修改引用逻辑，修改长期记忆bug

rag_core/__init__.py

@@ -4,10 +4,10 @@ RAG Core - 公共 RAG 组件包
 提供嵌入模型、向量存储和文档存储的公共功能，被 rag_indexer 和 app/rag 共用。
 """
 
-from .embedders import LlamaCppEmbedder
-from .vector_store import QdrantVectorStore, QDRANT_URL, QDRANT_API_KEY
-from .store import PostgresDocStore, create_docstore
-from .retriever_factory import create_parent_retriever
+from rag_core.embedders import LlamaCppEmbedder
+from rag_core.vector_store import QdrantVectorStore, QDRANT_URL, QDRANT_API_KEY
+from rag_core.store import PostgresDocStore, create_docstore
+from rag_core.retriever_factory import create_parent_retriever
 
 
 __all__ = [

rag_core/embedders.py

@@ -5,11 +5,9 @@
 import os
 import httpx
 from typing import List, Optional
-from urllib.parse import urljoin
 
 from langchain_core.embeddings import Embeddings
 
-
 class LlamaCppEmbedder:
     """通过 OpenAI 兼容 API 封装 llama.cpp 嵌入服务。"""
 
@@ -17,7 +15,7 @@ class LlamaCppEmbedder:
         self,
         base_url: Optional[str] = None,
         api_key: Optional[str] = None,
-        model: str = "embeddinggemma-300M-Q8_0",
+        model: str = "Qwen3-Embedding-0.6B-Q8_0",
     ):
         self.base_url = base_url or os.getenv("LLAMACPP_EMBEDDING_URL", "http://127.0.0.1:8082")
         self.api_key = api_key or os.getenv("LLAMACPP_API_KEY", "")
@@ -71,7 +69,6 @@ class LlamaCppEmbedder:
             else:
                 raise ValueError(f"未知的嵌入 API 响应格式: {data}")
 
-
 class _LlamaCppLangchainAdapter(Embeddings):
     """将 LlamaCppEmbedder 适配为 LangChain Embeddings 接口。"""
 

rag_core/retriever_factory.py

@@ -2,14 +2,7 @@
 from langchain_core.embeddings import Embeddings
 from langchain_classic.retrievers import ParentDocumentRetriever
 from langchain_text_splitters import RecursiveCharacterTextSplitter
-from rag_indexer.splitters import SplitterType, get_splitter
-import asyncio
-import logging
-from dataclasses import dataclass, field
-from pathlib import Path
-from typing import List, Union, Optional, Any, Dict, Tuple
-from httpx import RemoteProtocolError
-from langchain_core.documents import Document
+from typing import Optional
 from langchain_core.embeddings import Embeddings
 from langchain_core.stores import BaseStore
 from langchain_text_splitters import RecursiveCharacterTextSplitter, TextSplitter
@@ -17,7 +10,6 @@ from langchain_classic.retrievers import ParentDocumentRetriever
 
 from rag_core import LlamaCppEmbedder, QdrantVectorStore, create_docstore
 
-
 def create_parent_retriever(
     collection_name: str = "rag_documents",
     embeddings: Optional[Embeddings] = None,

rag_core/store/__init__.py

@@ -15,8 +15,8 @@
 """
 
 
-from .postgres import PostgresDocStore
-from .factory import create_docstore, get_docstore_uri, DEFAULT_DB_URI
+from rag_core.store.postgres import PostgresDocStore
+from rag_core.store.factory import create_docstore, get_docstore_uri, DEFAULT_DB_URI
 
 __version__ = "2.0.0"
 

rag_core/store/factory.py

@@ -9,7 +9,7 @@ import logging
 from typing import Optional, Tuple
 
 from langchain_core.stores import BaseStore
-from .postgres import PostgresDocStore
+from rag_core.store.postgres import PostgresDocStore
 
 logger = logging.getLogger(__name__)
 

rag_core/store/postgres.py

@@ -4,12 +4,10 @@
 使用 asyncpg 实现真正的异步 PostgreSQL 文档存储，支持高并发访问。
 """
 
-from __future__ import annotations
-
 import asyncio
 import json
 import logging
-from typing import List, Dict, Any, Optional, Iterator, Tuple, Sequence, cast
+from typing import List, Dict, Any, Optional, Iterator, Tuple, Sequence
 
 from langchain_core.documents import Document
 from langchain_core.stores import BaseStore
@@ -18,7 +16,6 @@ import asyncpg
 
 logger = logging.getLogger(__name__)
 
-
 class PostgresDocStore(BaseStore[str, Any]):
     """
     异步 PostgreSQL 文档存储实现。

rag_core/vector_store.py

@@ -13,7 +13,7 @@ from qdrant_client import QdrantClient
 from qdrant_client.http.models import Distance, VectorParams
 from httpx import RemoteProtocolError
 from qdrant_client.http.exceptions import ResponseHandlingException
-from .client import create_qdrant_client
+from rag_core.client import create_qdrant_client
 
 logger = logging.getLogger(__name__)
 
@@ -35,7 +35,7 @@ class QdrantVectorStore:
         self._last_connection_time: Optional[float] = None
 
         if embeddings is None:
-            from .embedders import LlamaCppEmbedder
+            from rag_core.embedders import LlamaCppEmbedder
             embedder = LlamaCppEmbedder()
             self.embeddings = embedder.as_langchain_embeddings()
         else:
@@ -96,7 +96,7 @@ class QdrantVectorStore:
     def create_collection(self, vector_size: Optional[int] = None, force_recreate: bool = False):
         """创建集合，设置合适的向量维度。"""
         if vector_size is None:
-            from .embedders import LlamaCppEmbedder
+            from rag_core.embedders import LlamaCppEmbedder
             embedder = LlamaCppEmbedder()
             vector_size = embedder.get_embedding_dimension()