Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: add Prospectuses / IPO Filings (S-1) templates - ShareholderStructure (AutoGraph) - ownership hierarchies - ProceedsUsage (AutoList) - fund allocation - CompanyHistoryTimeline (AutoTemporalGraph) - corporate milestones
yuxizheb8bbf0561ea3
diff --git a/hyperextract/templates/en/finance/company_history_timeline.py b/hyperextract/templates/en/finance/company_history_timeline.pynew file mode 100644index 0000000..76fd9f8--- /dev/null+++ b/hyperextract/templates/en/finance/company_history_timeline.py@@ -0,0 +1,203 @@+"""Company History Timeline - Chronological extraction of corporate milestones.++Extracts founding events, funding rounds, major pivots, and key milestones+from prospectuses and company histories for due diligence and history mapping.+"""++from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoTemporalGraph++# ==============================================================================+# 1. Schema Definitions+# ==============================================================================+++class CorporateEntity(BaseModel):+ """+ An entity involved in corporate history milestones.+ """++ name: str = Field(+ description="Name of the entity (e.g., company name, founder, investor, acquiree)."+ )+ entity_type: str = Field(+ description="Type: 'Company', 'Founder', 'Investor', 'Acquiree', 'Partner', 'Regulator'."+ )+ description: Optional[str] = Field(+ None, description="Role or context (e.g., 'Series A lead', 'Acquired subsidiary')."+ )+++class CorporateMilestoneEdge(BaseModel):+ """+ A corporate milestone event with temporal context.+ """++ source: str = Field(description="The acting entity name.")+ target: str = Field(description="The affected entity or milestone target.")+ event_type: str = Field(+ description="Type: 'Founding', 'Funding Round', 'Acquisition', 'Product Launch', "+ "'IPO', 'Pivot', 'Partnership', 'Expansion', 'Restructuring', 'Key Hire'."+ )+ start_timestamp: Optional[str] = Field(+ None,+ description="Date of the milestone (e.g., '2015-06', 'March 2018', '2020').",+ )+ end_timestamp: Optional[str] = Field(+ None,+ description="End date if applicable (e.g., acquisition closing date).",+ )+ description: Optional[str] = Field(+ None,+ description="Details of the milestone (e.g., '$50M Series B led by Sequoia').",+ )+ financial_details: Optional[str] = Field(+ None,+ description="Financial terms when available (e.g., valuation, deal size).",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a due diligence analyst. Extract corporate history milestones and the entities "+ "involved from this prospectus or company history document.\n\n"+ "Rules:\n"+ "- Identify founding events, funding rounds, acquisitions, pivots, and key hires.\n"+ "- Extract specific dates or time periods for each milestone.\n"+ "- Capture financial details (valuations, deal sizes) when mentioned.\n"+ "- Maintain chronological accuracy."+)++_NODE_PROMPT = (+ "You are a due diligence analyst. Extract all entities (Nodes) involved in corporate history.\n\n"+ "Extraction Rules:\n"+ "- Identify the company, founders, investors, acquired companies, and partners.\n"+ "- Classify each entity by type.\n"+ "- DO NOT extract events at this stage."+)++_EDGE_PROMPT = (+ "You are a due diligence analyst. Given the entities, extract corporate milestones (Edges) with dates.\n\n"+ "Extraction Rules:\n"+ "- Connect entities through milestone events.\n"+ "- Extract specific dates or time periods.\n"+ "- Capture financial details (deal sizes, valuations).\n"+ "- Classify each milestone by type.\n"+ "- Only create edges between nodes that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class CompanyHistoryTimeline(+ AutoTemporalGraph[CorporateEntity, CorporateMilestoneEdge]+):+ """+ Applicable to: S-1 Prospectuses (Business section), Company About pages,+ Due Diligence reports, Corporate History summaries, Investor Presentations.++ Template for chronologically extracting corporate milestones from prospectuses+ and company histories. Enables due diligence timeline construction and+ corporate evolution tracking.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> history = CompanyHistoryTimeline(llm_client=llm, embedder=embedder)+ >>> text = "Founded in 2015 by John Doe. Raised $10M Series A in 2017..."+ >>> history.feed_text(text)+ >>> history.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ observation_time: str = "2024-01-01",+ extraction_mode: str = "two_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ Initialize the Company History Timeline template.++ Args:+ llm_client (BaseChatModel): The LLM for milestone extraction.+ embedder (Embeddings): Embedding model for deduplication.+ observation_time (str): Reference time for resolving relative dates.+ extraction_mode (str): "one_stage" or "two_stage".+ chunk_size (int): Max characters per chunk.+ chunk_overlap (int): Overlap between chunks.+ max_workers (int): Parallel processing workers.+ verbose (bool): Enable progress logging.+ **kwargs: Additional arguments for AutoTemporalGraph.+ """+ super().__init__(+ node_schema=CorporateEntity,+ edge_schema=CorporateMilestoneEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}|{x.event_type.lower()}|{x.target.strip().lower()}"+ ),+ time_in_edge_extractor=lambda x: x.start_timestamp or "",+ nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ llm_client=llm_client,+ embedder=embedder,+ observation_time=observation_time,+ extraction_mode=extraction_mode,+ prompt=_PROMPT,+ prompt_for_node_extraction=_NODE_PROMPT,+ prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_nodes_for_search: int = 3,+ top_k_edges_for_search: int = 3,+ top_k_nodes_for_chat: int = 3,+ top_k_edges_for_chat: int = 3,+ ) -> None:+ """+ Visualize the company history timeline using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of entities to retrieve. Default 3.+ top_k_edges_for_search (int): Number of milestones to retrieve. Default 3.+ top_k_nodes_for_chat (int): Entities for chat context. Default 3.+ top_k_edges_for_chat (int): Milestones for chat context. Default 3.+ """++ def node_label_extractor(node: CorporateEntity) -> str:+ return f"{node.name} ({node.entity_type})"++ def edge_label_extractor(edge: CorporateMilestoneEdge) -> str:+ date = f" [{edge.start_timestamp}]" if edge.start_timestamp else ""+ return f"{edge.event_type}{date}"++ super().show(+ node_label_extractor=node_label_extractor,+ edge_label_extractor=edge_label_extractor,+ top_k_nodes_for_search=top_k_nodes_for_search,+ top_k_edges_for_search=top_k_edges_for_search,+ top_k_nodes_for_chat=top_k_nodes_for_chat,+ top_k_edges_for_chat=top_k_edges_for_chat,+ )diff --git a/hyperextract/templates/en/finance/proceeds_usage.py b/hyperextract/templates/en/finance/proceeds_usage.pynew file mode 100644index 0000000..b9e9b12--- /dev/null+++ b/hyperextract/templates/en/finance/proceeds_usage.py@@ -0,0 +1,146 @@+"""Proceeds Usage - Extracts fund allocation details from prospectuses.++Extracts project names, allocated amounts, and estimated timelines for IPO+proceeds or debt offering fund usage for post-IPO monitoring.+"""++from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoList++# ==============================================================================+# 1. Schema Definitions+# ==============================================================================+++class ProceedsItem(BaseModel):+ """+ A single use-of-proceeds allocation item.+ """++ use_category: str = Field(+ description="Category of fund usage (e.g., 'R&D Investment', 'Debt Repayment', 'Working Capital', "+ "'Acquisitions', 'Capital Expenditures', 'General Corporate Purposes')."+ )+ project_name: Optional[str] = Field(+ None,+ description="Specific project or initiative name (e.g., 'New Data Center in Virginia', 'Platform 2.0 Development').",+ )+ allocated_amount: Optional[str] = Field(+ None,+ description="Amount allocated (e.g., '$150 million', 'approximately 30% of net proceeds').",+ )+ percentage_of_proceeds: Optional[str] = Field(+ None,+ description="Percentage of total proceeds (e.g., '30%', 'approximately one-third').",+ )+ timeline: Optional[str] = Field(+ None,+ description="Expected deployment timeline (e.g., '12-18 months', 'FY2025-2026').",+ )+ description: Optional[str] = Field(+ None,+ description="Detailed description of how funds will be used.",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are an IPO analyst. Extract all use-of-proceeds allocations from this prospectus "+ "or offering document.\n\n"+ "Rules:\n"+ "- Extract every distinct fund usage category and specific project.\n"+ "- Capture allocated amounts and percentages.\n"+ "- Extract deployment timelines when stated.\n"+ "- Preserve detailed descriptions of how funds will be used.\n"+ "- Extract EVERY allocation independently as a separate item.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class ProceedsUsage(AutoList[ProceedsItem]):+ """+ Applicable to: S-1 Prospectuses (Use of Proceeds section), Debt Offering Memoranda,+ Secondary Offering Prospectuses, SPAC Proxy Statements.++ Template for extracting fund allocation details from prospectuses and offering+ documents. Each allocation is captured as an independent item for post-IPO+ monitoring and proceeds tracking.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> proceeds = ProceedsUsage(llm_client=llm, embedder=embedder)+ >>> prospectus = "We intend to use approximately $150M for R&D, $100M for debt repayment..."+ >>> proceeds.feed_text(prospectus)+ >>> proceeds.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ Initialize the Proceeds Usage template.++ Args:+ llm_client (BaseChatModel): The LLM for proceeds extraction.+ embedder (Embeddings): Embedding model for indexing.+ chunk_size (int): Max characters per chunk.+ chunk_overlap (int): Overlap between chunks.+ max_workers (int): Parallel processing workers.+ verbose (bool): Enable progress logging.+ **kwargs: Additional arguments for AutoList.+ """+ super().__init__(+ item_schema=ProceedsItem,+ llm_client=llm_client,+ embedder=embedder,+ prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_for_search: int = 3,+ top_k_for_chat: int = 3,+ ) -> None:+ """+ Visualize the proceeds usage list.++ Args:+ top_k_for_search (int): Items for search. Default 3.+ top_k_for_chat (int): Items for chat context. Default 3.+ """++ def label_extractor(item: ProceedsItem) -> str:+ amount = f": {item.allocated_amount}" if item.allocated_amount else ""+ return f"{item.use_category}{amount}"++ super().show(+ item_label_extractor=label_extractor,+ top_k_for_search=top_k_for_search,+ top_k_for_chat=top_k_for_chat,+ )diff --git a/hyperextract/templates/en/finance/shareholder_structure.py b/hyperextract/templates/en/finance/shareholder_structure.pynew file mode 100644index 0000000..d3f80f4--- /dev/null+++ b/hyperextract/templates/en/finance/shareholder_structure.py@@ -0,0 +1,205 @@+"""Shareholder Structure - Extracts ownership hierarchies from prospectuses.++Maps shareholder percentages, controlling paths, and parent-subsidiary relations+from S-1 filings and proxy statements for ultimate controller analysis.+"""++from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoGraph++# ==============================================================================+# 1. Schema Definitions+# ==============================================================================+++class OwnershipEntity(BaseModel):+ """+ An entity in the ownership structure.+ """++ name: str = Field(+ description="Name of the entity (e.g., person, fund, holding company, trust)."+ )+ entity_type: str = Field(+ description="Type: 'Individual', 'Institutional Investor', 'Holding Company', 'Venture Capital', "+ "'Private Equity', 'Trust', 'Government Entity', 'Issuing Company'."+ )+ description: Optional[str] = Field(+ None,+ description="Additional details (e.g., 'Co-founder and CEO', 'Series B lead investor').",+ )+++class OwnershipEdge(BaseModel):+ """+ An ownership or control relationship between entities.+ """++ source: str = Field(description="The owner/parent entity name.")+ target: str = Field(description="The owned/subsidiary entity name.")+ relationship_type: str = Field(+ description="Type: 'Direct Ownership', 'Indirect Ownership', 'Beneficial Ownership', "+ "'Voting Control', 'Board Seat', 'Parent-Subsidiary'."+ )+ ownership_percentage: Optional[str] = Field(+ None,+ description="Percentage ownership (e.g., '15.3%', '51%', 'Controlling interest').",+ )+ share_class: Optional[str] = Field(+ None,+ description="Class of shares (e.g., 'Class A', 'Class B (10x voting)', 'Preferred Series C').",+ )+ shares_held: Optional[str] = Field(+ None,+ description="Number of shares held (e.g., '45,000,000 shares').",+ )+ voting_power: Optional[str] = Field(+ None,+ description="Voting power percentage if different from ownership (e.g., '65% voting power').",+ )+ lock_up_period: Optional[str] = Field(+ None,+ description="Post-IPO lock-up period if applicable (e.g., '180 days').",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a corporate governance analyst. Extract the ownership structure including shareholders, "+ "holding companies, and their ownership relationships from this prospectus or proxy filing.\n\n"+ "Rules:\n"+ "- Identify all significant shareholders (5%+ beneficial owners).\n"+ "- Extract ownership percentages and share classes.\n"+ "- Map parent-subsidiary and holding company structures.\n"+ "- Note dual-class voting structures and voting power differentials.\n"+ "- Capture lock-up periods and post-IPO restrictions."+)++_NODE_PROMPT = (+ "You are a corporate governance analyst. Extract all ownership entities (Nodes).\n\n"+ "Extraction Rules:\n"+ "- Identify individuals, institutional investors, holding companies, and trusts.\n"+ "- Identify the issuing company itself.\n"+ "- Classify each entity by type.\n"+ "- DO NOT extract ownership relationships at this stage."+)++_EDGE_PROMPT = (+ "You are a corporate governance analyst. Given the entities, extract ownership "+ "and control relationships (Edges).\n\n"+ "Extraction Rules:\n"+ "- Connect owners to their holdings.\n"+ "- Extract ownership percentages and share classes.\n"+ "- Note voting power differentials.\n"+ "- Capture lock-up periods.\n"+ "- Only create edges between nodes that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class ShareholderStructure(AutoGraph[OwnershipEntity, OwnershipEdge]):+ """+ Applicable to: S-1 Prospectuses, Proxy Statements (DEF 14A), Schedule 13D/G filings,+ Annual Reports (Beneficial Ownership sections), IPO Filings.++ Template for extracting and mapping corporate ownership structures. Enables+ ultimate controller analysis, voting power assessment, and post-IPO lock-up tracking.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> ownership = ShareholderStructure(llm_client=llm, embedder=embedder)+ >>> prospectus = "The following table sets forth beneficial ownership: CEO holds 15.3%..."+ >>> ownership.feed_text(prospectus)+ >>> ownership.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "two_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ Initialize the Shareholder Structure template.++ Args:+ llm_client (BaseChatModel): The LLM for ownership extraction.+ embedder (Embeddings): Embedding model for deduplication.+ extraction_mode (str): "one_stage" or "two_stage".+ chunk_size (int): Max characters per chunk.+ chunk_overlap (int): Overlap between chunks.+ max_workers (int): Parallel processing workers.+ verbose (bool): Enable progress logging.+ **kwargs: Additional arguments for AutoGraph.+ """+ super().__init__(+ node_schema=OwnershipEntity,+ edge_schema=OwnershipEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}--({x.relationship_type})-->{x.target.strip().lower()}"+ ),+ nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ llm_client=llm_client,+ embedder=embedder,+ extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ prompt=_PROMPT,+ prompt_for_node_extraction=_NODE_PROMPT,+ prompt_for_edge_extraction=_EDGE_PROMPT,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_nodes_for_search: int = 3,+ top_k_edges_for_search: int = 3,+ top_k_nodes_for_chat: int = 3,+ top_k_edges_for_chat: int = 3,+ ) -> None:+ """+ Visualize the shareholder structure graph using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of entities to retrieve. Default 3.+ top_k_edges_for_search (int): Number of relationships to retrieve. Default 3.+ top_k_nodes_for_chat (int): Entities for chat context. Default 3.+ top_k_edges_for_chat (int): Relationships for chat context. Default 3.+ """++ def node_label_extractor(node: OwnershipEntity) -> str:+ return f"{node.name} ({node.entity_type})"++ def edge_label_extractor(edge: OwnershipEdge) -> str:+ pct = f" {edge.ownership_percentage}" if edge.ownership_percentage else ""+ return f"{edge.relationship_type}{pct}"++ super().show(+ node_label_extractor=node_label_extractor,+ edge_label_extractor=edge_label_extractor,+ top_k_nodes_for_search=top_k_nodes_for_search,+ top_k_edges_for_search=top_k_edges_for_search,+ top_k_nodes_for_chat=top_k_nodes_for_chat,+ top_k_edges_for_chat=top_k_edges_for_chat,+ )diff --git a/hyperextract/templates/zh/finance/company_history_timeline.py b/hyperextract/templates/zh/finance/company_history_timeline.pynew file mode 100644index 0000000..bc7f707--- /dev/null+++ b/hyperextract/templates/zh/finance/company_history_timeline.py@@ -0,0 +1,195 @@+from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoTemporalGraph++# ==============================================================================+# 1. Schema 定义+# ==============================================================================+++class CorporateEntity(BaseModel):+ """+ 参与公司历史里程碑的实体。+ """++ name: str = Field(+ description="实体名称(例如公司名称、创始人、投资者、被收购方)。"+ )+ entity_type: str = Field(+ description='类型:"公司"、"创始人"、"投资者"、"被收购方"、"合作伙伴"、"监管机构"。'+ )+ description: Optional[str] = Field(+ None, description="角色或背景信息(例如'A 轮领投方'、'被收购子公司')。"+ )+++class CorporateMilestoneEdge(BaseModel):+ """+ 带有时间上下文的公司里程碑事件。+ """++ source: str = Field(description="发起方实体名称。")+ target: str = Field(description="受影响的实体或里程碑目标。")+ event_type: str = Field(+ description='类型:"创立"、"融资轮次"、"收购"、"产品发布"、'+ '"IPO"、"战略转型"、"合作"、"扩张"、"重组"、"关键人才引进"。'+ )+ start_timestamp: Optional[str] = Field(+ None,+ description="里程碑日期(例如'2015-06'、'2018 年 3 月'、'2020')。",+ )+ end_timestamp: Optional[str] = Field(+ None,+ description="结束日期(如适用,例如收购完成日期)。",+ )+ description: Optional[str] = Field(+ None,+ description="里程碑详情(例如'红杉资本领投 5000 万美元 B 轮融资')。",+ )+ financial_details: Optional[str] = Field(+ None,+ description="财务条款(如有,例如估值、交易规模)。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是尽职调查分析师。从本招股说明书或公司历史文档中提取公司历史里程碑及相关实体。\n\n"+ "规则:\n"+ "- 识别创立事件、融资轮次、收购、战略转型和关键人才引进。\n"+ "- 提取每个里程碑的具体日期或时间段。\n"+ "- 捕捉财务细节(估值、交易规模)(如有提及)。\n"+ "- 保持时间顺序的准确性。"+)++_NODE_PROMPT = (+ "你是尽职调查分析师。提取公司历史中涉及的所有实体(节点)。\n\n"+ "提取规则:\n"+ "- 识别公司、创始人、投资者、被收购公司和合作伙伴。\n"+ "- 按类型对每个实体进行分类。\n"+ "- 此阶段不提取事件。"+)++_EDGE_PROMPT = (+ "你是尽职调查分析师。在获得实体清单的基础上,提取带有日期的公司里程碑(边)。\n\n"+ "提取规则:\n"+ "- 通过里程碑事件连接实体。\n"+ "- 提取具体日期或时间段。\n"+ "- 捕捉财务细节(交易规模、估值)。\n"+ "- 按类型对每个里程碑进行分类。\n"+ "- 仅在提供的列表中存在的节点之间创建边。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class CompanyHistoryTimeline(+ AutoTemporalGraph[CorporateEntity, CorporateMilestoneEdge]+):+ """+ 适用文档: S-1 招股说明书(业务部分)、公司简介页面、+ 尽职调查报告、公司历史摘要、投资者演示材料。++ 模板用于从招股说明书和公司历史中按时间顺序提取公司里程碑。支持尽职调查+ 时间线构建和企业演进跟踪。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> history = CompanyHistoryTimeline(llm_client=llm, embedder=embedder)+ >>> text = "公司于 2015 年由张三创立。2017 年完成 1000 万美元 A 轮融资..."+ >>> history.feed_text(text)+ >>> history.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ observation_time: str = "2024-01-01",+ extraction_mode: str = "two_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ 初始化公司历史时间线模板。++ Args:+ llm_client (BaseChatModel): 用于里程碑提取的 LLM。+ embedder (Embeddings): 用于去重的嵌入模型。+ observation_time (str): 用于解析相对日期的参考时间。+ extraction_mode (str): "one_stage" 或 "two_stage"。+ chunk_size (int): 每个分块的最大字符数。+ chunk_overlap (int): 分块之间的重叠。+ max_workers (int): 并行处理工作线程数。+ verbose (bool): 是否启用进度日志。+ **kwargs: AutoTemporalGraph 的其他参数。+ """+ super().__init__(+ node_schema=CorporateEntity,+ edge_schema=CorporateMilestoneEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}|{x.event_type.lower()}|{x.target.strip().lower()}"+ ),+ time_in_edge_extractor=lambda x: x.start_timestamp or "",+ nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ llm_client=llm_client,+ embedder=embedder,+ observation_time=observation_time,+ extraction_mode=extraction_mode,+ prompt=_PROMPT,+ prompt_for_node_extraction=_NODE_PROMPT,+ prompt_for_edge_extraction=_EDGE_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_nodes_for_search: int = 3,+ top_k_edges_for_search: int = 3,+ top_k_nodes_for_chat: int = 3,+ top_k_edges_for_chat: int = 3,+ ) -> None:+ """+ 使用 OntoSight 可视化公司历史时间线。++ Args:+ top_k_nodes_for_search (int): 检索的实体数。默认 3。+ top_k_edges_for_search (int): 检索的里程碑数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的实体数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的里程碑数。默认 3。+ """++ def node_label_extractor(node: CorporateEntity) -> str:+ return f"{node.name} ({node.entity_type})"++ def edge_label_extractor(edge: CorporateMilestoneEdge) -> str:+ date = f" [{edge.start_timestamp}]" if edge.start_timestamp else ""+ return f"{edge.event_type}{date}"++ super().show(+ node_label_extractor=node_label_extractor,+ edge_label_extractor=edge_label_extractor,+ top_k_nodes_for_search=top_k_nodes_for_search,+ top_k_edges_for_search=top_k_edges_for_search,+ top_k_nodes_for_chat=top_k_nodes_for_chat,+ top_k_edges_for_chat=top_k_edges_for_chat,+ )diff --git a/hyperextract/templates/zh/finance/proceeds_usage.py b/hyperextract/templates/zh/finance/proceeds_usage.pynew file mode 100644index 0000000..7416af1--- /dev/null+++ b/hyperextract/templates/zh/finance/proceeds_usage.py@@ -0,0 +1,138 @@+from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoList++# ==============================================================================+# 1. Schema 定义+# ==============================================================================+++class ProceedsItem(BaseModel):+ """+ 单项募集资金用途分配条目。+ """++ use_category: str = Field(+ description="资金用途类别(例如'研发投入'、'偿还债务'、'营运资金'、"+ "'收购'、'资本支出'、'一般企业用途')。"+ )+ project_name: Optional[str] = Field(+ None,+ description="具体项目或计划名称(例如'弗吉尼亚新数据中心'、'平台 2.0 开发')。",+ )+ allocated_amount: Optional[str] = Field(+ None,+ description="分配金额(例如'1.5 亿美元'、'约占净募集资金的 30%')。",+ )+ percentage_of_proceeds: Optional[str] = Field(+ None,+ description="占总募集资金的百分比(例如'30%'、'约三分之一')。",+ )+ timeline: Optional[str] = Field(+ None,+ description="预计资金使用时间表(例如'12-18 个月'、'2025-2026 财年')。",+ )+ description: Optional[str] = Field(+ None,+ description="资金具体使用方式的详细说明。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是 IPO 分析师。从本招股说明书或发行文件中提取所有募集资金用途分配信息。\n\n"+ "规则:\n"+ "- 提取每一项资金用途类别和具体项目。\n"+ "- 捕捉分配金额和百分比。\n"+ "- 提取资金使用时间表(如有说明)。\n"+ "- 保留资金使用方式的详细描述。\n"+ "- 将每项分配作为独立条目提取。\n\n"+ "### 原文:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class ProceedsUsage(AutoList[ProceedsItem]):+ """+ 适用文档: S-1 招股说明书(募集资金用途部分)、债券发行备忘录、+ 二次发行招股说明书、SPAC 委托声明书。++ 模板用于从招股说明书和发行文件中提取资金分配明细。每项分配作为独立条目捕捉,+ 便于 IPO 后监控和资金用途跟踪。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> proceeds = ProceedsUsage(llm_client=llm, embedder=embedder)+ >>> prospectus = "我们拟将约 1.5 亿美元用于研发,1 亿美元用于偿还债务..."+ >>> proceeds.feed_text(prospectus)+ >>> proceeds.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ 初始化募集资金用途模板。++ Args:+ llm_client (BaseChatModel): 用于资金用途提取的 LLM。+ embedder (Embeddings): 用于索引的嵌入模型。+ chunk_size (int): 每个分块的最大字符数。+ chunk_overlap (int): 分块之间的重叠。+ max_workers (int): 并行处理工作线程数。+ verbose (bool): 是否启用进度日志。+ **kwargs: AutoList 的其他参数。+ """+ super().__init__(+ item_schema=ProceedsItem,+ llm_client=llm_client,+ embedder=embedder,+ prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_for_search: int = 3,+ top_k_for_chat: int = 3,+ ) -> None:+ """+ 可视化募集资金用途列表。++ Args:+ top_k_for_search (int): 检索的条目数。默认 3。+ top_k_for_chat (int): 对话上下文中的条目数。默认 3。+ """++ def label_extractor(item: ProceedsItem) -> str:+ amount = f": {item.allocated_amount}" if item.allocated_amount else ""+ return f"{item.use_category}{amount}"++ super().show(+ item_label_extractor=label_extractor,+ top_k_for_search=top_k_for_search,+ top_k_for_chat=top_k_for_chat,+ )diff --git a/hyperextract/templates/zh/finance/shareholder_structure.py b/hyperextract/templates/zh/finance/shareholder_structure.pynew file mode 100644index 0000000..eabb863--- /dev/null+++ b/hyperextract/templates/zh/finance/shareholder_structure.py@@ -0,0 +1,198 @@+from typing import Optional, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from hyperextract.types import AutoGraph++# ==============================================================================+# 1. Schema 定义+# ==============================================================================+++class OwnershipEntity(BaseModel):+ """+ 股权结构中的实体。+ """++ name: str = Field(+ description="实体名称(例如个人、基金、控股公司、信托)。"+ )+ entity_type: str = Field(+ description='类型:"个人"、"机构投资者"、"控股公司"、"风险投资"、'+ '"私募股权"、"信托"、"政府实体"、"发行公司"。'+ )+ description: Optional[str] = Field(+ None,+ description="附加信息(例如'联合创始人兼 CEO'、'B 轮领投机构')。",+ )+++class OwnershipEdge(BaseModel):+ """+ 实体之间的持股或控制关系。+ """++ source: str = Field(description="持有方/母公司实体名称。")+ target: str = Field(description="被持有方/子公司实体名称。")+ relationship_type: str = Field(+ description='类型:"直接持股"、"间接持股"、"实益所有权"、'+ '"投票权控制"、"董事会席位"、"母子公司"。'+ )+ ownership_percentage: Optional[str] = Field(+ None,+ description="持股比例(例如'15.3%'、'51%'、'控股权')。",+ )+ share_class: Optional[str] = Field(+ None,+ description="股份类别(例如'A 类普通股'、'B 类(10 倍投票权)'、'C 轮优先股')。",+ )+ shares_held: Optional[str] = Field(+ None,+ description="持有股份数量(例如'45,000,000 股')。",+ )+ voting_power: Optional[str] = Field(+ None,+ description="投票权百分比(若与持股比例不同,例如'65% 投票权')。",+ )+ lock_up_period: Optional[str] = Field(+ None,+ description="IPO 后锁定期(如适用,例如'180 天')。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是公司治理分析师。从本招股说明书或委托声明文件中提取股权结构,包括股东、"+ "控股公司及其持股关系。\n\n"+ "规则:\n"+ "- 识别所有重要股东(5% 以上实益所有人)。\n"+ "- 提取持股比例和股份类别。\n"+ "- 映射母子公司和控股公司结构。\n"+ "- 注意双重股权结构和投票权差异。\n"+ "- 捕捉锁定期和 IPO 后限制条款。"+)++_NODE_PROMPT = (+ "你是公司治理分析师。提取所有股权实体(节点)。\n\n"+ "提取规则:\n"+ "- 识别个人、机构投资者、控股公司和信托。\n"+ "- 识别发行公司本身。\n"+ "- 按类型对每个实体进行分类。\n"+ "- 此阶段不提取持股关系。"+)++_EDGE_PROMPT = (+ "你是公司治理分析师。在获得实体清单的基础上,提取持股和控制关系(边)。\n\n"+ "提取规则:\n"+ "- 将持有方连接到其持有的资产。\n"+ "- 提取持股比例和股份类别。\n"+ "- 注意投票权差异。\n"+ "- 捕捉锁定期。\n"+ "- 仅在提供的列表中存在的节点之间创建边。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class ShareholderStructure(AutoGraph[OwnershipEntity, OwnershipEdge]):+ """+ 适用文档: S-1 招股说明书、委托声明书(DEF 14A)、Schedule 13D/G 申报文件、+ 年度报告(实益所有权部分)、IPO 申报文件。++ 模板用于提取和映射公司股权结构。支持最终控制人分析、投票权评估和+ IPO 后锁定期跟踪。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> ownership = ShareholderStructure(llm_client=llm, embedder=embedder)+ >>> prospectus = "下表列示实益所有权情况:CEO 持有 15.3%..."+ >>> ownership.feed_text(prospectus)+ >>> ownership.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "two_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ 初始化股东结构图谱模板。++ Args:+ llm_client (BaseChatModel): 用于股权提取的 LLM。+ embedder (Embeddings): 用于去重的嵌入模型。+ extraction_mode (str): "one_stage" 或 "two_stage"。+ chunk_size (int): 每个分块的最大字符数。+ chunk_overlap (int): 分块之间的重叠。+ max_workers (int): 并行处理工作线程数。+ verbose (bool): 是否启用进度日志。+ **kwargs: AutoGraph 的其他参数。+ """+ super().__init__(+ node_schema=OwnershipEntity,+ edge_schema=OwnershipEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}--({x.relationship_type})-->{x.target.strip().lower()}"+ ),+ nodes_in_edge_extractor=lambda x: (x.source.strip(), x.target.strip()),+ llm_client=llm_client,+ embedder=embedder,+ extraction_mode=extraction_mode,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ prompt=_PROMPT,+ prompt_for_node_extraction=_NODE_PROMPT,+ prompt_for_edge_extraction=_EDGE_PROMPT,+ **kwargs,+ )++ def show(+ self,+ *,+ top_k_nodes_for_search: int = 3,+ top_k_edges_for_search: int = 3,+ top_k_nodes_for_chat: int = 3,+ top_k_edges_for_chat: int = 3,+ ) -> None:+ """+ 使用 OntoSight 可视化股东结构图。++ Args:+ top_k_nodes_for_search (int): 检索的实体数。默认 3。+ top_k_edges_for_search (int): 检索的关系数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的实体数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的关系数。默认 3。+ """++ def node_label_extractor(node: OwnershipEntity) -> str:+ return f"{node.name} ({node.entity_type})"++ def edge_label_extractor(edge: OwnershipEdge) -> str:+ pct = f" {edge.ownership_percentage}" if edge.ownership_percentage else ""+ return f"{edge.relationship_type}{pct}"++ super().show(+ node_label_extractor=node_label_extractor,+ edge_label_extractor=edge_label_extractor,+ top_k_nodes_for_search=top_k_nodes_for_search,+ top_k_edges_for_search=top_k_edges_for_search,+ top_k_nodes_for_chat=top_k_nodes_for_chat,+ top_k_edges_for_chat=top_k_edges_for_chat,+ )