重构代码，实现相对导入

rag_indexer/__init__.py

@@ -23,9 +23,9 @@ Offline RAG Indexer module.
     >>> await builder.build_from_file("document.pdf")
 """
 
-from rag_indexer.index_builder import IndexBuilder, IndexBuilderConfig, DocstoreConfig
-from rag_indexer.loaders import DocumentLoader
-from rag_indexer.splitters import SplitterType, get_splitter
+from .index_builder import IndexBuilder, IndexBuilderConfig, DocstoreConfig
+from .loaders import DocumentLoader
+from .splitters import SplitterType, get_splitter
 
 # 从 rag_core 重新导出常用组件
 from rag_core import (

rag_indexer/cli.py

@@ -7,8 +7,12 @@ import logging
 import sys
 from pathlib import Path
 
-from rag_indexer.index_builder import IndexBuilder, IndexBuilderConfig
-from rag_indexer.splitters import SplitterType
+# 添加项目根目录和 backend 目录到 Python 路径
+sys.path.insert(0, str(Path(__file__).parent.parent))
+sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))
+
+from .index_builder import IndexBuilder, IndexBuilderConfig
+from .splitters import SplitterType
 
 logging.basicConfig(
     level=logging.INFO,

rag_indexer/index_builder.py

@@ -6,10 +6,14 @@
 
 import asyncio
 import logging
-from dataclasses import dataclass, field
+import sys
 from pathlib import Path
+from dataclasses import dataclass, field
 from typing import List, Union, Optional, Any, Dict
 
+# 添加 backend 目录到路径以导入 rag_core
+sys.path.insert(0, str(Path(__file__).parent.parent / "backend"))
+
 from httpx import RemoteProtocolError
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
@@ -17,8 +21,8 @@ from langchain_core.stores import BaseStore
 from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter
 from qdrant_client.http.exceptions import ResponseHandlingException
 
-from rag_indexer.loaders import DocumentLoader
-from rag_indexer.splitters import SplitterType, get_splitter
+from .loaders import DocumentLoader
+from .splitters import SplitterType, get_splitter
 from rag_core import LlamaCppEmbedder, QdrantVectorStore, create_docstore, create_parent_retriever
 
 logger = logging.getLogger(__name__)

rag_indexer/requirements.txt

@@ -0,0 +1,33 @@
+# RAG Indexer - 本地索引工具依赖
+# 依赖 rag_core (从 ../backend/rag_core 导入)
+
+# Core
+pydantic==2.12.5
+python-dotenv==1.2.2
+typing-extensions==4.15.0
+
+# LangChain (用于文档处理)
+langchain==1.2.15
+langchain-community==0.4.1
+langchain-core==1.2.28
+tiktoken>=0.12.0
+
+# Vector DB
+qdrant-client==1.17.1
+
+# HTTP
+httpx==0.28.1
+
+# Utilities
+tenacity==9.1.4
+rich==15.0.0
+PyYAML==6.0.3
+numpy>=1.26.2
+
+# Document Processing
+unstructured==0.22.21
+pypdf==6.10.0
+beautifulsoup4==4.14.3
+lxml==6.1.0
+pandas==3.0.2
+spacy==3.8.14

rag_indexer/test/test_inspect_vectors.py

@@ -5,12 +5,10 @@ import sys
 import numpy as np
 from dotenv import load_dotenv
 from qdrant_client import QdrantClient
-
+from backend.rag_core import LlamaCppEmbedder
+load_dotenv()
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../.."))
-from rag_core import LlamaCppEmbedder
-
-load_dotenv()
 
 QDRANT_URL = os.getenv("QDRANT_URL", "http://127.0.0.1:6333")
 QDRANT_API_KEY = os.getenv("QDRANT_API_KEY")

rag_indexer/test/test_refactored.py

@@ -10,8 +10,8 @@ import sys
 # 添加项目根目录到 Python 路径
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", ".."))
 
-from rag_indexer.index_builder import IndexBuilder
-from rag_indexer.splitters import SplitterType
+from ..index_builder import IndexBuilder
+from ..splitters import SplitterType
 
 async def test_index_builder():
     """测试索引构建功能"""