Skip to content

Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.

feat: 新增 Atom 模块及演示,优化时序知识图谱提取功能,并更新相关合并策略

yifanfeng97fc006bcb54f3
diff --git a/examples/atom_demo.py b/examples/atom_demo.py
new file mode 100644
index 0000000..32d0819
--- /dev/null
+++ b/examples/atom_demo.py
@@ -0,0 +1,308 @@
+"""
+Atom 演示:产品历史中的时序知识图谱提取
+
+这个演示展示了如何使用 Atom 从产品迭代历史中提取结构化知识。
+重点展示:
+1. 产品发布时间与版本信息的提取
+2. 关键人物与产品的关联
+3. 公司并购与产品策略变化
+4. 时序关系的精确捕获(t_start, t_end)
+5. 证据追踪与来源溯源
+"""
+
+import os
+import sys
+from collections import Counter, defaultdict
+
+# 添加项目根目录到路径
+sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from dotenv import load_dotenv
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+
+from hyperextract.graphs import Atom
+
+load_dotenv()
+
+# ==============================================================================
+# 示例文本:产品历史(技术产品迭代)
+# ==============================================================================
+
+# EXAMPLE_TEXT = """
+# 2024年是李四职业生涯的转折点。6月15日,李四加入了Google,担任工程师一职。
+# 他加入的是核心技术团队,主要从事后端服务开发。工作初期,李四表现出色,
+# 与团队协作顺利,代码质量得到认可。
+
+# 到了9月,由于李四在多个关键项目中的出色表现,Google决定将其提升为技术主管。
+# 升职后,李四开始领导一个30人的技术团队,负责推荐系统的开发和优化。
+# 他实施了多项技术改革,团队效率提升了40%。
+
+# 然而,到了11月中旬,李四发现自己对当前的薪资待遇不满意。经过深思熟虑,
+# 他决定寻求新的机会。最终,李四接受了字节跳动的邀约,并于11月25日正式加入。
+# 在字节,李四担任高级工程师,继续从事推荐系统的研发工作。
+# """
+
+EXAMPLE_TEXT = """
+"CyberPhone"是未来科技(FutureTech)公司旗下的旗舰智能手机系列,代表了移动设备革新的前沿。
+
+第一代CyberPhone于2010年6月发布,凭其全息投影屏幕震惊业界。当时的首席设计师是乔纳森·李,他与工程主管陈思共同主导了这次创新。
+这款产品上市后迅速成为全球最受欢迎的高端手机,首年销售额达到了2亿美元。
+
+2012年9月,FutureTech推出了CyberPhone 2。这一代产品引入了脑机接口(BMI)的雏形功能,允许用户通过脑电波进行基础交互。
+设计师乔纳森·李继续领导设计团队,而陈思则被晋升为首席工程师。
+然而,这次创新也带来了风险:由于集成度过高,CyberPhone 2的电池安全问题频频出现。
+
+到了2013年,由于电池缺陷引发的多起安全事故,FutureTech不得不宣布全球召回所有CyberPhone 2。
+这场危机导致公司股价大幅下跌,管理层面临巨大压力。
+时任CEO的王芳为了挽回信誉,做出了一个大胆的决定:整个2014年不发布新产品,所有资源投入到底层系统和安全机制的重构。
+
+直到2015年底,经过两年打磨,CyberPhone 3终于问世。虽然发布时间大幅推迟,但这一代产品搭载了革命性的AI助手"Luna"。
+Luna是由FutureTech在2015年年中收购的初创公司"Moon AI"开发的核心算法。
+Moon AI的创始人兼CEO李想因此加入了FutureTech,担任AI创新部门的副总裁,任期从2015年7月至2019年6月。
+CyberPhone 3一经发布就获得了业界的广泛赞誉,被誉为"手机史上的里程碑"。
+
+自此之后,FutureTech建立了稳定的产品节奏,基本保持每两年推出一代新品的策略。
+2017年3月发布的CyberPhone 4进一步完善了AI助手功能,并加入了增强现实(AR)显示技术。
+2019年9月发布的CyberPhone 5则在续航能力和计算性能上取得了突破。
+在这个阶段,乔纳森·李仍然是首席设计师,陈思继续担任首席工程师。
+
+但转折点来了。2021年4月,乔纳森·李在为FutureTech服务了整整12年后,宣布离职并加入竞品公司"QuantumTech"担任设计总监。
+乔纳森的离职引发了业界热议,许多人认为这标志着CyberPhone系列即将走向衰落。
+与此同时,新晋设计师韩雪接替了乔纳森的职位,但她的设计风格与乔纳森截然不同。
+
+2021年底发布的CyberPhone 6展现了全新的设计语言——极简风格取代了之前的科技感。
+业界对这一变化评价不一,许多长期粉丝甚至戏称这是"最不像CyberPhone的一代"。
+销售数据也反映了这一点:CyberPhone 6的市场反应相比前几代明显不足。
+
+在这个困难时期,陈思于2022年年底晋升为首席产品官(CPO),获得了更大的权力重新调整产品方向。
+同时,李想在2022年中期转任为AI伦理委员会主席,虽然仍在公司但已远离产品一线。
+
+去年(2023年)全年,FutureTech几乎没有推出任何重大产品更新。这个沉默期引发了市场猜测。
+直到今年初,公司宣布了一个雄心勃勃的计划:将在今年晚些时候发布CyberPhone X。
+
+本周,FutureTech官方确认了CyberPhone X的发布时间定在今年Q3,并透露这款产品将是对CyberPhone系列的根本性重新定义。
+根据公司声明,CyberPhone X旨在纪念该系列诞生15周年,同时引入突破性的新技术。
+韩雪确认将继续担任首席设计师,而陈思作为CPO将主导这次产品重塑项目。
+令人惊喜的是,曾经的设计大师乔纳森·李也获邀作为顾问加盟这个项目,尽管他目前仍就职于QuantumTech。
+
+业界普遍认为,CyberPhone X将成为检验FutureTech是否能重获竞争力的关键产品。
+"""
+
+# ==============================================================================
+# 主程序
+# ==============================================================================
+
+def main():
+ print("=" * 80)
+ print("🕒 Atom 演示:产品历史中的时序知识图谱提取")
+ print("=" * 80)
+ print()
+
+ # 1. 初始化
+ print("📦 初始化组件...")
+ llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+ embedder = OpenAIEmbeddings(model="text-embedding-3-small")
+
+ obs_date = "2024-12-15"
+ print(f"🚀 创建 Atom 实例(观察日期:{obs_date})...")
+ kg = Atom(
+ llm_client=llm,
+ embedder=embedder,
+ observation_date=obs_date,
+ facts_per_chunk=10,
+ verbose=True,
+ )
+
+ # 2. 提取
+ print(f"\n📄 正在处理产品历史文本(长度:{len(EXAMPLE_TEXT)} 字符)...")
+ print("状态: 正在进行两阶段提取...")
+ print(" [Phase 1] 原子事实提取")
+ print(" [Phase 2] 关系提取(带时序和证据追踪)")
+ print()
+ kg.feed_text(EXAMPLE_TEXT)
+
+ # 3. 显示初步结果
+ print("\n" + "=" * 80)
+ print("✅ Phase 1-2 提取完成!")
+ print("=" * 80)
+
+ # 统计信息
+ print(f"\n📊 提取统计:")
+ print(f" 节点数量: {len(kg.nodes)}")
+ print(f" 关系数量: {len(kg.edges)}")
+
+ # 统计标签分布
+ labels = Counter(n.label for n in kg.nodes)
+ print(f" 实体类型分布: {dict(labels)}")
+
+ # 显示所有节点
+ print("\n" + "-" * 80)
+ print(f"🏷️ 提取的实体及其类型 ({len(kg.nodes)} 个):")
+ print("-" * 80)
+ for i, node in enumerate(kg.nodes, 1):
+ print(f" {i:2d}. {node.name:<30} [类型: {node.label}]")
+
+ # 显示所有关系(包括时间和证据信息)
+ print("\n" + "-" * 80)
+ print(f"🔗 提取的关系 ({len(kg.edges)} 个):")
+ print("-" * 80)
+
+ # 按时间排序关系
+ sorted_edges = sorted(
+ kg.edges,
+ key=lambda e: e.t_start[0] if e.t_start else "9999-12-31"
+ )
+
+ for i, edge in enumerate(sorted_edges, 1):
+ # 基本关系
+ rel_str = f"{edge.startNode.name} --[{edge.name}]--> {edge.endNode.name}"
+
+ # 添加时间信息
+ time_info = ""
+ if edge.t_start:
+ time_info += f"(从 {edge.t_start[0]}"
+ if edge.t_end:
+ time_info += f" 到 {edge.t_end[0]})"
+ else:
+ time_info += ")"
+ elif edge.t_end:
+ time_info += f"(截止 {edge.t_end[0]})"
+
+ print(f" {i:2d}. {rel_str:<65} {time_info}")
+
+ # 显示证据(只显示第一条)
+ if edge.atomic_facts:
+ evidence = edge.atomic_facts[0].replace("\n", " ")
+ if len(evidence) > 70:
+ evidence = evidence[:70] + "..."
+ print(f" 📌 证据: {evidence}")
+
+ # 按谓词分组显示
+ print("\n" + "-" * 80)
+ print("📋 按关系类型分类:")
+ print("-" * 80)
+
+ relations_by_type = defaultdict(list)
+ for edge in kg.edges:
+ relations_by_type[edge.name].append((edge.startNode.name, edge.endNode.name))
+
+ for pred in sorted(relations_by_type.keys()):
+ pairs = relations_by_type[pred]
+ print(f"\n ✓ {pred} ({len(pairs)} 条)")
+ for s, o in pairs[:8]: # 显示前 8 条
+ print(f" • {s} → {o}")
+ if len(pairs) > 8:
+ print(f" • ... 及 {len(pairs) - 8} 条其他关系")
+
+ # 实体连接度分析
+ print("\n" + "-" * 80)
+ print("⭐ 高关联度实体 (Top 15):")
+ print("-" * 80)
+
+ entity_degree = Counter()
+ for edge in kg.edges:
+ entity_degree[edge.startNode.name] += 1
+ entity_degree[edge.endNode.name] += 1
+
+ for entity, count in entity_degree.most_common(15):
+ print(f" • {entity:<30} 参与 {count:2d} 个关系")
+
+ # ============================================================================
+ # Phase 3: 语义去重
+ # ============================================================================
+ print("\n" + "=" * 80)
+ print("🔄 Phase 3: 语义去重 (使用 SemHash)")
+ print("=" * 80)
+
+ print(f"\n去重前: 节点 {len(kg.nodes)}, 关系 {len(kg.edges)}")
+ print(" 执行语义相似度匹配 (threshold=0.8)...")
+
+ kg.match_nodes_and_update_edges(threshold=0.8)
+
+ print(f"去重后: 节点 {len(kg.nodes)}, 关系 {len(kg.edges)}")
+
+ # 对比统计
+ print("\n📊 去重后统计:")
+
+ # 更新标签分布
+ labels_after = Counter(n.label for n in kg.nodes)
+ print(f" 实体类型分布: {dict(labels_after)}")
+
+ # 更新关系类型分布
+ relations_after = defaultdict(int)
+ for edge in kg.edges:
+ relations_after[edge.name] += 1
+ print(f" 关系类型: {len(relations_after)} 种")
+
+ # 显示去重后的节点
+ print("\n" + "-" * 80)
+ print(f"🏷️ 去重后的实体 ({len(kg.nodes)} 个):")
+ print("-" * 80)
+ for i, node in enumerate(kg.nodes, 1):
+ print(f" {i:2d}. {node.name:<30} [类型: {node.label}]")
+
+ # 显示去重后的关系(简要版)
+ print("\n" + "-" * 80)
+ print(f"🔗 去重后的关系 ({len(kg.edges)} 个 - 简要版):")
+ print("-" * 80)
+
+ sorted_edges_after = sorted(
+ kg.edges,
+ key=lambda e: e.t_start[0] if e.t_start else "9999-12-31"
+ )
+
+ for i, edge in enumerate(sorted_edges_after, 1):
+ rel_str = f"{edge.startNode.name} --[{edge.name}]--> {edge.endNode.name}"
+
+ time_info = ""
+ if edge.t_start:
+ time_info += f"(从 {edge.t_start[0]}"
+ if edge.t_end:
+ time_info += f" 到 {edge.t_end[0]})"
+ else:
+ time_info += ")"
+ elif edge.t_end:
+ time_info += f"(截止 {edge.t_end[0]})"
+
+ print(f" {i:2d}. {rel_str:<65} {time_info}")
+
+ # ============================================================================
+ # 保存结果
+ # ============================================================================
+ print("\n" + "=" * 80)
+ print("💾 保存结果...")
+ print("=" * 80)
+
+ try:
+ output_dir = "temp/atom_demo"
+ kg.dump(output_dir)
+ print(f"✓ 结果已保存到 {output_dir}/")
+
+ # 列出保存的文件
+ import os
+ saved_files = []
+ if os.path.exists(output_dir):
+ for root, dirs, files in os.walk(output_dir):
+ for file in files:
+ rel_path = os.path.relpath(os.path.join(root, file), output_dir)
+ saved_files.append(rel_path)
+
+ if saved_files:
+ print("\n 保存的文件:")
+ for f in sorted(saved_files):
+ print(f" - {f}")
+ except Exception as e:
+ print(f"⚠ 警告: 无法保存结果: {str(e)}")
+
+ print("\n" + "=" * 80)
+ print("✨ Atom 演示完成!")
+ print("=" * 80)
+ print("\n📌 演示要点:")
+ print(" ✓ 两阶段提取:原子事实 → 关系提取")
+ print(" ✓ 时序追踪:产品发布日期、人物任职期间")
+ print(" ✓ 证据追踪:每条关系都关联到源事实")
+ print(" ✓ 语义去重:自动合并同义实体")
+
+
+if __name__ == "__main__":
+ main()
diff --git a/hyperextract/graphs/__init__.py b/hyperextract/graphs/__init__.py
index cd4b7fb..bf69b20 100644
--- a/hyperextract/graphs/__init__.py
+++ b/hyperextract/graphs/__init__.py
@@ -2,6 +2,7 @@ from .base import AutoGraph
from .kg_gen import KG_Gen
from .itext2kg import iText2KG
from .itext2kg_star import iText2KG_Star
+from .atom import Atom
-__all__ = ["AutoGraph", "KG_Gen", "iText2KG", "iText2KG_Star"]
+__all__ = ["AutoGraph", "KG_Gen", "iText2KG", "iText2KG_Star", "Atom"]
diff --git a/hyperextract/graphs/atom.py b/hyperextract/graphs/atom.py
index 5559d03..b806b9b 100644
--- a/hyperextract/graphs/atom.py
+++ b/hyperextract/graphs/atom.py
@@ -7,14 +7,14 @@ standardized triple-based knowledge graphs.
Prompts and schemas are adapted from the original Atom implementation.
"""
-from typing import Optional
+from typing import Optional, List
from datetime import datetime
from pydantic import BaseModel, Field
from semhash import SemHash
from langchain_core.language_models import BaseChatModel
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.embeddings import Embeddings
-from ontomem.merger import MergeStrategy
+from ontomem.merger import MergeStrategy, CustomRuleMerger
from .base import AutoGraph, AutoGraphSchema
from ..utils.logging import logger
@@ -128,7 +128,7 @@ class EdgeSchema(BaseModel):
"A list of exact string copies of the atomic facts or sentences from the source text that provide evidence for this relationship. "
"Select the specific facts from the input context that justify this edge. "
"Do NOT paraphrase or modify the text. Copy it exactly as it appears in the source."
- )
+ ),
)
@@ -138,6 +138,8 @@ class EdgeSchema(BaseModel):
Atom_FACTOID_EXTRACTION_PROMPT = """
+Observation Date: {observation_date}
+
You are an expert factoid extraction engine. Your primary function is to read a news paragraph and its associated observation date, and then decompose the text into a comprehensive list of atomic, self-contained, and temporally-grounded facts.
## Task
@@ -196,7 +198,7 @@ Given an input paragraph and an `observation_date`, generate a list of all disti
"""
Atom_EDGE_EXTRACTION_PROMPT = """
-Observation Date: {obs_timestamp}
+Observation Date: {observation_date}
You are a precise knowledge extraction engine designed to distill unstructured text into a structured Knowledge Graph.
Your goal is to extract all meaningful relationships (edges) between entities, while rigorously capturing their temporal bounds and grounding evidence.
@@ -220,8 +222,8 @@ Extract a list of relationships where each relationship consists of:
#### 2. Temporal Extraction (Critical)
- **Format**: All dates must be in `YYYY-MM-DD` or `YYYY` format.
- **Lists**: `t_start` and `t_end` must always be lists of strings. If no date is found, use an empty list `[]`.
-- **Relative Time Resolution**: Calculate absolute dates based on the **Observation Date** ({obs_timestamp}).
- - "last year" -> {obs_timestamp} year - 1 (Jan 1st)
+- **Relative Time Resolution**: Calculate absolute dates based on the **Observation Date** ({observation_date}).
+ - "last year" -> {observation_date} year - 1 (Jan 1st)
- "a few months ago" -> Estimate conservatively based on context.
- "currently" -> implies the relationship is active (no `t_end`).
- **End Actions**: If the text says someone "left" or "stopped", capture this in `t_end` while keeping the relation positive (e.g., Relation: "works_at", t_end: ["2023-01-01"]).
@@ -261,6 +263,25 @@ Extract a list of relationships where each relationship consists of:
"""
+# ============================================================================
+# Merge Templates for LLM.CUSTOM_RULE Strategy
+# ============================================================================
+
+
+EDGE_MERGE_RULE = """You are an intelligent data merging assistant.
+You will receive a list of edges representing the exact same relationship (Same Subject -> Same Predicate -> Same Object).
+
+Your task is to merge them into a SINGLE edge object exactly matching the schema.
+
+Merge strategy:
+1. **startNode/endNode**: Keep the node definitions consistent.
+2. **name**: Keep the canonical predicate name (since they are already grouped by this key).
+3. **t_start**: Collect ALL distinct start dates/times from all inputs into a single list. Remove exact duplicates.
+4. **t_end**: Collect ALL distinct end dates/times from all inputs into a single list. Remove exact duplicates.
+5. **t_obs**: Collect ALL distinct observation dates from all inputs into a single list.
+6. **atomic_facts**: Merge all evidence strings into a single list. Remove exact duplicate strings.
+"""
+
# ==============================================================================
# 3. Atom Implementation - Inherits from AutoGraph
# ==============================================================================
@@ -300,6 +321,7 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
observation_date: str | None = None,
chunk_size: int = 2000,
chunk_overlap: int = 200,
+ facts_per_chunk: int = 10,
max_workers: int = 10,
verbose: bool = False,
):
@@ -312,10 +334,12 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
If None, uses current date and time.
chunk_size: Characters per chunk
chunk_overlap: Overlapping characters between chunks
+ facts_per_chunk: Max number of atomic facts to group into a single extraction batch (default: 20)
max_workers: Max concurrent extraction workers
verbose: Display detailed execution logs and progress information
"""
+ self.facts_per_chunk = facts_per_chunk
self.observation_date = observation_date
# 1. Define Key Extractors (critical for deduplication)
@@ -328,6 +352,14 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
# 2. Edge consistency check: tell AutoGraph which nodes this edge connects
nodes_in_edge_fn = lambda x: (x.startNode.name, x.endNode.name)
+ # Edge merger: merges relationship descriptions using EDGE_MERGE_RULE
+ edge_merger = CustomRuleMerger(
+ key_extractor=edge_key_fn,
+ llm_client=llm_client,
+ item_schema=EdgeSchema,
+ rule=EDGE_MERGE_RULE,
+ )
+
# 3. Call parent class initialization
logger.info("🚀 Initializing Atom")
super().__init__(
@@ -344,7 +376,7 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
prompt_for_edge_extraction=Atom_EDGE_EXTRACTION_PROMPT,
# Configure deduplication strategy
node_strategy_or_merger=MergeStrategy.KEEP_EXISTING,
- edge_strategy_or_merger=MergeStrategy.KEEP_EXISTING,
+ edge_strategy_or_merger=edge_merger,
# Optimize indexing: only index name field
node_fields_for_index=["name", "label"],
edge_fields_for_index=["startNode", "name", "endNode"],
@@ -376,10 +408,10 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
Extracted and validated graph.
"""
obs_date_str = self.observation_date or datetime.now().strftime("%Y-%m-%d")
-
+
# ==================== Step 1: Extract Atomic Facts ====================
logger.info("🔍 [Phase 1] Extracting Atomic Facts...")
-
+
# 1. Prepare raw chunks
if len(text) <= self.chunk_size:
raw_chunks = [text]
@@ -399,7 +431,7 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
{"chunk_text": chunk, "observation_date": obs_date_str}
for chunk in raw_chunks
]
- chunk_fact_lists = fact_chain.batch(
+ chunk_fact_lists: List[AtomicFactSchema] = fact_chain.batch(
fact_inputs, config={"max_concurrency": self.max_workers}
)
@@ -413,23 +445,53 @@ class Atom(AutoGraph[NodeSchema, EdgeSchema]):
if not all_facts:
logger.warning("⚠️ No facts extracted. Returning empty graph.")
- return self._create_empty_instance().data
+ return AutoGraphSchema()
# ==================== Step 2: Extract Edges from Facts ====================
logger.info("🔍 [Phase 2] Extracting Edges from Atomic Facts...")
- # 5. Create new context from facts (join with newlines)
- fact_context_text = "\n".join(all_facts)
-
- # 6. Split Fact Context into chunks
- if len(fact_context_text) <= self.chunk_size:
- fact_chunks = [fact_context_text]
- else:
- fact_chunks = self.text_splitter.split_text(fact_context_text)
-
- # 7. Batch Extract Edges directly from Fact Chunks
+ # 5. Group Facts into Chunks (Controlled by count AND size)
+ # This ensures each fact remains intact and fact IDs reset per chunk
+ fact_chunks = []
+ current_batch = []
+ current_char_count = 0
+
+ # Estimate overhead: "[Fact 99]: " + newline is approx 12 chars
+ PREFIX_OVERHEAD = 12
+
+ for fact in all_facts:
+ fact_len = len(fact) + PREFIX_OVERHEAD
+
+ # Check constraints:
+ # 1. Size limit (fuzzy check to keep under chunk_size)
+ # 2. Count limit (facts_per_chunk)
+ size_limit_reached = (current_char_count + fact_len) > self.chunk_size
+ count_limit_reached = len(current_batch) >= self.facts_per_chunk
+
+ if (size_limit_reached or count_limit_reached) and current_batch:
+ # Flush current batch
+ formatted_chunk = "\n".join(
+ [f"[Fact {i+1}]: {f}" for i, f in enumerate(current_batch)]
+ )
+ fact_chunks.append(formatted_chunk)
+
+ # Reset
+ current_batch = []
+ current_char_count = 0
+
+ current_batch.append(fact)
+ current_char_count += fact_len
+
+ # Flush remaining items
+ if current_batch:
+ formatted_chunk = "\n".join(
+ [f"[Fact {i+1}]: {f}" for i, f in enumerate(current_batch)]
+ )
+ fact_chunks.append(formatted_chunk)
+
+ # 6. Batch Extract Edges directly from Fact Chunks
# Format the edge prompt with observation date
- edge_prompt_with_date = self.edge_prompt.format(obs_timestamp=obs_date_str)
+ edge_prompt_with_date = self.edge_prompt.format(observation_date=obs_date_str)
edge_prompt_template = ChatPromptTemplate.from_template(
f"{edge_prompt_with_date}\n\n### Source Text:\n{{chunk_text}}"
)
diff --git a/hyperextract/hypergraphs/hyper_rag.py b/hyperextract/hypergraphs/hyper_rag.py
index a37be29..d47b339 100644
--- a/hyperextract/hypergraphs/hyper_rag.py
+++ b/hyperextract/hypergraphs/hyper_rag.py
@@ -154,7 +154,7 @@ class Hyper_RAG(AutoHypergraph[NodeSchema, EdgeSchema]):
nodes_in_edge_fn = lambda x: x.participants
# 3. Create custom Mergers with LLM.CUSTOM_RULE strategy
- # Node merger: merges entity descriptions using NODE_MERGE_TEMPLATE
+ # Node merger: merges entity descriptions using NODE_MERGE_RULE
node_merger = CustomRuleMerger(
key_extractor=node_key_fn,
llm_client=llm_client,
@@ -162,7 +162,7 @@ class Hyper_RAG(AutoHypergraph[NodeSchema, EdgeSchema]):
rule=NODE_MERGE_RULE,
)
- # Edge merger: merges relationship descriptions using EDGE_MERGE_TEMPLATE
+ # Edge merger: merges relationship descriptions using EDGE_MERGE_RULE
edge_merger = CustomRuleMerger(
key_extractor=edge_key_fn,
llm_client=llm_client,