Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: add Earnings Call Transcripts templates - EarningsCallSummary (AutoModel) - call overview - ManagementGuidanceList (AutoList) - forward guidance - AnalystQAGraph (AutoGraph) - Q&A interactions - CallSentimentHypergraph (AutoHypergraph) - topic-sentiment
yuxizheb718b3d019e2
diff --git a/hyperextract/templates/en/finance/analyst_qa_graph.py b/hyperextract/templates/en/finance/analyst_qa_graph.pynew file mode 100644index 0000000..13fa20b--- /dev/null+++ b/hyperextract/templates/en/finance/analyst_qa_graph.py@@ -0,0 +1,200 @@+"""Analyst Q&A Graph - Maps analyst questions to management responses.++Extracts the question-and-answer interactions from earnings call Q&A sessions,+capturing concerns raised and commitments made for analyst focus 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 QAParticipant(BaseModel):+ """+ A participant in the earnings call Q&A session.+ """++ name: str = Field(+ description="Name of the participant (e.g., analyst name, CEO, CFO)."+ )+ role: str = Field(+ description="Role: 'Analyst', 'CEO', 'CFO', 'COO', 'CTO', 'IR Head', 'Other Management'."+ )+ firm: Optional[str] = Field(+ None,+ description="Firm affiliation (e.g., 'JPMorgan', 'Goldman Sachs') for analysts.",+ )+++class QAInteraction(BaseModel):+ """+ A question-answer interaction between analyst and management.+ """++ source: str = Field(description="The questioner's name (analyst).")+ target: str = Field(description="The responder's name (management).")+ topic: str = Field(+ description="Topic of the question (e.g., 'Margin outlook', 'AI strategy', 'Capital allocation')."+ )+ question_summary: str = Field(+ description="Concise summary of the analyst's question."+ )+ answer_summary: str = Field(+ description="Concise summary of management's response."+ )+ sentiment: Optional[str] = Field(+ None,+ description="Tone of the exchange: 'Constructive', 'Pressing', 'Reassuring', 'Evasive', 'Direct'.",+ )+ commitment_made: Optional[str] = Field(+ None,+ description="Any specific commitment from management (e.g., 'will provide update next quarter').",+ )+ follow_up: Optional[bool] = Field(+ None,+ description="Whether the analyst asked a follow-up question on the same topic.",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are an earnings call analyst. Extract the Q&A interactions between analysts and management "+ "from this earnings call transcript.\n\n"+ "Rules:\n"+ "- Identify each analyst and management participant.\n"+ "- Summarize each question and its corresponding answer.\n"+ "- Capture the topic and sentiment of each exchange.\n"+ "- Note any commitments management makes.\n"+ "- Track follow-up questions on the same topic."+)++_NODE_PROMPT = (+ "You are an earnings call analyst. Extract all Q&A participants (Nodes).\n\n"+ "Extraction Rules:\n"+ "- Identify analysts by name and firm.\n"+ "- Identify management participants by name and role.\n"+ "- DO NOT extract Q&A interactions at this stage."+)++_EDGE_PROMPT = (+ "You are an earnings call analyst. Given the participants, extract Q&A interactions (Edges).\n\n"+ "Extraction Rules:\n"+ "- Connect each analyst question to the management response.\n"+ "- Summarize both the question and answer concisely.\n"+ "- Capture the topic, sentiment, and any commitments.\n"+ "- Only create edges between nodes that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class AnalystQAGraph(AutoGraph[QAParticipant, QAInteraction]):+ """+ Applicable to: Earnings Call Transcripts (Q&A section), Investor Day Q&A,+ Annual Meeting Q&A, Analyst Day Transcripts.++ Template for mapping analyst questions to management responses in earnings calls.+ Enables analyst focus analysis, commitment tracking, and identification of+ key concerns across the analyst community.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> qa = AnalystQAGraph(llm_client=llm, embedder=embedder)+ >>> transcript = "Analyst: Can you discuss your margin outlook? CEO: We expect margins to..."+ >>> qa.feed_text(transcript)+ >>> qa.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 Analyst Q&A Graph template.++ Args:+ llm_client (BaseChatModel): The LLM for Q&A 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=QAParticipant,+ edge_schema=QAInteraction,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}|{x.topic.lower()}|{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 analyst Q&A graph using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of participants to retrieve. Default 3.+ top_k_edges_for_search (int): Number of Q&A interactions to retrieve. Default 3.+ top_k_nodes_for_chat (int): Participants for chat context. Default 3.+ top_k_edges_for_chat (int): Interactions for chat context. Default 3.+ """++ def node_label_extractor(node: QAParticipant) -> str:+ firm = f" @ {node.firm}" if node.firm else ""+ return f"{node.name} ({node.role}{firm})"++ def edge_label_extractor(edge: QAInteraction) -> str:+ sentiment = f" [{edge.sentiment}]" if edge.sentiment else ""+ return f"{edge.topic}{sentiment}"++ 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/call_sentiment_hypergraph.py b/hyperextract/templates/en/finance/call_sentiment_hypergraph.pynew file mode 100644index 0000000..3670793--- /dev/null+++ b/hyperextract/templates/en/finance/call_sentiment_hypergraph.py@@ -0,0 +1,198 @@+"""Call Sentiment Hypergraph - Models topic-sentiment analysis across earnings calls.++Models multi-dimensional sentiment: {Topic, Speaker, Sentiment, Driving Factor}+across the call for sentiment-driven trading signals and tone shift detection.+"""++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 CallTopic(BaseModel):+ """+ A topic, speaker, or sentiment driver discussed in an earnings call.+ """++ name: str = Field(+ description="Name of the topic element (e.g., 'Revenue Growth', 'CEO Tim Cook', 'AI Investment Cycle', 'Cautious')."+ )+ element_type: str = Field(+ description="Type: 'Topic', 'Speaker', 'Sentiment', 'Driving Factor'."+ )+ description: Optional[str] = Field(+ None, description="Context or explanation for this element."+ )+++class SentimentCluster(BaseModel):+ """+ A multi-dimensional sentiment cluster connecting topic, speaker, sentiment, and driver.+ """++ cluster_name: str = Field(+ description="Descriptive name (e.g., 'CEO Positive on AI Revenue', 'CFO Cautious on Margins')."+ )+ participating_elements: List[str] = Field(+ description="Names of all elements in this sentiment cluster (topic + speaker + sentiment + driver)."+ )+ sentiment_polarity: str = Field(+ description="Overall sentiment: 'Bullish', 'Bearish', 'Neutral', 'Mixed'."+ )+ intensity: str = Field(+ description="Sentiment intensity: 'Strong', 'Moderate', 'Mild'."+ )+ evidence: Optional[str] = Field(+ None,+ description="Key quote or paraphrase supporting the sentiment assessment.",+ )+ shift_from_prior: Optional[str] = Field(+ None,+ description="Change from prior quarter's tone if notable (e.g., 'More cautious than Q2', 'Upgraded from neutral').",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a sentiment analysis specialist for earnings calls. Extract topics, speakers, "+ "sentiment signals, and their multi-dimensional relationships.\n\n"+ "Rules:\n"+ "- Identify key topics discussed (revenue, margins, guidance, strategy).\n"+ "- Identify speakers and their roles.\n"+ "- Assess sentiment polarity and intensity for each topic-speaker combination.\n"+ "- A hyperedge connects a Topic + Speaker + Sentiment + Driving Factor.\n"+ "- Note shifts from prior quarter's tone."+)++_NODE_PROMPT = (+ "You are a sentiment analysis specialist. Extract all topics, speakers, sentiments, "+ "and driving factors (Nodes) from the earnings call.\n\n"+ "Extraction Rules:\n"+ "- Identify financial topics discussed.\n"+ "- Identify speakers (analysts, management).\n"+ "- Identify sentiment labels and driving factors.\n"+ "- DO NOT create sentiment clusters at this stage."+)++_EDGE_PROMPT = (+ "You are a sentiment analysis specialist. Given the elements, create multi-dimensional "+ "sentiment clusters (Hyperedges).\n\n"+ "Extraction Rules:\n"+ "- Each cluster connects a Topic + Speaker + Sentiment + Driving Factor.\n"+ "- Assess overall polarity and intensity.\n"+ "- Capture supporting evidence.\n"+ "- Note tone shifts from prior quarters.\n"+ "- Only reference elements that exist in the provided lists."+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class CallSentimentHypergraph(AutoHypergraph[CallTopic, SentimentCluster]):+ """+ Applicable to: Earnings Call Transcripts, Investor Day Transcripts,+ Management Presentations, Conference Transcripts.++ Template for multi-dimensional sentiment analysis of earnings calls. Uses+ hyperedges to model {Topic, Speaker, Sentiment, Driving Factor} clusters,+ enabling sentiment-driven trading signals and tone shift detection.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> sentiment = CallSentimentHypergraph(llm_client=llm, embedder=embedder)+ >>> transcript = "CEO: We are very excited about AI revenue growth..."+ >>> sentiment.feed_text(transcript)+ >>> sentiment.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 Call Sentiment Hypergraph template.++ Args:+ llm_client (BaseChatModel): The LLM for sentiment 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=CallTopic,+ edge_schema=SentimentCluster,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: x.cluster_name.strip().lower(),+ nodes_in_edge_extractor=lambda x: tuple(+ e.strip().lower() for e in x.participating_elements+ ),+ 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 call sentiment hypergraph using OntoSight.++ Args:+ top_k_nodes_for_search (int): Number of elements to retrieve. Default 3.+ top_k_edges_for_search (int): Number of sentiment clusters to retrieve. Default 3.+ top_k_nodes_for_chat (int): Elements for chat context. Default 3.+ top_k_edges_for_chat (int): Clusters for chat context. Default 3.+ """++ def node_label_extractor(node: CallTopic) -> str:+ return f"{node.name} [{node.element_type}]"++ def edge_label_extractor(edge: SentimentCluster) -> str:+ return f"[{edge.sentiment_polarity}/{edge.intensity}] {edge.cluster_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/earnings_call_summary.py b/hyperextract/templates/en/finance/earnings_call_summary.pynew file mode 100644index 0000000..e904323--- /dev/null+++ b/hyperextract/templates/en/finance/earnings_call_summary.py@@ -0,0 +1,154 @@+"""Earnings Call Summary - Extracts key metrics and tone from earnings calls.++Extracts reported metrics (Revenue, EPS), management guidance, and overall call+tone from quarterly conference call transcripts for review dashboards.+"""++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 EarningsCallSummarySchema(BaseModel):+ """+ Structured summary of an earnings conference call.+ """++ company_name: Optional[str] = Field(+ None, description="Name of the company."+ )+ ticker: Optional[str] = Field(+ None, description="Stock ticker symbol."+ )+ quarter: Optional[str] = Field(+ None, description="Reporting quarter (e.g., 'Q3 FY2024', 'Q4 2024')."+ )+ call_date: Optional[str] = Field(+ None, description="Date of the earnings call."+ )+ reported_revenue: Optional[str] = Field(+ None, description="Reported revenue for the quarter (e.g., '$94.8 billion')."+ )+ revenue_vs_consensus: Optional[str] = Field(+ None,+ description="Revenue vs. consensus (e.g., 'beat by $1.2B', 'in-line', 'missed by $500M').",+ )+ reported_eps: Optional[str] = Field(+ None, description="Reported diluted EPS (e.g., '$1.46')."+ )+ eps_vs_consensus: Optional[str] = Field(+ None, description="EPS vs. consensus (e.g., 'beat by $0.05')."+ )+ guidance_revenue: Optional[str] = Field(+ None,+ description="Forward revenue guidance (e.g., '$95-97B for Q4', 'FY2025 revenue $380-390B').",+ )+ guidance_eps: Optional[str] = Field(+ None, description="Forward EPS guidance if provided."+ )+ overall_tone: Optional[str] = Field(+ None,+ description="Overall tone of the call: 'Positive', 'Cautiously Optimistic', 'Neutral', 'Cautious', 'Negative'.",+ )+ key_highlights: Optional[List[str]] = Field(+ None,+ description="Top 3-5 highlights from management's prepared remarks.",+ )+ key_concerns: Optional[List[str]] = Field(+ None,+ description="Top concerns raised by management or analysts during Q&A.",+ )+ strategic_priorities: Optional[List[str]] = Field(+ None,+ description="Strategic priorities emphasized by management.",+ )+ ceo_name: Optional[str] = Field(+ None, description="CEO or primary presenter name."+ )+ cfo_name: Optional[str] = Field(+ None, description="CFO name."+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are a buy-side analyst reviewing an earnings call transcript. "+ "Extract the key financial metrics, guidance, and overall tone.\n\n"+ "Rules:\n"+ "- Extract exact reported figures (Revenue, EPS) and compare to consensus.\n"+ "- Capture forward guidance for revenue and earnings.\n"+ "- Assess the overall tone of the call (management's language, analyst reactions).\n"+ "- List key highlights from prepared remarks and concerns from Q&A.\n"+ "- Identify strategic priorities management emphasized.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class EarningsCallSummary(AutoModel[EarningsCallSummarySchema]):+ """+ Applicable to: Quarterly Earnings Call Transcripts, Earnings Press Releases,+ Investor Day Transcripts, Annual Meeting Transcripts.++ Template for extracting a structured summary from earnings call transcripts.+ Produces a single consolidated view of reported metrics, guidance, tone, and+ key themes for quarterly review dashboards and consensus tracking.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> summary = EarningsCallSummary(llm_client=llm, embedder=embedder)+ >>> transcript = "Good afternoon. Q3 revenue was $94.8 billion, beating consensus..."+ >>> summary.feed_text(transcript)+ >>> 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 Earnings Call Summary template.++ Args:+ llm_client (BaseChatModel): The LLM for transcript 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=EarningsCallSummarySchema,+ 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/management_guidance_list.py b/hyperextract/templates/en/finance/management_guidance_list.pynew file mode 100644index 0000000..c451b8b--- /dev/null+++ b/hyperextract/templates/en/finance/management_guidance_list.py@@ -0,0 +1,153 @@+"""Management Guidance List - Extracts forward-looking statements from earnings calls.++Extracts projected figures, strategic priorities, and qualitative outlook from+management's forward guidance for tracking and expectation management.+"""++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 GuidanceItem(BaseModel):+ """+ A single forward-looking guidance statement from management.+ """++ guidance_topic: str = Field(+ description="Topic of the guidance (e.g., 'Q4 Revenue', 'FY2025 CapEx', 'Gross Margin Outlook', 'Hiring Plans')."+ )+ guidance_type: str = Field(+ description="Type: 'Quantitative', 'Qualitative', 'Strategic', 'Operational'."+ )+ guidance_value: str = Field(+ description="The guidance statement or projected value (e.g., '$95-97B', 'expanding into 5 new markets', "+ "'expect margin improvement in H2')."+ )+ prior_guidance: Optional[str] = Field(+ None,+ description="Previous guidance for the same metric if revised (e.g., '$90-93B').",+ )+ direction: Optional[str] = Field(+ None,+ description="Direction vs prior guidance or consensus: 'Raised', 'Lowered', 'Maintained', 'Initiated'.",+ )+ time_period: Optional[str] = Field(+ None,+ description="Period the guidance covers (e.g., 'Q4 2024', 'FY2025', 'Next 12 months').",+ )+ confidence_language: Optional[str] = Field(+ None,+ description="Management's conviction language (e.g., 'we expect', 'we are confident', 'we anticipate').",+ )+ speaker: Optional[str] = Field(+ None,+ description="Who provided the guidance (e.g., 'CEO', 'CFO', 'COO').",+ )+++# ==============================================================================+# 2. Prompts+# ==============================================================================++_PROMPT = (+ "You are an analyst tracking management guidance from earnings calls. "+ "Extract all forward-looking statements and guidance from this transcript.\n\n"+ "Rules:\n"+ "- Extract every distinct guidance item (quantitative figures, strategic plans, outlook statements).\n"+ "- Note if guidance was raised, lowered, or maintained vs. prior.\n"+ "- Capture the time period each guidance covers.\n"+ "- Preserve management's confidence language.\n"+ "- Identify who provided each guidance item.\n"+ "- Extract EVERY guidance statement independently.\n\n"+ "### Source Text:\n"+)++# ==============================================================================+# 3. Template Class+# ==============================================================================+++class ManagementGuidanceList(AutoList[GuidanceItem]):+ """+ Applicable to: Earnings Call Transcripts, Investor Day Presentations,+ Guidance Updates, Management Commentary sections.++ Template for extracting forward-looking guidance from earnings calls and+ management presentations. Each guidance item is captured independently+ for tracking revisions and managing expectations.++ Example Usage:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> guidance = ManagementGuidanceList(llm_client=llm, embedder=embedder)+ >>> transcript = "For Q4, we expect revenue in the range of $95-97 billion..."+ >>> guidance.feed_text(transcript)+ >>> guidance.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 Management Guidance List template.++ Args:+ llm_client (BaseChatModel): The LLM for guidance 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=GuidanceItem,+ 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 management guidance 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: GuidanceItem) -> str:+ direction = f" [{item.direction}]" if item.direction else ""+ return f"{item.guidance_topic}{direction}: {item.guidance_value[:50]}"++ 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/analyst_qa_graph.py b/hyperextract/templates/zh/finance/analyst_qa_graph.pynew file mode 100644index 0000000..9e657a5--- /dev/null+++ b/hyperextract/templates/zh/finance/analyst_qa_graph.py@@ -0,0 +1,192 @@+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 QAParticipant(BaseModel):+ """+ 财报电话会议问答环节的参与者。+ """++ name: str = Field(+ description="参与者姓名(例如分析师姓名、CEO、CFO)。"+ )+ role: str = Field(+ description='角色:"分析师"、"CEO"、"CFO"、"COO"、"CTO"、"IR 负责人"、"其他管理层"。'+ )+ firm: Optional[str] = Field(+ None,+ description="所属机构(例如'摩根大通'、'高盛'),适用于分析师。",+ )+++class QAInteraction(BaseModel):+ """+ 分析师与管理层之间的问答互动。+ """++ source: str = Field(description="提问者姓名(分析师)。")+ target: str = Field(description="回答者姓名(管理层)。")+ topic: str = Field(+ description="问题主题(例如'利润率展望'、'AI 战略'、'资本配置')。"+ )+ question_summary: str = Field(+ description="分析师问题的简要概述。"+ )+ answer_summary: str = Field(+ description="管理层回答的简要概述。"+ )+ sentiment: Optional[str] = Field(+ None,+ description="互动基调:'建设性'、'追问式'、'安抚性'、'回避性'、'直接'。",+ )+ commitment_made: Optional[str] = Field(+ None,+ description="管理层作出的具体承诺(例如'将在下季度提供更新')。",+ )+ follow_up: Optional[bool] = Field(+ None,+ description="分析师是否就同一主题提出了追问。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是财报电话会议分析师。从本财报电话会议记录中提取分析师与管理层之间的问答互动。\n\n"+ "规则:\n"+ "- 识别每位分析师和管理层参与者。\n"+ "- 概述每个问题及其对应的回答。\n"+ "- 捕捉每次互动的主题和基调。\n"+ "- 记录管理层作出的任何承诺。\n"+ "- 跟踪针对同一主题的追问。"+)++_NODE_PROMPT = (+ "你是财报电话会议分析师。提取所有问答参与者(节点)。\n\n"+ "提取规则:\n"+ "- 按姓名和所属机构识别分析师。\n"+ "- 按姓名和职务识别管理层参与者。\n"+ "- 此阶段不提取问答互动。"+)++_EDGE_PROMPT = (+ "你是财报电话会议分析师。在获得参与者清单的基础上,提取问答互动(边)。\n\n"+ "提取规则:\n"+ "- 将每位分析师的问题连接到管理层的回答。\n"+ "- 简要概述问题和回答。\n"+ "- 捕捉主题、基调和任何承诺。\n"+ "- 仅在提供的列表中存在的节点之间创建边。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class AnalystQAGraph(AutoGraph[QAParticipant, QAInteraction]):+ """+ 适用文档: 财报电话会议记录(问答部分)、投资者日问答、+ 年度股东大会问答、分析师日活动记录。++ 模板用于将分析师问题映射到管理层回答。支持分析师关注点分析、+ 承诺跟踪以及识别分析师群体中的核心关切。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> qa = AnalystQAGraph(llm_client=llm, embedder=embedder)+ >>> transcript = "分析师:能否讨论一下利润率展望?CEO:我们预计利润率将..."+ >>> qa.feed_text(transcript)+ >>> qa.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,+ ):+ """+ 初始化分析师问答图谱模板。++ Args:+ llm_client (BaseChatModel): 用于问答提取的 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=QAParticipant,+ edge_schema=QAInteraction,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: (+ f"{x.source.strip().lower()}|{x.topic.lower()}|{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 可视化分析师问答图。++ Args:+ top_k_nodes_for_search (int): 检索的参与者数。默认 3。+ top_k_edges_for_search (int): 检索的问答互动数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的参与者数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的互动数。默认 3。+ """++ def node_label_extractor(node: QAParticipant) -> str:+ firm = f" @ {node.firm}" if node.firm else ""+ return f"{node.name} ({node.role}{firm})"++ def edge_label_extractor(edge: QAInteraction) -> str:+ sentiment = f" [{edge.sentiment}]" if edge.sentiment else ""+ return f"{edge.topic}{sentiment}"++ 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/call_sentiment_hypergraph.py b/hyperextract/templates/zh/finance/call_sentiment_hypergraph.pynew file mode 100644index 0000000..0e31e4a--- /dev/null+++ b/hyperextract/templates/zh/finance/call_sentiment_hypergraph.py@@ -0,0 +1,191 @@+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 CallTopic(BaseModel):+ """+ 财报电话会议中讨论的主题、发言人或情绪驱动因素。+ """++ name: str = Field(+ description="主题元素名称(例如'收入增长'、'CEO 蒂姆·库克'、'AI 投资周期'、'谨慎')。"+ )+ element_type: str = Field(+ description='类型:"主题"、"发言人"、"情绪"、"驱动因素"。'+ )+ description: Optional[str] = Field(+ None, description="该元素的上下文或说明。"+ )+++class SentimentCluster(BaseModel):+ """+ 连接主题、发言人、情绪和驱动因素的多维情绪聚类。+ """++ cluster_name: str = Field(+ description="描述性名称(例如'CEO 看好 AI 收入'、'CFO 对利润率持谨慎态度')。"+ )+ participating_elements: List[str] = Field(+ description="此情绪聚类中所有元素的名称(主题 + 发言人 + 情绪 + 驱动因素)。"+ )+ sentiment_polarity: str = Field(+ description='整体情绪方向:"看多"、"看空"、"中性"、"混合"。'+ )+ intensity: str = Field(+ description='情绪强度:"强"、"中等"、"轻微"。'+ )+ evidence: Optional[str] = Field(+ None,+ description="支持情绪判断的关键引述或意译。",+ )+ shift_from_prior: Optional[str] = Field(+ None,+ description="与前一季度基调的变化(如显著,例如'比第二季度更为谨慎'、'从中性上调')。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是财报电话会议情绪分析专家。提取主题、发言人、"+ "情绪信号及其多维关系。\n\n"+ "规则:\n"+ "- 识别讨论的关键主题(收入、利润率、指引、战略)。\n"+ "- 识别发言人及其角色。\n"+ "- 评估每个主题-发言人组合的情绪方向和强度。\n"+ "- 超边连接 主题 + 发言人 + 情绪 + 驱动因素。\n"+ "- 记录与前一季度基调的变化。"+)++_NODE_PROMPT = (+ "你是情绪分析专家。从财报电话会议中提取所有主题、发言人、情绪和"+ "驱动因素(节点)。\n\n"+ "提取规则:\n"+ "- 识别讨论的财务主题。\n"+ "- 识别发言人(分析师、管理层)。\n"+ "- 识别情绪标签和驱动因素。\n"+ "- 此阶段不创建情绪聚类。"+)++_EDGE_PROMPT = (+ "你是情绪分析专家。在获得元素清单的基础上,创建多维"+ "情绪聚类(超边)。\n\n"+ "提取规则:\n"+ "- 每个聚类连接 主题 + 发言人 + 情绪 + 驱动因素。\n"+ "- 评估整体情绪方向和强度。\n"+ "- 捕捉支撑证据。\n"+ "- 记录与前几个季度的基调变化。\n"+ "- 仅引用提供列表中存在的元素。"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class CallSentimentHypergraph(AutoHypergraph[CallTopic, SentimentCluster]):+ """+ 适用文档: 财报电话会议记录、投资者日活动记录、+ 管理层报告、行业会议记录。++ 模板用于财报电话会议的多维情绪分析。使用超边建模+ {主题, 发言人, 情绪, 驱动因素} 聚类,支持情绪驱动的交易信号和基调变化检测。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> sentiment = CallSentimentHypergraph(llm_client=llm, embedder=embedder)+ >>> transcript = "CEO:我们对 AI 收入增长感到非常兴奋..."+ >>> sentiment.feed_text(transcript)+ >>> sentiment.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,+ ):+ """+ 初始化电话会议情绪超图模板。++ Args:+ llm_client (BaseChatModel): 用于情绪提取的 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=CallTopic,+ edge_schema=SentimentCluster,+ node_key_extractor=lambda x: x.name.strip().lower(),+ edge_key_extractor=lambda x: x.cluster_name.strip().lower(),+ nodes_in_edge_extractor=lambda x: tuple(+ e.strip().lower() for e in x.participating_elements+ ),+ 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 可视化电话会议情绪超图。++ Args:+ top_k_nodes_for_search (int): 检索的元素数。默认 3。+ top_k_edges_for_search (int): 检索的情绪聚类数。默认 3。+ top_k_nodes_for_chat (int): 对话上下文中的元素数。默认 3。+ top_k_edges_for_chat (int): 对话上下文中的聚类数。默认 3。+ """++ def node_label_extractor(node: CallTopic) -> str:+ return f"{node.name} [{node.element_type}]"++ def edge_label_extractor(edge: SentimentCluster) -> str:+ return f"[{edge.sentiment_polarity}/{edge.intensity}] {edge.cluster_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/earnings_call_summary.py b/hyperextract/templates/zh/finance/earnings_call_summary.pynew file mode 100644index 0000000..f3a5fd9--- /dev/null+++ b/hyperextract/templates/zh/finance/earnings_call_summary.py@@ -0,0 +1,147 @@+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 EarningsCallSummarySchema(BaseModel):+ """+ 财报电话会议的结构化摘要。+ """++ company_name: Optional[str] = Field(+ None, description="公司名称。"+ )+ ticker: Optional[str] = Field(+ None, description="股票代码。"+ )+ quarter: Optional[str] = Field(+ None, description="报告季度(例如'Q3 FY2024'、'2024 年第四季度')。"+ )+ call_date: Optional[str] = Field(+ None, description="财报电话会议日期。"+ )+ reported_revenue: Optional[str] = Field(+ None, description="本季度报告收入(例如'948 亿美元')。"+ )+ revenue_vs_consensus: Optional[str] = Field(+ None,+ description="收入与市场一致预期对比(例如'超出 12 亿美元'、'符合预期'、'低于预期 5 亿美元')。",+ )+ reported_eps: Optional[str] = Field(+ None, description="报告的稀释每股收益(例如'1.46 美元')。"+ )+ eps_vs_consensus: Optional[str] = Field(+ None, description="每股收益与一致预期对比(例如'超出 0.05 美元')。"+ )+ guidance_revenue: Optional[str] = Field(+ None,+ description="前瞻性收入指引(例如'第四季度 950-970 亿美元'、'2025 财年收入 3800-3900 亿美元')。",+ )+ guidance_eps: Optional[str] = Field(+ None, description="前瞻性每股收益指引(如有提供)。"+ )+ overall_tone: Optional[str] = Field(+ None,+ description="电话会议整体基调:'积极'、'审慎乐观'、'中性'、'谨慎'、'消极'。",+ )+ key_highlights: Optional[List[str]] = Field(+ None,+ description="管理层准备发言中的 3-5 项核心亮点。",+ )+ key_concerns: Optional[List[str]] = Field(+ None,+ description="管理层或分析师在问答环节提出的主要关切。",+ )+ strategic_priorities: Optional[List[str]] = Field(+ None,+ description="管理层强调的战略重点。",+ )+ ceo_name: Optional[str] = Field(+ None, description="CEO 或主要发言人姓名。"+ )+ cfo_name: Optional[str] = Field(+ None, description="CFO 姓名。"+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是买方分析师,正在审阅财报电话会议记录。"+ "提取关键财务指标、业绩指引和整体基调。\n\n"+ "规则:\n"+ "- 提取确切的报告数据(收入、每股收益)并与一致预期进行对比。\n"+ "- 捕捉收入和盈利的前瞻性指引。\n"+ "- 评估电话会议的整体基调(管理层措辞、分析师反应)。\n"+ "- 列出准备发言中的核心亮点和问答环节中的主要关切。\n"+ "- 识别管理层强调的战略重点。\n\n"+ "### 原文:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class EarningsCallSummary(AutoModel[EarningsCallSummarySchema]):+ """+ 适用文档: 季度财报电话会议记录、业绩新闻稿、+ 投资者日活动记录、年度股东大会记录。++ 模板用于从财报电话会议记录中提取结构化摘要。生成已报告指标、业绩指引、+ 基调和核心主题的统一视图,便于季度复盘仪表板和一致预期跟踪。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> summary = EarningsCallSummary(llm_client=llm, embedder=embedder)+ >>> transcript = "下午好。第三季度收入为 948 亿美元,超出一致预期..."+ >>> summary.feed_text(transcript)+ >>> 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,+ ):+ """+ 初始化财报电话会议摘要模板。++ Args:+ llm_client (BaseChatModel): 用于会议记录提取的 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=EarningsCallSummarySchema,+ 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/management_guidance_list.py b/hyperextract/templates/zh/finance/management_guidance_list.pynew file mode 100644index 0000000..b8515f7--- /dev/null+++ b/hyperextract/templates/zh/finance/management_guidance_list.py@@ -0,0 +1,146 @@+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 GuidanceItem(BaseModel):+ """+ 管理层的单项前瞻性指引声明。+ """++ guidance_topic: str = Field(+ description="指引主题(例如'第四季度收入'、'2025 财年资本支出'、'毛利率展望'、'招聘计划')。"+ )+ guidance_type: str = Field(+ description='类型:"定量"、"定性"、"战略"、"运营"。'+ )+ guidance_value: str = Field(+ description="指引内容或预测值(例如'950-970 亿美元'、'将拓展 5 个新市场'、"+ "'预计下半年利润率改善')。"+ )+ prior_guidance: Optional[str] = Field(+ None,+ description="同一指标的前次指引(如有修订,例如'900-930 亿美元')。",+ )+ direction: Optional[str] = Field(+ None,+ description="相对前次指引或一致预期的方向:'上调'、'下调'、'维持'、'首次发布'。",+ )+ time_period: Optional[str] = Field(+ None,+ description="指引覆盖的时间段(例如'2024 年第四季度'、'2025 财年'、'未来 12 个月')。",+ )+ confidence_language: Optional[str] = Field(+ None,+ description="管理层的确信程度措辞(例如'我们预计'、'我们有信心'、'我们预期')。",+ )+ speaker: Optional[str] = Field(+ None,+ description="指引发布者(例如'CEO'、'CFO'、'COO')。",+ )+++# ==============================================================================+# 2. 提示词 (Prompts)+# ==============================================================================++_PROMPT = (+ "你是跟踪财报电话会议管理层指引的分析师。"+ "从本会议记录中提取所有前瞻性声明和业绩指引。\n\n"+ "规则:\n"+ "- 提取每一项指引条目(定量数据、战略规划、展望声明)。\n"+ "- 注明指引相较前次是上调、下调还是维持不变。\n"+ "- 捕捉每项指引覆盖的时间段。\n"+ "- 保留管理层的确信程度措辞。\n"+ "- 识别每项指引的发布者。\n"+ "- 将每项指引声明作为独立条目提取。\n\n"+ "### 原文:\n"+)++# ==============================================================================+# 3. 模板类+# ==============================================================================+++class ManagementGuidanceList(AutoList[GuidanceItem]):+ """+ 适用文档: 财报电话会议记录、投资者日演示材料、+ 业绩指引更新、管理层评论部分。++ 模板用于从财报电话会议和管理层报告中提取前瞻性指引。每项指引条目+ 独立捕捉,便于跟踪修订和管理预期。++ 使用示例:+ >>> from langchain_openai import ChatOpenAI, OpenAIEmbeddings+ >>> llm = ChatOpenAI(model="gpt-4o")+ >>> embedder = OpenAIEmbeddings()+ >>> guidance = ManagementGuidanceList(llm_client=llm, embedder=embedder)+ >>> transcript = "对于第四季度,我们预计收入在 950 至 970 亿美元之间..."+ >>> guidance.feed_text(transcript)+ >>> guidance.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,+ ):+ """+ 初始化管理层指引列表模板。++ Args:+ llm_client (BaseChatModel): 用于指引提取的 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=GuidanceItem,+ 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:+ """+ 可视化管理层指引列表。++ 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: GuidanceItem) -> str:+ direction = f" [{item.direction}]" if item.direction else ""+ return f"{item.guidance_topic}{direction}: {item.guidance_value[:50]}"++ super().show(+ item_label_extractor=label_extractor,+ top_k_for_search=top_k_for_search,+ top_k_for_chat=top_k_for_chat,+ )