Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: add Equity Research Reports templates - ResearchNoteSummary (AutoModel) - ratings & target prices - FinancialForecast (AutoList) - revenue/EPS projections - ValuationLogicMap (AutoGraph) - valuation driver chains - FactorInfluenceHypergraph (AutoHypergraph) - multi-factor analysis - RiskFactorList (AutoList) - downside risks
yuxizhee4f0532a93d0
diff --git a/hyperextract/templates/en/finance/factor_influence_hypergraph.py b/hyperextract/templates/en/finance/factor_influence_hypergraph.pynew file mode 100644index 0000000..eda97ff--- /dev/null+++ b/hyperextract/templates/en/finance/factor_influence_hypergraph.py@@ -0,0 +1,200 @@+"""Factor Influence Hypergraph - Models multi-factor relationships in equity analysis.++Models complex relationships between macro factors, industry trends, and company+metrics as hyperedges connecting multiple factors simultaneously.+"""++from typing import Optional, List, 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 AutoHypergraph++# ==============================================================================+# 1. Schema Definitions+# ==============================================================================+++class InvestmentFactor(BaseModel):+ """+ A factor in multi-factor investment analysis.+ """++ name: str = Field(+ description="Name of the factor (e.g., 'GDP Growth', 'Semiconductor Cycle', 'Cloud Revenue')."+ )+ factor_level: str = Field(+ description="Level: 'Macro', 'Industry', 'Company', 'Technical'."+ )+ current_reading: Optional[str] = Field(+ None,+ description="Current value or state (e.g., '3.2% YoY', 'Upcycle Phase', 'Accelerating').",+ )+ description: Optional[str] = Field(+ None, description="Explanation of this factor's significance."+ )+++class FactorInteraction(BaseModel):+ """+ A multi-factor interaction where several factors jointly influence an outcome.+ """++ interaction_name: str = Field(+ description="Descriptive name (e.g., 'AI Capex Multiplier Effect', 'Rate-Sensitive Rotation')."+ )+ participating_factors: List[str] = Field(+ description="Names of all factors involved in this interaction."+ )+ interaction_type: str = Field(+ description="Type: 'Reinforcing', 'Offsetting', 'Conditional', 'Cascading', 'Threshold'."+ )+ outcome: str = Field(+ description="The combined outcome or effect (e.g., 'Accelerated revenue growth for cloud names')."+ )+ mechanism: Optional[str] = Field(+ None,+ description="How the factors interact to produce the outcome.",+ )+ confidence: Optional[str] = Field(+ None,+ description="Analyst's confidence in this interaction: 'High', 'Medium', 'Low'.",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a quantamental research analyst. Extract investment factors and their multi-factor "+ "interactions from this research report.\n\n"+ "Rules:\n"+ "- Identify macro, industry, and company-level factors.\n"+ "- Extract complex interactions where multiple factors jointly produce an outcome.\n"+ "- A hyperedge connects ALL participating factors, not just pairs.\n"+ "- Capture the mechanism and outcome of each interaction."+)++_NODE_PROMPT = (+ "You are a quantamental research analyst. Extract all investment factors (Nodes).\n\n"+ "Extraction Rules:\n"+ "- Identify macro indicators, industry metrics, and company KPIs.\n"+ "- Capture current values or readings.\n"+ "- Classify each factor by level.\n"+ "- DO NOT extract interactions at this stage."+)++_EDGE_PROMPT = (+ "You are a quantamental research analyst. Given the factors, extract multi-factor "+ "interactions (Hyperedges) where multiple factors jointly influence outcomes.\n\n"+ "Extraction Rules:\n"+ "- Each hyperedge should connect 2 or more factors.\n"+ "- Describe the interaction mechanism and outcome.\n"+ "- Classify the interaction type.\n"+ "- Only reference factors that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class FactorInfluenceHypergraph(AutoHypergraph[InvestmentFactor, FactorInteraction]):+ """+ Applicable to: Multi-Factor Research Reports, Quantamental Analysis,+ Macro Strategy Notes, Cross-Asset Research, Factor Attribution Studies.++ Template for modeling complex multi-factor relationships in equity analysis.+ Uses hyperedges to capture interactions where multiple factors jointly influence+ an outcome, going beyond simple pairwise relationships.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> factors = FactorInfluenceHypergraph(llm_client=llm, embedder=embedder)+ >>> report = "Rising rates combined with strong GDP and AI capex create a rotation into quality growth..."+ >>> factors.feed_text(report)+ >>> factors.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 Factor Influence Hypergraph template.++ Args:+ llm_client (BaseChatModel): The LLM for factor 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 AutoHypergraph.+ """+ super().__init__(+ node_schema=InvestmentFactor,+ edge_schema=FactorInteraction,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: x.interaction_name.strip().lower(),+ nodes_in_edge_extractor=lambda x: tuple(+ f.strip().lower() for f in x.participating_factors+ ),+ llm_client=llm_client,+ embedder=embedder,+ 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 factor influence hypergraph using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of factors to retrieve. Default 3.+ top_k_edges_for_search (int): Number of interactions to retrieve. Default 3.+ top_k_nodes_for_chat (int): Factors for chat context. Default 3.+ top_k_edges_for_chat (int): Interactions for chat context. Default 3.+ """++ def node_label_extractor(node: InvestmentFactor) -> str:+ reading = f": {node.current_reading}" if node.current_reading else ""+ return f"{node.name} [{node.factor_level}]{reading}"++ def edge_label_extractor(edge: FactorInteraction) -> str:+ return f"[{edge.interaction_type}] {edge.interaction_name}"++ 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/financial_forecast.py b/hyperextract/templates/en/finance/financial_forecast.pynew file mode 100644index 0000000..7f505bf--- /dev/null+++ b/hyperextract/templates/en/finance/financial_forecast.py@@ -0,0 +1,147 @@+"""Financial Forecast - Extracts projected financial data from equity research reports.++Extracts revenue, EPS, PE, and other financial projections for future periods+from analyst reports for consensus analysis and financial modeling.+"""++from typing import Optional, List, 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 ForecastItem(BaseModel):+ """+ A single financial projection for a specific metric and period.+ """++ metric: str = Field(+ description="Financial metric being projected (e.g., 'Revenue', 'EPS', 'EBITDA', 'Operating Margin', 'Free Cash Flow')."+ )+ period: str = Field(+ description="Forecast period (e.g., 'FY2025E', 'Q1 2025E', 'CY2026E')."+ )+ estimate: str = Field(+ description="Projected value (e.g., '$120.5B', '$6.25', '35.2%')."+ )+ prior_estimate: Optional[str] = Field(+ None, description="Previous estimate if revised (e.g., '$115.0B')."+ )+ consensus: Optional[str] = Field(+ None, description="Street consensus estimate for comparison (e.g., '$118.2B')."+ )+ growth_rate: Optional[str] = Field(+ None,+ description="Implied growth rate (e.g., '+15% YoY', 'flat').",+ )+ assumptions: Optional[str] = Field(+ None,+ description="Key assumptions underlying the estimate (e.g., 'assumes 5M unit increase').",+ )+ source_firm: Optional[str] = Field(+ None, description="Research firm providing the estimate."+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a financial analyst building earnings models. Extract all financial projections "+ "and estimates from this equity research report.\n\n"+ "Rules:\n"+ "- Extract every projected metric with its specific time period.\n"+ "- Capture both current and prior estimates when revisions are noted.\n"+ "- Extract consensus estimates when compared.\n"+ "- Capture growth rates and key assumptions.\n"+ "- Extract EVERY forecast independently as a separate item.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class FinancialForecast(AutoList[ForecastItem]):+ """+ Applicable to: Equity Research Reports, Earnings Estimates, Financial Models,+ Consensus Estimate Reports, Analyst Forecasts.++ Template for extracting projected financial data from analyst reports. Each+ forecast is captured as an independent list item, enabling consensus analysis,+ estimate revision tracking, and financial model building.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> forecast = FinancialForecast(llm_client=llm, embedder=embedder)+ >>> report = "We raise our FY2025 revenue estimate to $120.5B (from $115B)..."+ >>> forecast.feed_text(report)+ >>> forecast.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 Financial Forecast template.++ Args:+ llm_client (BaseChatModel): The LLM for estimate 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=ForecastItem,+ 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 financial forecast 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: ForecastItem) -> str:+ return f"{item.metric} ({item.period}): {item.estimate}"++ 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/research_note_summary.py b/hyperextract/templates/en/finance/research_note_summary.pynew file mode 100644index 0000000..23b5a0b--- /dev/null+++ b/hyperextract/templates/en/finance/research_note_summary.py@@ -0,0 +1,149 @@+"""Research Note Summary - Extracts core investment thesis from equity research reports.++Extracts ratings, target prices, and top-level investment logic from analyst research+notes for report database population and screening.+"""++from typing import Optional, List, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from ontomem.merger import MergeStrategy+from hyperextract.types import AutoModel++# ==============================================================================+# 1. Schema Definitions+# ==============================================================================+++class ResearchNoteSummarySchema(BaseModel):+ """+ Structured summary of an equity research report.+ """++ company_name: Optional[str] = Field(+ None, description="Name of the covered company."+ )+ ticker: Optional[str] = Field(+ None, description="Stock ticker symbol (e.g., 'AAPL', 'NVDA')."+ )+ analyst_name: Optional[str] = Field(+ None, description="Name of the lead analyst."+ )+ research_firm: Optional[str] = Field(+ None, description="Name of the research firm (e.g., 'Goldman Sachs', 'Morgan Stanley')."+ )+ report_date: Optional[str] = Field(+ None, description="Publication date of the report."+ )+ rating: Optional[str] = Field(+ None,+ description="Analyst rating: 'Buy', 'Overweight', 'Hold', 'Neutral', 'Sell', 'Underweight'.",+ )+ prior_rating: Optional[str] = Field(+ None, description="Previous rating if changed."+ )+ target_price: Optional[str] = Field(+ None, description="Current price target (e.g., '$150.00')."+ )+ prior_target_price: Optional[str] = Field(+ None, description="Previous price target if changed."+ )+ current_price: Optional[str] = Field(+ None, description="Stock price at time of report."+ )+ investment_thesis: Optional[str] = Field(+ None,+ description="Core investment thesis or key argument for the rating.",+ )+ key_catalysts: Optional[List[str]] = Field(+ None,+ description="Near-term catalysts identified (e.g., ['Q4 earnings beat', 'New product launch', 'Regulatory approval']).",+ )+ key_risks: Optional[List[str]] = Field(+ None,+ description="Key risks highlighted by the analyst.",+ )+ revenue_estimate: Optional[str] = Field(+ None, description="Analyst's revenue estimate for the current/next fiscal year."+ )+ eps_estimate: Optional[str] = Field(+ None, description="Analyst's EPS estimate for the current/next fiscal year."+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are an equity research analyst. Extract the core investment thesis, rating, target price, "+ "and key arguments from this research report.\n\n"+ "Rules:\n"+ "- Extract the analyst's rating and any rating changes.\n"+ "- Capture target price and prior target price if changed.\n"+ "- Summarize the core investment thesis concisely.\n"+ "- List key catalysts and risks as identified by the analyst.\n"+ "- Extract financial estimates (revenue, EPS) when stated.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class ResearchNoteSummary(AutoModel[ResearchNoteSummarySchema]):+ """+ Applicable to: Equity Research Reports, Analyst Notes, Rating Changes,+ Initiation of Coverage reports, Sector Research.++ Template for extracting the core investment thesis and key parameters from+ equity research reports. Produces a single structured summary per report for+ database population and screening.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> summary = ResearchNoteSummary(llm_client=llm, embedder=embedder)+ >>> report = "We upgrade AAPL to Buy with a $200 price target..."+ >>> summary.feed_text(report)+ >>> print(summary.data)+ """++ 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 Research Note Summary template.++ Args:+ llm_client (BaseChatModel): The LLM for report 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 AutoModel.+ """+ super().__init__(+ data_schema=ResearchNoteSummarySchema,+ llm_client=llm_client,+ embedder=embedder,+ strategy_or_merger=MergeStrategy.LLM.BALANCED,+ prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )diff --git a/hyperextract/templates/en/finance/risk_factor_list.py b/hyperextract/templates/en/finance/risk_factor_list.pynew file mode 100644index 0000000..fe0c021--- /dev/null+++ b/hyperextract/templates/en/finance/risk_factor_list.py@@ -0,0 +1,142 @@+"""Risk Factor List - Extracts downside risks from equity research reports.++Lists specific downside risks identified by analysts including regulatory,+FX, supply chain, and other risk categories for risk 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 RiskItem(BaseModel):+ """+ A specific downside risk identified in equity research.+ """++ risk_name: str = Field(+ description="Concise name of the risk (e.g., 'Regulatory Tightening in EU', 'FX Headwinds from Strong Dollar')."+ )+ risk_category: str = Field(+ description="Category: 'Regulatory', 'Competitive', 'Macroeconomic', 'Operational', 'FX/Currency', "+ "'Geopolitical', 'Technology', 'Legal/Litigation', 'ESG', 'Execution'."+ )+ description: str = Field(+ description="Detailed description of the risk scenario."+ )+ potential_impact: Optional[str] = Field(+ None,+ description="Estimated financial impact (e.g., '3-5% revenue downside', '$0.50 EPS risk').",+ )+ probability: Optional[str] = Field(+ None,+ description="Analyst's probability assessment: 'High', 'Medium', 'Low'.",+ )+ time_horizon: Optional[str] = Field(+ None,+ description="When the risk could materialize (e.g., 'Near-term', '2025', '12-18 months').",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a risk analyst reviewing equity research reports. Extract all downside risks "+ "and risk factors identified by the analyst.\n\n"+ "Rules:\n"+ "- Extract every distinct risk factor mentioned.\n"+ "- Categorize each risk appropriately.\n"+ "- Capture quantified impact estimates when provided.\n"+ "- Note probability assessments and time horizons.\n"+ "- Extract EVERY risk independently as a separate item.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class RiskFactorList(AutoList[RiskItem]):+ """+ Applicable to: Equity Research Reports (Risk Sections), Investment Committee Memos,+ Portfolio Risk Assessments, Analyst Downgrade Notes.++ Template for extracting downside risks from equity research. Each risk is captured+ as an independent list item for risk monitoring and portfolio risk assessment.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> risks = RiskFactorList(llm_client=llm, embedder=embedder)+ >>> report = "Key risks include: 1) EU Digital Markets Act compliance costs..."+ >>> risks.feed_text(report)+ >>> risks.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 Risk Factor List template.++ Args:+ llm_client (BaseChatModel): The LLM for risk 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=RiskItem,+ 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 risk factor 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: RiskItem) -> str:+ return f"[{item.risk_category}] {item.risk_name}"++ 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/valuation_logic_map.py b/hyperextract/templates/en/finance/valuation_logic_map.pynew file mode 100644index 0000000..62e1e1e--- /dev/null+++ b/hyperextract/templates/en/finance/valuation_logic_map.py@@ -0,0 +1,194 @@+"""Valuation Logic Map - Maps causal chains driving stock performance.++Extracts the logical chain from business drivers to valuation conclusions as+presented in equity research reports (e.g., New Market -> Growth -> Multiple Expansion).+"""++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 ValuationDriver(BaseModel):+ """+ A factor in the analyst's valuation logic chain.+ """++ name: str = Field(+ description="Name of the valuation driver (e.g., 'Market Share Gains', 'Multiple Expansion', 'DCF Assumption')."+ )+ driver_type: str = Field(+ description="Type: 'Fundamental', 'Valuation Metric', 'Growth Driver', 'Comparable', 'Discount Rate', 'Terminal Value'."+ )+ value: Optional[str] = Field(+ None,+ description="Quantified value or metric (e.g., '25x forward P/E', 'WACC 9.5%', '$15B TAM').",+ )+ description: Optional[str] = Field(+ None,+ description="Analyst's explanation of this driver's role in the valuation.",+ )+++class ValuationEdge(BaseModel):+ """+ A causal link in the analyst's valuation logic.+ """++ source: str = Field(description="The cause or input driver name.")+ target: str = Field(description="The effect or output driver name.")+ logic: str = Field(+ description="The analyst's reasoning connecting source to target "+ "(e.g., 'higher cloud adoption drives recurring revenue growth')."+ )+ direction: str = Field(+ description="Impact direction: 'Positive', 'Negative', 'Neutral'."+ )+ confidence: Optional[str] = Field(+ None,+ description="Analyst's conviction level: 'High', 'Medium', 'Low'.",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are an equity research analyst. Extract the valuation logic chain from this research report: "+ "the causal reasoning from business fundamentals through to valuation conclusions.\n\n"+ "Rules:\n"+ "- Identify fundamental drivers, growth catalysts, and valuation metrics.\n"+ "- Extract the causal chain from business drivers to target price.\n"+ "- Capture the analyst's specific reasoning at each link.\n"+ "- Note impact direction and conviction level."+)++_NODE_PROMPT = (+ "You are an equity research analyst. Extract all valuation drivers and metrics (Nodes).\n\n"+ "Extraction Rules:\n"+ "- Identify fundamental drivers (revenue growth, market share, TAM).\n"+ "- Identify valuation metrics (P/E, EV/EBITDA, DCF, comparable multiples).\n"+ "- Capture quantified values when stated.\n"+ "- DO NOT establish causal links at this stage."+)++_EDGE_PROMPT = (+ "You are an equity research analyst. Given the valuation drivers, extract the logical "+ "reasoning chain (Edges) that connects them.\n\n"+ "Extraction Rules:\n"+ "- Connect business drivers to financial outcomes to valuation conclusions.\n"+ "- Capture the specific reasoning at each link.\n"+ "- Note whether each link is positive, negative, or neutral.\n"+ "- Only create edges between nodes that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class ValuationLogicMap(AutoGraph[ValuationDriver, ValuationEdge]):+ """+ Applicable to: Equity Research Reports, Initiation Reports, Valuation Analysis,+ Sum-of-Parts Analyses, DCF Model Summaries.++ Template for mapping the causal chains in an analyst's valuation logic. Connects+ business fundamentals to growth drivers to valuation metrics to target price,+ enabling investment strategy mapping and thesis comparison.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> valuation = ValuationLogicMap(llm_client=llm, embedder=embedder)+ >>> report = "Cloud adoption drives recurring revenue, justifying a 30x forward P/E..."+ >>> valuation.feed_text(report)+ >>> valuation.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ Initialize the Valuation Logic Map template.++ Args:+ llm_client (BaseChatModel): The LLM for valuation logic 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=ValuationDriver,+ edge_schema=ValuationEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}--({x.direction})-->{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 valuation logic map using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of drivers to retrieve. Default 3.+ top_k_edges_for_search (int): Number of logic links to retrieve. Default 3.+ top_k_nodes_for_chat (int): Drivers for chat context. Default 3.+ top_k_edges_for_chat (int): Logic links for chat context. Default 3.+ """++ def node_label_extractor(node: ValuationDriver) -> str:+ val = f": {node.value}" if node.value else ""+ return f"{node.name}{val}"++ def edge_label_extractor(edge: ValuationEdge) -> str:+ return f"[{edge.direction}] {edge.logic[:60]}"++ 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/factor_influence_hypergraph.py b/hyperextract/templates/zh/finance/factor_influence_hypergraph.pynew file mode 100644index 0000000..34a684e--- /dev/null+++ b/hyperextract/templates/zh/finance/factor_influence_hypergraph.py@@ -0,0 +1,197 @@+"""因子影响超图 - 建模股票分析中的多因子关系。++将宏观因素、行业趋势和公司指标之间的复杂关系建模为+同时连接多个因子的超边。+"""++from typing import Optional, List, 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 AutoHypergraph++# ==============================================================================+# 1. Schema 定义+# ==============================================================================+++class InvestmentFactor(BaseModel):+ """+ 多因子投资分析中的一个因子。+ """++ name: str = Field(+ description="因子名称(例如 'GDP 增长'、'半导体周期'、'云计算收入')。"+ )+ factor_level: str = Field(+ description="层级:'宏观'、'行业'、'公司'、'技术面'。"+ )+ current_reading: Optional[str] = Field(+ None,+ description="当前值或状态(例如 '同比 3.2%'、'上升周期'、'加速增长')。",+ )+ description: Optional[str] = Field(+ None, description="该因子重要性的说明。"+ )+++class FactorInteraction(BaseModel):+ """+ 多因子交互关系,多个因子共同影响一个结果。+ """++ interaction_name: str = Field(+ description="交互关系的描述性名称(例如 'AI 资本支出乘数效应'、'利率敏感型轮动')。"+ )+ participating_factors: List[str] = Field(+ description="参与此交互关系的所有因子名称。"+ )+ interaction_type: str = Field(+ description="类型:'增强型'、'抵消型'、'条件型'、'级联型'、'阈值型'。"+ )+ outcome: str = Field(+ description="综合结果或效应(例如 '云计算公司收入增长加速')。"+ )+ mechanism: Optional[str] = Field(+ None,+ description="各因子如何相互作用产生该结果的机制。",+ )+ confidence: Optional[str] = Field(+ None,+ description="分析师对此交互关系的确信度:'高'、'中等'、'低'。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是一名量化基本面研究分析师。从本研究报告中提取投资因子及其多因子交互关系。\n\n"+ "规则:\n"+ "- 识别宏观、行业和公司层面的因子。\n"+ "- 提取多个因子共同产生结果的复杂交互关系。\n"+ "- 超边连接所有参与因子,而非仅成对连接。\n"+ "- 捕获每个交互关系的机制和结果。"+)++_NODE_PROMPT = (+ "你是一名量化基本面研究分析师。提取所有投资因子(节点)。\n\n"+ "提取规则:\n"+ "- 识别宏观指标、行业指标和公司关键绩效指标。\n"+ "- 捕获当前值或读数。\n"+ "- 按层级对每个因子进行分类。\n"+ "- 此阶段不提取交互关系。"+)++_EDGE_PROMPT = (+ "你是一名量化基本面研究分析师。在获得因子列表的基础上,提取多个因子共同影响结果的"+ "多因子交互关系(超边)。\n\n"+ "提取规则:\n"+ "- 每条超边应连接 2 个或更多因子。\n"+ "- 描述交互机制和结果。\n"+ "- 对交互类型进行分类。\n"+ "- 仅引用提供列表中存在的因子。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class FactorInfluenceHypergraph(AutoHypergraph[InvestmentFactor, FactorInteraction]):+ """+ 适用文档: 多因子研究报告、量化基本面分析、宏观策略笔记、跨资产研究、因子归因研究。++ 模板用于建模股票分析中的复杂多因子关系。使用超边捕获多个因子共同影响结果的+ 交互关系,超越简单的成对关系。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> factors = FactorInfluenceHypergraph(llm_client=llm, embedder=embedder)+ >>> report = "利率上升叠加强劲 GDP 和 AI 资本支出,推动向优质成长股轮动..."+ >>> factors.feed_text(report)+ >>> factors.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,+ ):+ """+ 初始化因子影响超图模板。++ Args:+ llm_client (BaseChatModel): 用于因子提取的 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: AutoHypergraph 的其他参数。+ """+ super().__init__(+ node_schema=InvestmentFactor,+ edge_schema=FactorInteraction,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: x.interaction_name.strip().lower(),+ nodes_in_edge_extractor=lambda x: tuple(+ f.strip().lower() for f in x.participating_factors+ ),+ llm_client=llm_client,+ embedder=embedder,+ 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 可视化因子影响超图。++ Args:+ top_k_nodes_for_search (int): 检索的因子数。默认 3。+ top_k_edges_for_search (int): 检索的交互关系数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的因子数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的交互关系数。默认 3。+ """++ def node_label_extractor(node: InvestmentFactor) -> str:+ reading = f": {node.current_reading}" if node.current_reading else ""+ return f"{node.name} [{node.factor_level}]{reading}"++ def edge_label_extractor(edge: FactorInteraction) -> str:+ return f"[{edge.interaction_type}] {edge.interaction_name}"++ 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/financial_forecast.py b/hyperextract/templates/zh/finance/financial_forecast.pynew file mode 100644index 0000000..3ff4cce--- /dev/null+++ b/hyperextract/templates/zh/finance/financial_forecast.py@@ -0,0 +1,144 @@+"""财务预测 - 从股票研究报告中提取预测财务数据。++提取分析师报告中的收入、每股收益、市盈率等未来期间的财务预测,+用于一致性预期分析和财务建模。+"""++from typing import Optional, List, 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 ForecastItem(BaseModel):+ """+ 特定指标和期间的单项财务预测。+ """++ metric: str = Field(+ description="被预测的财务指标(例如 '收入'、'每股收益'、'EBITDA'、'营业利润率'、'自由现金流')。"+ )+ period: str = Field(+ description="预测期间(例如 'FY2025E'、'Q1 2025E'、'CY2026E')。"+ )+ estimate: str = Field(+ description="预测值(例如 '$120.5B'、'$6.25'、'35.2%')。"+ )+ prior_estimate: Optional[str] = Field(+ None, description="如有修订,之前的预测值(例如 '$115.0B')。"+ )+ consensus: Optional[str] = Field(+ None, description="用于对比的市场一致性预期(例如 '$118.2B')。"+ )+ growth_rate: Optional[str] = Field(+ None,+ description="隐含增长率(例如 '同比+15%'、'持平')。",+ )+ assumptions: Optional[str] = Field(+ None,+ description="预测所依据的关键假设(例如 '假设销量增加 500 万台')。",+ )+ source_firm: Optional[str] = Field(+ None, description="提供该预测的研究机构。"+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是一名构建盈利模型的金融分析师。从本股票研究报告中提取所有财务预测和估算。\n\n"+ "规则:\n"+ "- 提取每个预测指标及其对应的具体时间段。\n"+ "- 在注明修订时,同时捕获当前和之前的预测值。\n"+ "- 在进行对比时提取一致性预期。\n"+ "- 捕获增长率和关键假设。\n"+ "- 将每项预测作为独立条目单独提取。\n\n"+ "### 源文本:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class FinancialForecast(AutoList[ForecastItem]):+ """+ 适用文档: 股票研究报告、盈利预测、财务模型、一致性预期报告、分析师预测。++ 模板用于从分析师报告中提取预测财务数据。每项预测作为独立列表项捕获,+ 支持一致性预期分析、预测修订跟踪和财务模型构建。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> forecast = FinancialForecast(llm_client=llm, embedder=embedder)+ >>> report = "我们将 FY2025 收入预测上调至 1205 亿美元(此前为 1150 亿美元)..."+ >>> forecast.feed_text(report)+ >>> forecast.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,+ ):+ """+ 初始化财务预测模板。++ Args:+ llm_client (BaseChatModel): 用于预测提取的 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=ForecastItem,+ 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:+ """+ 可视化财务预测列表。++ 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: ForecastItem) -> str:+ return f"{item.metric} ({item.period}): {item.estimate}"++ 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/research_note_summary.py b/hyperextract/templates/zh/finance/research_note_summary.pynew file mode 100644index 0000000..f36f78c--- /dev/null+++ b/hyperextract/templates/zh/finance/research_note_summary.py@@ -0,0 +1,146 @@+"""研究报告摘要 - 从股票研究报告中提取核心投资论点。++提取分析师研究报告中的评级、目标价和顶层投资逻辑,+用于报告数据库填充和筛选。+"""++from typing import Optional, List, Any+from pydantic import BaseModel, Field+from langchain_core.language_models.chat_models import BaseChatModel+from langchain_core.embeddings import Embeddings+from ontomem.merger import MergeStrategy+from hyperextract.types import AutoModel++# ==============================================================================+# 1. Schema 定义+# ==============================================================================+++class ResearchNoteSummarySchema(BaseModel):+ """+ 股票研究报告的结构化摘要。+ """++ company_name: Optional[str] = Field(+ None, description="被覆盖公司的名称。"+ )+ ticker: Optional[str] = Field(+ None, description="股票代码(例如 'AAPL'、'NVDA')。"+ )+ analyst_name: Optional[str] = Field(+ None, description="首席分析师的姓名。"+ )+ research_firm: Optional[str] = Field(+ None, description="研究机构名称(例如 '高盛'、'摩根士丹利')。"+ )+ report_date: Optional[str] = Field(+ None, description="报告发布日期。"+ )+ rating: Optional[str] = Field(+ None,+ description="分析师评级:'买入'、'增持'、'持有'、'中性'、'卖出'、'减持'。",+ )+ prior_rating: Optional[str] = Field(+ None, description="如有变更,之前的评级。"+ )+ target_price: Optional[str] = Field(+ None, description="当前目标价(例如 '$150.00')。"+ )+ prior_target_price: Optional[str] = Field(+ None, description="如有变更,之前的目标价。"+ )+ current_price: Optional[str] = Field(+ None, description="报告发布时的股价。"+ )+ investment_thesis: Optional[str] = Field(+ None,+ description="核心投资论点或评级的关键论据。",+ )+ key_catalysts: Optional[List[str]] = Field(+ None,+ description="已识别的近期催化剂(例如 ['Q4 业绩超预期', '新产品发布', '监管审批'])。",+ )+ key_risks: Optional[List[str]] = Field(+ None,+ description="分析师强调的主要风险。",+ )+ revenue_estimate: Optional[str] = Field(+ None, description="分析师对当前/下一财年的收入预测。"+ )+ eps_estimate: Optional[str] = Field(+ None, description="分析师对当前/下一财年的每股收益预测。"+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是一名股票研究分析师。从本研究报告中提取核心投资论点、评级、目标价和关键论据。\n\n"+ "规则:\n"+ "- 提取分析师的评级及任何评级变更。\n"+ "- 捕获目标价以及变更前的目标价(如有变更)。\n"+ "- 简洁地总结核心投资论点。\n"+ "- 列出分析师识别的关键催化剂和风险。\n"+ "- 在提及时提取财务预测(收入、每股收益)。\n\n"+ "### 源文本:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class ResearchNoteSummary(AutoModel[ResearchNoteSummarySchema]):+ """+ 适用文档: 股票研究报告、分析师笔记、评级变更、首次覆盖报告、行业研究。++ 模板用于从股票研究报告中提取核心投资论点和关键参数。每份报告生成一个结构化摘要,+ 用于数据库填充和筛选。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> summary = ResearchNoteSummary(llm_client=llm, embedder=embedder)+ >>> report = "我们将 AAPL 评级上调为买入,目标价 200 美元..."+ >>> summary.feed_text(report)+ >>> print(summary.data)+ """++ 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,+ ):+ """+ 初始化研究报告摘要模板。++ Args:+ llm_client (BaseChatModel): 用于报告提取的 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: AutoModel 的其他参数。+ """+ super().__init__(+ data_schema=ResearchNoteSummarySchema,+ llm_client=llm_client,+ embedder=embedder,+ strategy_or_merger=MergeStrategy.LLM.BALANCED,+ prompt=_PROMPT,+ chunk_size=chunk_size,+ chunk_overlap=chunk_overlap,+ max_workers=max_workers,+ verbose=verbose,+ **kwargs,+ )diff --git a/hyperextract/templates/zh/finance/risk_factor_list.py b/hyperextract/templates/zh/finance/risk_factor_list.pynew file mode 100644index 0000000..4c4992b--- /dev/null+++ b/hyperextract/templates/zh/finance/risk_factor_list.py@@ -0,0 +1,140 @@+"""风险因素列表 - 从股票研究报告中提取下行风险。++列出分析师识别的具体下行风险,包括监管、汇率、供应链等+风险类别,用于风险监控。+"""++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 RiskItem(BaseModel):+ """+ 股票研究中识别的一项具体下行风险。+ """++ risk_name: str = Field(+ description="风险的简洁名称(例如 '欧盟监管收紧'、'强势美元带来的汇率逆风')。"+ )+ risk_category: str = Field(+ description="类别:'监管'、'竞争'、'宏观经济'、'运营'、'汇率/货币'、"+ "'地缘政治'、'技术'、'法律/诉讼'、'ESG'、'执行'。"+ )+ description: str = Field(+ description="风险情景的详细描述。"+ )+ potential_impact: Optional[str] = Field(+ None,+ description="估计的财务影响(例如 '收入下行 3-5%'、'每股收益风险 $0.50')。",+ )+ probability: Optional[str] = Field(+ None,+ description="分析师的概率评估:'高'、'中等'、'低'。",+ )+ time_horizon: Optional[str] = Field(+ None,+ description="风险可能兑现的时间(例如 '近期'、'2025 年'、'12-18 个月')。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是一名审查股票研究报告的风险分析师。提取分析师识别的所有下行风险和风险因素。\n\n"+ "规则:\n"+ "- 提取提及的每一个不同的风险因素。\n"+ "- 对每项风险进行适当分类。\n"+ "- 在提供量化影响估算时予以捕获。\n"+ "- 记录概率评估和时间范围。\n"+ "- 将每项风险作为独立条目单独提取。\n\n"+ "### 源文本:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class RiskFactorList(AutoList[RiskItem]):+ """+ 适用文档: 股票研究报告(风险章节)、投资委员会备忘录、投资组合风险评估、分析师降级笔记。++ 模板用于从股票研究中提取下行风险。每项风险作为独立列表项捕获,+ 用于风险监控和投资组合风险评估。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> risks = RiskFactorList(llm_client=llm, embedder=embedder)+ >>> report = "主要风险包括:1) 欧盟数字市场法合规成本..."+ >>> risks.feed_text(report)+ >>> risks.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,+ ):+ """+ 初始化风险因素列表模板。++ Args:+ llm_client (BaseChatModel): 用于风险提取的 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=RiskItem,+ 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:+ """+ 可视化风险因素列表。++ 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: RiskItem) -> str:+ return f"[{item.risk_category}] {item.risk_name}"++ 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/valuation_logic_map.py b/hyperextract/templates/zh/finance/valuation_logic_map.pynew file mode 100644index 0000000..5318144--- /dev/null+++ b/hyperextract/templates/zh/finance/valuation_logic_map.py@@ -0,0 +1,190 @@+"""估值逻辑图谱 - 映射驱动股票表现的因果链。++提取股票研究报告中从业务驱动因素到估值结论的逻辑链+(例如 新市场 -> 增长 -> 估值倍数扩张)。+"""++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 ValuationDriver(BaseModel):+ """+ 分析师估值逻辑链中的一个因素。+ """++ name: str = Field(+ description="估值驱动因素名称(例如 '市场份额增长'、'估值倍数扩张'、'DCF 假设')。"+ )+ driver_type: str = Field(+ description="类型:'基本面'、'估值指标'、'增长驱动因素'、'可比公司'、'折现率'、'终值'。"+ )+ value: Optional[str] = Field(+ None,+ description="量化值或指标(例如 '25 倍前瞻市盈率'、'WACC 9.5%'、'TAM 150 亿美元')。",+ )+ description: Optional[str] = Field(+ None,+ description="分析师对该驱动因素在估值中所起作用的解释。",+ )+++class ValuationEdge(BaseModel):+ """+ 分析师估值逻辑中的因果链接。+ """++ source: str = Field(description="原因或输入驱动因素名称。")+ target: str = Field(description="结果或输出驱动因素名称。")+ logic: str = Field(+ description="分析师连接源到目标的推理逻辑"+ "(例如 '更高的云计算采用率推动经常性收入增长')。"+ )+ direction: str = Field(+ description="影响方向:'正面'、'负面'、'中性'。"+ )+ confidence: Optional[str] = Field(+ None,+ description="分析师的确信度:'高'、'中等'、'低'。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是一名股票研究分析师。从本研究报告中提取估值逻辑链:即从业务基本面到估值结论的因果推理。\n\n"+ "规则:\n"+ "- 识别基本面驱动因素、增长催化剂和估值指标。\n"+ "- 提取从业务驱动因素到目标价的因果链。\n"+ "- 捕获分析师在每个链接处的具体推理。\n"+ "- 记录影响方向和确信度。"+)++_NODE_PROMPT = (+ "你是一名股票研究分析师。提取所有估值驱动因素和指标(节点)。\n\n"+ "提取规则:\n"+ "- 识别基本面驱动因素(收入增长、市场份额、TAM)。\n"+ "- 识别估值指标(P/E、EV/EBITDA、DCF、可比倍数)。\n"+ "- 在提及时捕获量化值。\n"+ "- 此阶段不建立因果链接。"+)++_EDGE_PROMPT = (+ "你是一名股票研究分析师。在获得估值驱动因素的基础上,提取连接它们的逻辑推理链(边)。\n\n"+ "提取规则:\n"+ "- 将业务驱动因素连接到财务结果再到估值结论。\n"+ "- 捕获每个链接处的具体推理。\n"+ "- 记录每个链接是正面、负面还是中性影响。\n"+ "- 仅在提供的列表中存在的节点之间创建边。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class ValuationLogicMap(AutoGraph[ValuationDriver, ValuationEdge]):+ """+ 适用文档: 股票研究报告、首次覆盖报告、估值分析、分部加总分析、DCF 模型摘要。++ 模板用于映射分析师估值逻辑中的因果链。将业务基本面连接到增长驱动因素,+ 再到估值指标和目标价,支持投资策略映射和论点比较。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> valuation = ValuationLogicMap(llm_client=llm, embedder=embedder)+ >>> report = "云计算采用推动经常性收入,支撑 30 倍前瞻市盈率..."+ >>> valuation.feed_text(report)+ >>> valuation.show()+ """++ def __init__(+ self,+ llm_client: BaseChatModel,+ embedder: Embeddings,+ *,+ extraction_mode: str = "one_stage",+ chunk_size: int = 2048,+ chunk_overlap: int = 256,+ max_workers: int = 10,+ verbose: bool = False,+ **kwargs: Any,+ ):+ """+ 初始化估值逻辑图谱模板。++ Args:+ llm_client (BaseChatModel): 用于估值逻辑提取的 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=ValuationDriver,+ edge_schema=ValuationEdge,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}--({x.direction})-->{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 可视化估值逻辑图谱。++ Args:+ top_k_nodes_for_search (int): 检索的驱动因素数。默认 3。+ top_k_edges_for_search (int): 检索的逻辑链接数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的驱动因素数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的逻辑链接数。默认 3。+ """++ def node_label_extractor(node: ValuationDriver) -> str:+ val = f": {node.value}" if node.value else ""+ return f"{node.name}{val}"++ def edge_label_extractor(edge: ValuationEdge) -> str:+ return f"[{edge.direction}] {edge.logic[:60]}"++ 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,+ )