AstrBot 3.5.6__py3-none-any.whl → 4.7.0__py3-none-any.whl

astrbot/core/db/vec_db/base.py

@@ -0,0 +1,73 @@
+import abc
+from dataclasses import dataclass
+
+
+@dataclass
+class Result:
+    similarity: float
+    data: dict
+
+
+class BaseVecDB:
+    async def initialize(self):
+        """初始化向量数据库"""
+
+    @abc.abstractmethod
+    async def insert(
+        self,
+        content: str,
+        metadata: dict | None = None,
+        id: str | None = None,
+    ) -> int:
+        """插入一条文本和其对应向量，自动生成 ID 并保持一致性。"""
+        ...
+
+    @abc.abstractmethod
+    async def insert_batch(
+        self,
+        contents: list[str],
+        metadatas: list[dict] | None = None,
+        ids: list[str] | None = None,
+        batch_size: int = 32,
+        tasks_limit: int = 3,
+        max_retries: int = 3,
+        progress_callback=None,
+    ) -> int:
+        """批量插入文本和其对应向量，自动生成 ID 并保持一致性。
+
+        Args:
+            progress_callback: 进度回调函数，接收参数 (current, total)
+
+        """
+        ...
+
+    @abc.abstractmethod
+    async def retrieve(
+        self,
+        query: str,
+        top_k: int = 5,
+        fetch_k: int = 20,
+        rerank: bool = False,
+        metadata_filters: dict | None = None,
+    ) -> list[Result]:
+        """搜索最相似的文档。
+        Args:
+            query (str): 查询文本
+            top_k (int): 返回的最相似文档的数量
+        Returns:
+            List[Result]: 查询结果
+        """
+        ...
+
+    @abc.abstractmethod
+    async def delete(self, doc_id: str) -> bool:
+        """删除指定文档。
+        Args:
+            doc_id (str): 要删除的文档 ID
+        Returns:
+            bool: 删除是否成功
+        """
+        ...
+
+    @abc.abstractmethod
+    async def close(self): ...

astrbot/core/db/vec_db/faiss_impl/__init__.py

@@ -0,0 +1,3 @@
+from .vec_db import FaissVecDB
+
+__all__ = ["FaissVecDB"]

astrbot/core/db/vec_db/faiss_impl/document_storage.py

@@ -0,0 +1,392 @@
+import json
+import os
+from contextlib import asynccontextmanager
+from datetime import datetime
+
+from sqlalchemy import Column, Text
+from sqlalchemy.ext.asyncio import AsyncEngine, AsyncSession, create_async_engine
+from sqlalchemy.orm import sessionmaker
+from sqlmodel import Field, MetaData, SQLModel, col, func, select, text
+
+from astrbot.core import logger
+
+
+class BaseDocModel(SQLModel, table=False):
+    metadata = MetaData()
+
+
+class Document(BaseDocModel, table=True):
+    """SQLModel for documents table."""
+
+    __tablename__ = "documents"  # type: ignore
+
+    id: int | None = Field(
+        default=None,
+        primary_key=True,
+        sa_column_kwargs={"autoincrement": True},
+    )
+    doc_id: str = Field(nullable=False)
+    text: str = Field(nullable=False)
+    metadata_: str | None = Field(default=None, sa_column=Column("metadata", Text))
+    created_at: datetime | None = Field(default=None)
+    updated_at: datetime | None = Field(default=None)
+
+
+class DocumentStorage:
+    def __init__(self, db_path: str):
+        self.db_path = db_path
+        self.DATABASE_URL = f"sqlite+aiosqlite:///{db_path}"
+        self.engine: AsyncEngine | None = None
+        self.async_session_maker: sessionmaker | None = None
+        self.sqlite_init_path = os.path.join(
+            os.path.dirname(__file__),
+            "sqlite_init.sql",
+        )
+
+    async def initialize(self):
+        """Initialize the SQLite database and create the documents table if it doesn't exist."""
+        await self.connect()
+        async with self.engine.begin() as conn:  # type: ignore
+            # Create tables using SQLModel
+            await conn.run_sync(BaseDocModel.metadata.create_all)
+
+            try:
+                await conn.execute(
+                    text(
+                        "ALTER TABLE documents ADD COLUMN kb_doc_id TEXT "
+                        "GENERATED ALWAYS AS (json_extract(metadata, '$.kb_doc_id')) STORED",
+                    ),
+                )
+                await conn.execute(
+                    text(
+                        "ALTER TABLE documents ADD COLUMN user_id TEXT "
+                        "GENERATED ALWAYS AS (json_extract(metadata, '$.user_id')) STORED",
+                    ),
+                )
+
+                # Create indexes
+                await conn.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_documents_kb_doc_id ON documents(kb_doc_id)",
+                    ),
+                )
+                await conn.execute(
+                    text(
+                        "CREATE INDEX IF NOT EXISTS idx_documents_user_id ON documents(user_id)",
+                    ),
+                )
+            except BaseException:
+                pass
+
+            await conn.commit()
+
+    async def connect(self):
+        """Connect to the SQLite database."""
+        if self.engine is None:
+            self.engine = create_async_engine(
+                self.DATABASE_URL,
+                echo=False,
+                future=True,
+            )
+            self.async_session_maker = sessionmaker(
+                self.engine,  # type: ignore
+                class_=AsyncSession,
+                expire_on_commit=False,
+            )  # type: ignore
+
+    @asynccontextmanager
+    async def get_session(self):
+        """Context manager for database sessions."""
+        async with self.async_session_maker() as session:  # type: ignore
+            yield session
+
+    async def get_documents(
+        self,
+        metadata_filters: dict,
+        ids: list | None = None,
+        offset: int | None = 0,
+        limit: int | None = 100,
+    ) -> list[dict]:
+        """Retrieve documents by metadata filters and ids.
+
+        Args:
+            metadata_filters (dict): The metadata filters to apply.
+            ids (list | None): Optional list of document IDs to filter.
+            offset (int | None): Offset for pagination.
+            limit (int | None): Limit for pagination.
+
+        Returns:
+            list: The list of documents that match the filters.
+
+        """
+        if self.engine is None:
+            logger.warning(
+                "Database connection is not initialized, returning empty result",
+            )
+            return []
+
+        async with self.get_session() as session:
+            query = select(Document)
+
+            for key, val in metadata_filters.items():
+                query = query.where(
+                    text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                ).params(**{f"filter_{key}": val})
+
+            if ids is not None and len(ids) > 0:
+                valid_ids = [int(i) for i in ids if i != -1]
+                if valid_ids:
+                    query = query.where(col(Document.id).in_(valid_ids))
+
+            if limit is not None:
+                query = query.limit(limit)
+            if offset is not None:
+                query = query.offset(offset)
+
+            result = await session.execute(query)
+            documents = result.scalars().all()
+
+            return [self._document_to_dict(doc) for doc in documents]
+
+    async def insert_document(self, doc_id: str, text: str, metadata: dict) -> int:
+        """Insert a single document and return its integer ID.
+
+        Args:
+            doc_id (str): The document ID (UUID string).
+            text (str): The document text.
+            metadata (dict): The document metadata.
+
+        Returns:
+            int: The integer ID of the inserted document.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            document = Document(
+                doc_id=doc_id,
+                text=text,
+                metadata_=json.dumps(metadata),
+                created_at=datetime.now(),
+                updated_at=datetime.now(),
+            )
+            session.add(document)
+            await session.flush()  # Flush to get the ID
+            return document.id  # type: ignore
+
+    async def insert_documents_batch(
+        self,
+        doc_ids: list[str],
+        texts: list[str],
+        metadatas: list[dict],
+    ) -> list[int]:
+        """Batch insert documents and return their integer IDs.
+
+        Args:
+            doc_ids (list[str]): List of document IDs (UUID strings).
+            texts (list[str]): List of document texts.
+            metadatas (list[dict]): List of document metadata.
+
+        Returns:
+            list[int]: List of integer IDs of the inserted documents.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            import json
+
+            documents = []
+            for doc_id, text, metadata in zip(doc_ids, texts, metadatas):
+                document = Document(
+                    doc_id=doc_id,
+                    text=text,
+                    metadata_=json.dumps(metadata),
+                    created_at=datetime.now(),
+                    updated_at=datetime.now(),
+                )
+                documents.append(document)
+                session.add(document)
+
+            await session.flush()  # Flush to get all IDs
+            return [doc.id for doc in documents]  # type: ignore
+
+    async def delete_document_by_doc_id(self, doc_id: str):
+        """Delete a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id of the document to delete.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                await session.delete(document)
+
+    async def get_document_by_doc_id(self, doc_id: str):
+        """Retrieve a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id of the document to retrieve.
+
+        Returns:
+            dict: The document data or None if not found.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session:
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                return self._document_to_dict(document)
+            return None
+
+    async def update_document_by_doc_id(self, doc_id: str, new_text: str):
+        """Update a document by its doc_id.
+
+        Args:
+            doc_id (str): The doc_id.
+            new_text (str): The new text to update the document with.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document).where(col(Document.doc_id) == doc_id)
+            result = await session.execute(query)
+            document = result.scalar_one_or_none()
+
+            if document:
+                document.text = new_text
+                document.updated_at = datetime.now()
+                session.add(document)
+
+    async def delete_documents(self, metadata_filters: dict):
+        """Delete documents by their metadata filters.
+
+        Args:
+            metadata_filters (dict): The metadata filters to apply.
+
+        """
+        if self.engine is None:
+            logger.warning(
+                "Database connection is not initialized, skipping delete operation",
+            )
+            return
+
+        async with self.get_session() as session, session.begin():
+            query = select(Document)
+
+            for key, val in metadata_filters.items():
+                query = query.where(
+                    text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                ).params(**{f"filter_{key}": val})
+
+            result = await session.execute(query)
+            documents = result.scalars().all()
+
+            for doc in documents:
+                await session.delete(doc)
+
+    async def count_documents(self, metadata_filters: dict | None = None) -> int:
+        """Count documents in the database.
+
+        Args:
+            metadata_filters (dict | None): Metadata filters to apply.
+
+        Returns:
+            int: The count of documents.
+
+        """
+        if self.engine is None:
+            logger.warning("Database connection is not initialized, returning 0")
+            return 0
+
+        async with self.get_session() as session:
+            query = select(func.count(col(Document.id)))
+
+            if metadata_filters:
+                for key, val in metadata_filters.items():
+                    query = query.where(
+                        text(f"json_extract(metadata, '$.{key}') = :filter_{key}"),
+                    ).params(**{f"filter_{key}": val})
+
+            result = await session.execute(query)
+            count = result.scalar_one_or_none()
+            return count if count is not None else 0
+
+    async def get_user_ids(self) -> list[str]:
+        """Retrieve all user IDs from the documents table.
+
+        Returns:
+            list: A list of user IDs.
+
+        """
+        assert self.engine is not None, "Database connection is not initialized."
+
+        async with self.get_session() as session:
+            query = text(
+                "SELECT DISTINCT user_id FROM documents WHERE user_id IS NOT NULL",
+            )
+            result = await session.execute(query)
+            rows = result.fetchall()
+            return [row[0] for row in rows]
+
+    def _document_to_dict(self, document: Document) -> dict:
+        """Convert a Document model to a dictionary.
+
+        Args:
+            document (Document): The document to convert.
+
+        Returns:
+            dict: The converted dictionary.
+
+        """
+        return {
+            "id": document.id,
+            "doc_id": document.doc_id,
+            "text": document.text,
+            "metadata": document.metadata_,
+            "created_at": document.created_at.isoformat()
+            if isinstance(document.created_at, datetime)
+            else document.created_at,
+            "updated_at": document.updated_at.isoformat()
+            if isinstance(document.updated_at, datetime)
+            else document.updated_at,
+        }
+
+    async def tuple_to_dict(self, row):
+        """Convert a tuple to a dictionary.
+
+        Args:
+            row (tuple): The row to convert.
+
+        Returns:
+            dict: The converted dictionary.
+
+        Note: This method is kept for backward compatibility but is no longer used internally.
+
+        """
+        return {
+            "id": row[0],
+            "doc_id": row[1],
+            "text": row[2],
+            "metadata": row[3],
+            "created_at": row[4],
+            "updated_at": row[5],
+        }
+
+    async def close(self):
+        """Close the connection to the SQLite database."""
+        if self.engine:
+            await self.engine.dispose()
+            self.engine = None
+            self.async_session_maker = None

astrbot/core/db/vec_db/faiss_impl/embedding_storage.py

@@ -0,0 +1,93 @@
+try:
+    import faiss
+except ModuleNotFoundError:
+    raise ImportError(
+        "faiss 未安装。请使用 'pip install faiss-cpu' 或 'pip install faiss-gpu' 安装。",
+    )
+import os
+
+import numpy as np
+
+
+class EmbeddingStorage:
+    def __init__(self, dimension: int, path: str | None = None):
+        self.dimension = dimension
+        self.path = path
+        self.index = None
+        if path and os.path.exists(path):
+            self.index = faiss.read_index(path)
+        else:
+            base_index = faiss.IndexFlatL2(dimension)
+            self.index = faiss.IndexIDMap(base_index)
+
+    async def insert(self, vector: np.ndarray, id: int):
+        """插入向量
+
+        Args:
+            vector (np.ndarray): 要插入的向量
+            id (int): 向量的ID
+        Raises:
+            ValueError: 如果向量的维度与存储的维度不匹配
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        if vector.shape[0] != self.dimension:
+            raise ValueError(
+                f"向量维度不匹配, 期望: {self.dimension}, 实际: {vector.shape[0]}",
+            )
+        self.index.add_with_ids(vector.reshape(1, -1), np.array([id]))
+        await self.save_index()
+
+    async def insert_batch(self, vectors: np.ndarray, ids: list[int]):
+        """批量插入向量
+
+        Args:
+            vectors (np.ndarray): 要插入的向量数组
+            ids (list[int]): 向量的ID列表
+        Raises:
+            ValueError: 如果向量的维度与存储的维度不匹配
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        if vectors.shape[1] != self.dimension:
+            raise ValueError(
+                f"向量维度不匹配, 期望: {self.dimension}, 实际: {vectors.shape[1]}",
+            )
+        self.index.add_with_ids(vectors, np.array(ids))
+        await self.save_index()
+
+    async def search(self, vector: np.ndarray, k: int) -> tuple:
+        """搜索最相似的向量
+
+        Args:
+            vector (np.ndarray): 查询向量
+            k (int): 返回的最相似向量的数量
+        Returns:
+            tuple: (距离, 索引)
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        faiss.normalize_L2(vector)
+        distances, indices = self.index.search(vector, k)
+        return distances, indices
+
+    async def delete(self, ids: list[int]):
+        """删除向量
+
+        Args:
+            ids (list[int]): 要删除的向量ID列表
+
+        """
+        assert self.index is not None, "FAISS index is not initialized."
+        id_array = np.array(ids, dtype=np.int64)
+        self.index.remove_ids(id_array)
+        await self.save_index()
+
+    async def save_index(self):
+        """保存索引
+
+        Args:
+            path (str): 保存索引的路径
+
+        """
+        faiss.write_index(self.index, self.path)

astrbot/core/db/vec_db/faiss_impl/sqlite_init.sql

@@ -0,0 +1,17 @@
+-- 创建文档存储表，包含 faiss 中文档的 id，文档文本，create_at，updated_at
+CREATE TABLE documents (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    doc_id TEXT NOT NULL,
+    text TEXT NOT NULL,
+    metadata TEXT,
+    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+    updated_at DATETIME DEFAULT CURRENT_TIMESTAMP
+);
+
+ALTER TABLE documents
+ADD COLUMN group_id TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.group_id')) STORED;
+ALTER TABLE documents
+ADD COLUMN user_id TEXT GENERATED ALWAYS AS (json_extract(metadata, '$.user_id')) STORED;
+
+CREATE INDEX idx_documents_user_id ON documents(user_id);
+CREATE INDEX idx_documents_group_id ON documents(group_id);