Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
refactor default_prompt
yifanfeng974040a9ad9b36
diff --git a/hyperextract/core/base.py b/hyperextract/core/base.pyindex 6672854..0fb7306 100644--- a/hyperextract/core/base.py+++ b/hyperextract/core/base.py@@ -109,16 +109,13 @@ class BaseAutoType(ABC, Generic[T]):show_progress=self.show_progress,)- @staticmethod- def _default_prompt() -> str:- """Returns the default extraction prompt template."""- return (- "You are an expert knowledge extraction assistant. "- "Your task is to carefully analyze the following text and extract structured information "- "according to the specified schema. Be precise, comprehensive, and faithful to the source text. "- "Extract all relevant details without adding information not present in the text.\n\n"- "### Source Text:\n"- )+ @abstractmethod+ def _default_prompt(self) -> str:+ """Returns the default extraction prompt template.++ Subclasses must implement this to provide a prompt tailored to their extraction pattern.+ """+ pass# ==================== Data Management ====================diff --git a/hyperextract/core/list.py b/hyperextract/core/list.pyindex 3bd3a37..f3da7d4 100644--- a/hyperextract/core/list.py+++ b/hyperextract/core/list.py@@ -106,8 +106,7 @@ class AutoList(BaseAutoType[AutoListSchema[Item]], Generic[Item]):**kwargs,)- @staticmethod- def _default_prompt() -> str:+ def _default_prompt(self) -> str:"""Returns the default extraction prompt for list-based extraction."""return ("You are an expert knowledge extraction assistant. "diff --git a/hyperextract/core/model.py b/hyperextract/core/model.pyindex b7654d7..a2565da 100644--- a/hyperextract/core/model.py+++ b/hyperextract/core/model.py@@ -69,8 +69,7 @@ class AutoModel(BaseAutoType[T]):**kwargs,)- @staticmethod- def _default_prompt() -> str:+ def _default_prompt(self) -> str:"""Returns the default extraction prompt for single-object extraction."""return ("You are an expert knowledge extraction assistant. "@@ -80,72 +79,6 @@ class AutoModel(BaseAutoType[T]):"### Source Text:\n")- # ==================== Extraction & Aggregation ====================-- def extract(self, text: str, *, store: bool = True) -> T:- """Extracts knowledge using LangChain native batch processing.-- Automatically handles text chunking for long documents and aggregates results- using the field-level merge strategy.-- Args:- text: Input text to extract knowledge from.- store: Controls whether to store extracted knowledge internally.- - True (default): Store mode - merge with existing knowledge and update internal state- - False: Temporary mode - return extracted data without modifying internal state-- Returns:- The extracted knowledge object.- """- start_time = datetime.now()-- # Determine if chunking is needed based on text length- if len(text) <= self.chunk_size:- # Short text: direct extraction without chunking- if self.show_progress:- logger.info(f"Processing single text (length: {len(text)})...")-- extracted_data = self.llm_chain_extract.invoke({"chunk_text": text})- extracted_data_list = [extracted_data]-- else:- # Long text: extract by chunking- chunks = self.text_splitter.split_text(text)- logger.info(f"Split text into {len(chunks)} chunks")-- if self.show_progress:- logger.info(f"Processing {len(chunks)} chunk(s)...")-- inputs = [{"chunk_text": chunk} for chunk in chunks]- extracted_data_list = self.llm_chain_extract.batch(- inputs, config={"max_concurrency": self.max_workers}- )-- if self.show_progress:- logger.info(f"Extracted {len(extracted_data_list)} chunks")-- logger.info("Merging extracted knowledge...")- merged_data = self.merge(extracted_data_list)-- # If store=True, merge with existing data and update internal state- if store:- if self._data and any(- v is not None for v in self._data.model_dump().values()- ):- self._data = self.merge([self._data, merged_data])- else:- self._data = merged_data-- self.clear_index()- self.metadata["updated_at"] = datetime.now()-- logger.info("Knowledge extraction completed")- logger.info(- f"Duration: {(datetime.now() - start_time).total_seconds():.2f} seconds"- )-- return self._data if store else merged_data-def merge(self, data_list: List[T]) -> T:"""Pure data merge method implementing field-level update strategy.@@ -191,6 +124,18 @@ class AutoModel(BaseAutoType[T]):self._index = FAISS.from_documents(documents, self.embedder)logger.info(f"Built FAISS index with {len(documents)} documents")+ def __len__(self) -> int:+ """Returns 1 if there is data (non-empty fields), 0 otherwise.++ AutoModel always represents a single unit of knowledge, so it's either+ empty (0) or contains one item (1).+ """+ if not self._data:+ return 0+ # Check if any field is non-null+ has_data = any(v is not None for v in self._data.model_dump().values())+ return 1 if has_data else 0+def search(self, query: str, top_k: int = 3) -> List[Any]:"""Searches all indexed fields using semantic similarity.diff --git a/hyperextract/core/set.py b/hyperextract/core/set.pyindex 70153c7..b6aefa0 100644--- a/hyperextract/core/set.py+++ b/hyperextract/core/set.py@@ -170,10 +170,7 @@ class AutoSet(BaseAutoType[AutoSetSchema[Item]], Generic[Item]):llm_batch_size=self.llm_batch_size,)- # ==================== Validation ====================-- @staticmethod- def _default_prompt() -> str:+ def _default_prompt(self) -> str:"""Returns the default extraction prompt for set-based extraction."""return ("You are an expert knowledge extraction assistant. "diff --git a/hyperextract/graphs/base.py b/hyperextract/graphs/base.pyindex 74bbe2f..a97c30f 100644--- a/hyperextract/graphs/base.py+++ b/hyperextract/graphs/base.py@@ -1,71 +1,2 @@-from ..core.base import BaseAutoType-from typing import List, Optional, Dict, Any-from pydantic import BaseModel, Field+from ..core import BaseAutoType, AutoSet--class Entity(BaseModel):- """Represents a node in the knowledge graph."""-- id: str = Field(- ...,- description="The unique name or identifier of the entity (e.g., 'Elon Musk').",- )- type: str = Field(- "Unknown",- description="The category of the entity (e.g., 'Person', 'Organization', 'Concept').",- )- description: Optional[str] = Field(- None, description="A brief summary of the entity found in the text."- )---class Relationship(BaseModel):- """Represents an edge between two entities."""-- source: str = Field(..., description="The id of the source entity.")- target: str = Field(..., description="The id of the target entity.")- type: str = Field(- ..., description="The type of the relationship (e.g., 'FOUNDED', 'LOCATED_IN')."- )- description: Optional[str] = Field(- None, description="Contextual details about this relationship."- )---class GraphSchema(BaseModel):- """The container for the entire graph structure."""-- nodes: List[Entity] = Field(default_factory=list)- edges: List[Relationship] = Field(default_factory=list)-- def get_node_ids(self) -> set[str]:- """Helper to get all current node IDs for quick lookup."""- return {n.id for n in self.nodes}---class SimpleGraph(BaseAutoType[GraphSchema]):- def _get_schema_class(self):- return GraphSchema-- async def aextract(self, text: str, **kwargs):- # 1. 构造 prompt- prompt = f"Extract nodes and edges from: {text}"-- # 2. 调用自带的 LLM- response = await self.llm_client.ainvoke(prompt)-- # 3. 解析结果 (假设 parsed_data 是解析后的 GraphSchema 对象)- parsed_data = self._parse(response)-- # 4. 【直接在这里做合并逻辑】- # 简单的去重合并- existing_node_ids = {n.id for n in self._data.nodes}- for node in parsed_data.nodes:- if node.id not in existing_node_ids:- self._data.nodes.append(node)- self._data.edges.extend(parsed_data.edges)-- def dump(self, format="json"):- if format == "json":- return self._data.model_dump_json()- return self._data.model_dump()