指标、关系事实...">
|
||||
|
|
@ -83,11 +90,13 @@
|
|||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Stats Pane -->
|
||||
<div class="unified-pane hidden" id="unifiedStats">
|
||||
<div class="mini-stats" id="statsList"></div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<!-- Content Grid -->
|
||||
<div class="content-grid">
|
||||
<section class="panel" id="meeting-list">
|
||||
<div class="panel-head">
|
||||
|
|
@ -124,6 +133,7 @@
|
|||
</main>
|
||||
</div>
|
||||
|
||||
<!-- Meeting Detail Dialog -->
|
||||
<dialog class="detail-modal" id="meetingDialog">
|
||||
<div class="dialog-head">
|
||||
<div>
|
||||
|
|
@ -138,4 +148,4 @@
|
|||
|
||||
<script src="/app.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
</html>
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,186 @@
|
|||
"""
|
||||
Migration script: v1 (flat Entity + Fact nodes) → v2 (composite labels + direct edges)
|
||||
|
||||
Steps:
|
||||
1. Add composite Neo4j labels to existing Entity nodes based on entity_type
|
||||
2. Convert Fact nodes to RELATES_TO edges between Entity nodes
|
||||
3. Verify data integrity
|
||||
"""
|
||||
import logging
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||||
|
||||
from meeting_memory.graph_store import graph_store, _canonical_entity_type, _EntityType
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format='%(asctime)s [%(levelname)s] %(message)s')
|
||||
logger = logging.getLogger('migrate')
|
||||
|
||||
|
||||
def get_type_label_map() -> dict[str, str]:
|
||||
"""Map canonical entity_type -> Neo4j label"""
|
||||
return {
|
||||
_EntityType.DEPARTMENT.value: 'Department',
|
||||
_EntityType.PROJECT.value: 'Project',
|
||||
_EntityType.METRIC.value: 'Metric',
|
||||
_EntityType.PERSON.value: 'Person',
|
||||
_EntityType.SYSTEM.value: 'System',
|
||||
_EntityType.DOCUMENT.value: 'Document',
|
||||
}
|
||||
|
||||
|
||||
def step1_add_composite_labels():
|
||||
"""Add composite labels (e.g., :Department) to existing Entity nodes."""
|
||||
type_label_map = get_type_label_map()
|
||||
total = 0
|
||||
for canonical_type, label in type_label_map.items():
|
||||
rows = graph_store.run_query(
|
||||
'MATCH (e:Entity) WHERE e.entity_type = $etype RETURN count(e) AS cnt',
|
||||
etype=canonical_type,
|
||||
)
|
||||
count = rows[0]['cnt'] if rows else 0
|
||||
if count == 0:
|
||||
logger.info(' No Entity with entity_type=%s to migrate', canonical_type)
|
||||
continue
|
||||
graph_store.run_query(
|
||||
f'MATCH (e:Entity) WHERE e.entity_type = $etype SET e:{label}',
|
||||
etype=canonical_type,
|
||||
)
|
||||
logger.info(' Added :%s label to %d Entity nodes', label, count)
|
||||
total += count
|
||||
|
||||
# Also handle aliases: Organization -> Department
|
||||
for alias in ('组织', 'Organization', '部门'):
|
||||
rows = graph_store.run_query(
|
||||
'MATCH (e:Entity {entity_type: $etype}) RETURN count(e) AS cnt',
|
||||
etype=alias,
|
||||
)
|
||||
count = rows[0]['cnt'] if rows else 0
|
||||
if count == 0:
|
||||
continue
|
||||
graph_store.run_query(
|
||||
'MATCH (e:Entity {entity_type: $etype}) SET e.entity_type = $canonical, e:Department',
|
||||
etype=alias, canonical=_EntityType.DEPARTMENT.value,
|
||||
)
|
||||
logger.info(' Redirected %d entities from entity_type=%s -> Department', count, alias)
|
||||
total += count
|
||||
|
||||
for alias in ('指标', 'kpi', 'KPI'):
|
||||
rows = graph_store.run_query(
|
||||
'MATCH (e:Entity {entity_type: $etype}) RETURN count(e) AS cnt',
|
||||
etype=alias,
|
||||
)
|
||||
count = rows[0]['cnt'] if rows else 0
|
||||
if count == 0:
|
||||
continue
|
||||
graph_store.run_query(
|
||||
'MATCH (e:Entity {entity_type: $etype}) SET e.entity_type = $canonical, e:Metric',
|
||||
etype=alias, canonical=_EntityType.METRIC.value,
|
||||
)
|
||||
logger.info(' Redirected %d entities from entity_type=%s -> Metric', count, alias)
|
||||
total += count
|
||||
|
||||
logger.info('Step 1 done: %d entities got composite labels', total)
|
||||
|
||||
|
||||
def step2_convert_facts_to_edges():
|
||||
"""Convert existing Fact nodes to RELATES_TO edges, then remove Fact nodes."""
|
||||
facts = graph_store.run_query('''
|
||||
MATCH (s:Entity)-[:FACT_SOURCE]->(f:Fact)-[:FACT_TARGET]->(t:Entity)
|
||||
RETURN s.name AS source, t.name AS target,
|
||||
f.predicate AS relation_type,
|
||||
f.fact AS fact,
|
||||
f.qualifiers AS qualifiers,
|
||||
f.evidence AS evidence,
|
||||
f.confidence AS confidence,
|
||||
f.valid_at AS valid_at,
|
||||
f.invalid_at AS invalid_at,
|
||||
f.meeting_id AS meeting_id,
|
||||
f.meeting_date AS meeting_date,
|
||||
f.fact_embedding AS fact_embedding
|
||||
''')
|
||||
logger.info('Found %d Fact nodes to convert', len(facts))
|
||||
|
||||
converted = 0
|
||||
for f in facts:
|
||||
source = f.get('source', '')
|
||||
target = f.get('target', '')
|
||||
rtype = f.get('relation_type', '') or '关联'
|
||||
if not source or not target:
|
||||
continue
|
||||
fact_embedding = f.get('fact_embedding') or []
|
||||
graph_store.run_query('''
|
||||
MATCH (s:Entity {name: $source})
|
||||
MATCH (t:Entity {name: $target})
|
||||
MERGE (s)-[r:RELATES_TO {name: $rtype}]->(t)
|
||||
SET r.fact = $fact,
|
||||
r.evidence = $evidence,
|
||||
r.qualifiers = $qualifiers,
|
||||
r.confidence = $confidence,
|
||||
r.valid_at = $valid_at,
|
||||
r.invalid_at = $invalid_at,
|
||||
r.meeting_id = $meeting_id,
|
||||
r.meeting_date = $meeting_date,
|
||||
r.updated_at = datetime()
|
||||
''',
|
||||
source=source,
|
||||
target=target,
|
||||
rtype=rtype,
|
||||
fact=f.get('fact', ''),
|
||||
evidence=f.get('evidence', ''),
|
||||
qualifiers=f.get('qualifiers', []),
|
||||
confidence=f.get('confidence', 0.0),
|
||||
valid_at=f.get('valid_at', ''),
|
||||
invalid_at=f.get('invalid_at', ''),
|
||||
meeting_id=f.get('meeting_id', ''),
|
||||
meeting_date=f.get('meeting_date', ''),
|
||||
)
|
||||
if fact_embedding:
|
||||
graph_store.run_query('''
|
||||
MATCH (s:Entity {name: $source})-[r:RELATES_TO {name: $rtype}]->(t:Entity {name: $target})
|
||||
SET r.fact_embedding = $embedding
|
||||
''', source=source, target=target, rtype=rtype, embedding=fact_embedding)
|
||||
converted += 1
|
||||
|
||||
# Now remove Fact nodes and their incident edges
|
||||
graph_store.run_query('''
|
||||
MATCH (f:Fact)
|
||||
OPTIONAL MATCH (f)-[r]-()
|
||||
DELETE r, f
|
||||
''')
|
||||
logger.info('Step 2 done: converted %d facts to edges, removed Fact nodes', converted)
|
||||
|
||||
|
||||
def verify():
|
||||
"""Verify migration results."""
|
||||
stats = graph_store.get_stats()
|
||||
logger.info('Final stats: %s', stats)
|
||||
|
||||
types = graph_store.get_entity_types()
|
||||
logger.info('Entity types: %s', [(t['entity_type'], t['count']) for t in types])
|
||||
|
||||
kinds = graph_store.get_graph_kinds()
|
||||
logger.info('Graph kinds: %s', [(k['kind'], k['count']) for k in kinds])
|
||||
|
||||
# Count labeled entities
|
||||
for label in ('Department', 'Project', 'Metric', 'Person', 'System', 'Document'):
|
||||
rows = graph_store.run_query(f'MATCH (n:{label}) RETURN count(n) AS cnt')
|
||||
count = rows[0]['cnt'] if rows else 0
|
||||
if count:
|
||||
logger.info(' :%s nodes: %d', label, count)
|
||||
|
||||
edges = graph_store.run_query('MATCH ()-[r:RELATES_TO]->() RETURN count(r) AS cnt')
|
||||
logger.info(' RELATES_TO edges: %d', edges[0]['cnt'] if edges else 0)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
if not graph_store.enabled:
|
||||
logger.error('Neo4j is not available')
|
||||
sys.exit(1)
|
||||
|
||||
logger.info('Starting v1→v2 migration...')
|
||||
step1_add_composite_labels()
|
||||
step2_convert_facts_to_edges()
|
||||
verify()
|
||||
logger.info('Migration complete')
|
||||
Loading…
Reference in New Issue