Skip to content

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

重构导入语句,优化模块依赖关系;删除未使用的导入

yifanfeng97dc631fb31aa9
diff --git a/hyperextract/core/base.py b/hyperextract/core/base.py
index a481d6f..acc2f88 100644
--- a/hyperextract/core/base.py
+++ b/hyperextract/core/base.py
@@ -1,13 +1,13 @@
-from abc import ABC, abstractmethod
+import json
from pathlib import Path
-from typing import TypeVar, Generic, Any, Dict, Type, List
from datetime import datetime
-import json
from pydantic import BaseModel
-from langchain_core.language_models.chat_models import BaseChatModel
+from abc import ABC, abstractmethod
+from typing import TypeVar, Generic, Any, Dict, Type, List
from langchain_core.embeddings import Embeddings
-from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.language_models.chat_models import BaseChatModel
+from langchain_text_splitters import RecursiveCharacterTextSplitter
T = TypeVar("T", bound=BaseModel)
@@ -419,19 +419,21 @@ class BaseAutoType(ABC, Generic[T]):
try:
self.load_index(index_path)
except Exception as e:
- print(f"Warning: Failed to load vector index: {e}. You may need to rebuild_index().")
+ print(
+ f"Warning: Failed to load vector index: {e}. You may need to rebuild_index()."
+ )
# ==================== Serialization: Components ====================
def dump_data(self, file_path: str | Path) -> None:
"""Saves the pure knowledge data to disk as JSON.
-
+
Args:
file_path: Target file path for saving data (e.g., "data.json").
"""
path = Path(file_path)
path.parent.mkdir(parents=True, exist_ok=True)
-
+
# Use Pydantic's model_dump to serialize the schema
export_data = self.data.model_dump()
@@ -440,7 +442,7 @@ class BaseAutoType(ABC, Generic[T]):
def load_data(self, file_path: str | Path) -> None:
"""Loads data from disk and restores internal state.
-
+
Args:
file_path: Source file path containing data (e.g., "data.json").
"""
diff --git a/hyperextract/core/list.py b/hyperextract/core/list.py
index 8260cb0..feea855 100644
--- a/hyperextract/core/list.py
+++ b/hyperextract/core/list.py
@@ -1,6 +1,5 @@
"""List Knowledge Pattern - extracts a collection of objects from text."""
-from pathlib import Path
from typing import (
Any,
List,
@@ -12,6 +11,7 @@ from typing import (
Iterable,
TYPE_CHECKING,
)
+from pathlib import Path
from datetime import datetime
from pydantic import BaseModel, Field, create_model
from langchain_core.documents import Document
@@ -20,7 +20,7 @@ from langchain_core.language_models.chat_models import BaseChatModel
from langchain_community.vectorstores import FAISS
from .base import BaseAutoType
-from hyperextract.utils.logging import logger
+from ..utils.logging import logger
Item = TypeVar("Item", bound=BaseModel)
diff --git a/hyperextract/core/model.py b/hyperextract/core/model.py
index 1d7dc4f..da43860 100644
--- a/hyperextract/core/model.py
+++ b/hyperextract/core/model.py
@@ -1,22 +1,16 @@
"""Unit Knowledge Pattern - extracts a single structured object from text."""
from pathlib import Path
-from typing import List, Any, Type
from datetime import datetime
+from typing import List, Any, Type
+from ontomem.merger import MergeStrategy, create_merger, BaseMerger
from langchain_core.language_models.chat_models import BaseChatModel
from langchain_core.embeddings import Embeddings
from langchain_core.documents import Document
from langchain_community.vectorstores import FAISS
-from ontomem.merger import MergeStrategy, create_merger, BaseMerger
from .base import BaseAutoType, T
-
-try:
- from hyperextract.utils.logging import logger
-except ImportError:
- import logging
-
- logger = logging.getLogger(__name__)
+from ..utils.logging import logger
class AutoModel(BaseAutoType[T]):
@@ -70,7 +64,7 @@ class AutoModel(BaseAutoType[T]):
"""
# Store strategy before calling super().__init__
self._strategy_or_merger = strategy_or_merger
-
+
super().__init__(
data_schema,
llm_client,
@@ -214,7 +208,7 @@ class AutoModel(BaseAutoType[T]):
"""
if not data_list:
return self._data_schema()
-
+
if len(data_list) == 1:
return data_list[0]
diff --git a/hyperextract/core/set.py b/hyperextract/core/set.py
index 2ddf0f6..4803cd9 100644
--- a/hyperextract/core/set.py
+++ b/hyperextract/core/set.py
@@ -4,7 +4,6 @@ Provides automatic deduplication based on a user-specified unique key field.
Supports multiple merge strategies including LLM-powered intelligent merging.
"""
-from pathlib import Path
from typing import (
Any,
List,
@@ -15,15 +14,16 @@ from typing import (
Callable,
TYPE_CHECKING,
)
+from pathlib import Path
from datetime import datetime
from ontomem import OMem
from ontomem.merger import MergeStrategy, create_merger, BaseMerger
from pydantic import BaseModel, Field, create_model
-from langchain_core.language_models.chat_models import BaseChatModel
from langchain_core.embeddings import Embeddings
+from langchain_core.language_models.chat_models import BaseChatModel
from .base import BaseAutoType
-from hyperextract.utils.logging import logger
+from ..utils.logging import logger
Item = TypeVar("Item", bound=BaseModel)
diff --git a/hyperextract/graphs/base.py b/hyperextract/graphs/base.py
index a97c30f..e69de29 100644
--- a/hyperextract/graphs/base.py
+++ b/hyperextract/graphs/base.py
@@ -1,2 +0,0 @@
-from ..core import BaseAutoType, AutoSet
-