pensiev 0.25.5__py3-none-any.whl

memos/migrations/alembic/env.py

@@ -0,0 +1,108 @@
+from logging.config import fileConfig
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+from alembic import context
+import sqlite_vec
+from sqlalchemy import event
+from urllib.parse import urlparse
+
+from memos import models
+from memos import config as memosConfig
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+target_metadata = models.RawBase.metadata
+
+# overwrite the desired value
+config.set_main_option("sqlalchemy.url", memosConfig.settings.database_url)
+
+def get_db_type():
+    """Get database type from URL."""
+    url = config.get_main_option("sqlalchemy.url")
+    return urlparse(url).scheme
+
+def configure_sqlite(engine):
+    """Configure SQLite specific settings."""
+    def load_extension(dbapi_conn, connection_record):
+        dbapi_conn.enable_load_extension(True)
+        sqlite_vec.load(dbapi_conn)
+    
+    event.listen(engine, 'connect', load_extension)
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+    # Configure the database connection based on the database type
+    db_type = get_db_type()
+    
+    # Set appropriate connection parameters based on database type
+    if db_type == 'postgresql':
+        engine_config = {
+            'pool_size': 5,
+            'max_overflow': 10,
+            'pool_timeout': 30,
+            'pool_recycle': 3600,
+        }
+    else:  # sqlite
+        engine_config = {
+            'connect_args': {'timeout': 60},
+            'poolclass': pool.NullPool,  # SQLite doesn't need connection pooling
+        }
+    
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        **engine_config
+    )
+
+    # Configure SQLite extensions if needed
+    if db_type == 'sqlite':
+        configure_sqlite(connectable)
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            # Add PostgreSQL-specific options
+            compare_type=True,  # Compare column types
+            compare_server_default=True,  # Compare default values
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

memos/migrations/alembic/script.py.mako

@@ -0,0 +1,30 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+from urllib.parse import urlparse
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+def get_db_type():
+    config = op.get_context().config
+    url = config.get_main_option("sqlalchemy.url")
+    return urlparse(url).scheme
+
+def upgrade() -> None:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}

memos/migrations/alembic/versions/00904ac8c6fc_add_indexes_to_entitymodel.py

@@ -0,0 +1,63 @@
+"""Add indexes to EntityModel
+
+Revision ID: 00904ac8c6fc
+Revises: 
+Create Date: 2024-07-17 12:16:59.911285
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import inspect
+
+
+# revision identifiers, used by Alembic.
+revision: str = '00904ac8c6fc'
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # 获取 inspector
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('entities')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+
+    # 要创建的索引列表
+    indexes = [
+        ('idx_file_type', ['file_type']),
+        ('idx_filename', ['filename']),
+        ('idx_filepath', ['filepath']),
+        ('idx_folder_id', ['folder_id']),
+        ('idx_library_id', ['library_id']),
+    ]
+
+    # 只创建不存在的索引
+    for idx_name, columns in indexes:
+        if idx_name not in existing_index_names:
+            op.create_index(idx_name, 'entities', columns, unique=False)
+
+
+def downgrade() -> None:
+    # 获取 inspector
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('entities')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+
+    # 要删除的索引列表
+    indexes = [
+        'idx_library_id',
+        'idx_folder_id',
+        'idx_filepath',
+        'idx_filename',
+        'idx_file_type',
+    ]
+
+    # 只删除存在的索引
+    for idx_name in indexes:
+        if idx_name in existing_index_names:
+            op.drop_index(idx_name, table_name='entities')

memos/migrations/alembic/versions/04acdaf75664_add_indices_to_entitytags_and_metadata.py

@@ -0,0 +1,86 @@
+"""Add indices to EntityTags and Metadata
+
+Revision ID: 04acdaf75664
+Revises: 00904ac8c6fc
+Create Date: 2024-08-14 12:18:46.039436
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import inspect
+
+
+# revision identifiers, used by Alembic.
+revision: str = '04acdaf75664'
+down_revision: Union[str, None] = '00904ac8c6fc'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # 获取 inspector
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    
+    # 检查 entity_tags 表的索引
+    entity_tags_indexes = inspector.get_indexes('entity_tags')
+    entity_tags_index_names = [idx['name'] for idx in entity_tags_indexes]
+    
+    # 检查 metadata_entries 表的索引
+    metadata_indexes = inspector.get_indexes('metadata_entries')
+    metadata_index_names = [idx['name'] for idx in metadata_indexes]
+
+    # 创建 entity_tags 的索引
+    entity_tags_indices = [
+        ('idx_entity_tag_entity_id', ['entity_id']),
+        ('idx_entity_tag_tag_id', ['tag_id']),
+    ]
+    
+    for idx_name, columns in entity_tags_indices:
+        if idx_name not in entity_tags_index_names:
+            op.create_index(idx_name, 'entity_tags', columns, unique=False)
+
+    # 创建 metadata_entries 的索引
+    metadata_indices = [
+        ('idx_metadata_entity_id', ['entity_id']),
+        ('idx_metadata_key', ['key']),
+    ]
+    
+    for idx_name, columns in metadata_indices:
+        if idx_name not in metadata_index_names:
+            op.create_index(idx_name, 'metadata_entries', columns, unique=False)
+
+
+def downgrade() -> None:
+    # 获取 inspector
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    
+    # 检查现有索引
+    entity_tags_indexes = inspector.get_indexes('entity_tags')
+    entity_tags_index_names = [idx['name'] for idx in entity_tags_indexes]
+    
+    metadata_indexes = inspector.get_indexes('metadata_entries')
+    metadata_index_names = [idx['name'] for idx in metadata_indexes]
+
+    # 删除 metadata_entries 的索引
+    metadata_indices = [
+        'idx_metadata_key',
+        'idx_metadata_entity_id',
+    ]
+    
+    for idx_name in metadata_indices:
+        if idx_name in metadata_index_names:
+            op.drop_index(idx_name, table_name='metadata_entries')
+
+    # 删除 entity_tags 的索引
+    entity_tags_indices = [
+        'idx_entity_tag_tag_id',
+        'idx_entity_tag_entity_id',
+    ]
+    
+    for idx_name in entity_tags_indices:
+        if idx_name in entity_tags_index_names:
+            op.drop_index(idx_name, table_name='entity_tags')

memos/migrations/alembic/versions/12504c5b1d3c_add_extra_columns_for_embedding.py

@@ -0,0 +1,67 @@
+"""add_extra_columns_for_embedding
+
+Revision ID: 12504c5b1d3c
+Revises: f8f158182416
+Create Date: 2025-01-02 10:11:48.997145
+
+"""
+from typing import Sequence, Union
+from urllib.parse import urlparse
+
+from alembic import op
+import sqlalchemy as sa
+from memos.config import settings
+import sqlite_vec
+from sqlalchemy import inspect
+
+
+# revision identifiers, used by Alembic.
+revision: str = '12504c5b1d3c'
+down_revision: Union[str, None] = 'f8f158182416'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def get_db_type():
+    config = op.get_context().config
+    url = config.get_main_option("sqlalchemy.url")
+    return urlparse(url).scheme
+
+
+def upgrade() -> None:
+    if get_db_type() != 'sqlite':
+        return
+
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    tables = inspector.get_table_names()
+    
+    if 'entities_vec_v2' not in tables:
+        conn = op.get_bind()
+        
+        print("Loading sqlite_vec extension...")
+        conn.connection.enable_load_extension(True)
+        sqlite_vec.load(conn.connection)
+        print("sqlite_vec extension loaded successfully")
+
+        print("Creating entities_vec_v2 table...")
+        conn.execute(
+            sa.text(
+                f"""
+                CREATE VIRTUAL TABLE IF NOT EXISTS entities_vec_v2 USING vec0(
+                    embedding float[{settings.embedding.num_dim}] distance_metric=cosine,
+                    file_type_group text,
+                    created_at_timestamp integer,
+                    file_created_at_timestamp integer,
+                    file_created_at_date text partition key,
+                    app_name text,
+                    library_id integer
+                )
+                """
+            )
+        )
+        print("Table entities_vec_v2 created successfully")
+
+
+def downgrade() -> None:
+    pass

memos/migrations/alembic/versions/31a1ad0e10b3_add_entity_plugin_status.py

@@ -0,0 +1,71 @@
+"""add_entity_plugin_status
+
+Revision ID: 31a1ad0e10b3
+Revises: 12504c5b1d3c
+Create Date: 2025-01-03 13:47:44.291335
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '31a1ad0e10b3'
+down_revision: Union[str, None] = '12504c5b1d3c'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # 创建 entity_plugin_status 表
+    op.create_table(
+        'entity_plugin_status',
+        sa.Column('entity_id', sa.Integer(), nullable=False),
+        sa.Column('plugin_id', sa.Integer(), nullable=False),
+        sa.Column('processed_at', sa.DateTime(), server_default=sa.text('CURRENT_TIMESTAMP'), nullable=False),
+        sa.ForeignKeyConstraint(['entity_id'], ['entities.id'], ondelete='CASCADE'),
+        sa.ForeignKeyConstraint(['plugin_id'], ['plugins.id'], ondelete='CASCADE'),
+        sa.PrimaryKeyConstraint('entity_id', 'plugin_id'),
+        if_not_exists=True
+    )
+
+    # 创建索引
+    op.create_index('idx_entity_plugin_entity_id', 'entity_plugin_status', ['entity_id'], if_not_exists=True)
+    op.create_index('idx_entity_plugin_plugin_id', 'entity_plugin_status', ['plugin_id'], if_not_exists=True)
+
+    # 迁移现有数据
+    # 注意：使用 execute() 执行原始 SQL
+    op.execute("""
+        INSERT INTO entity_plugin_status (entity_id, plugin_id, processed_at)
+        SELECT DISTINCT 
+            e.id as entity_id,
+            p.id as plugin_id,
+            e.last_scan_at as processed_at
+        FROM entities e
+        JOIN metadata_entries me ON e.id = me.entity_id
+        JOIN plugins p ON p.name = 'builtin_ocr'
+        WHERE me.source = 'ocr'
+    """)
+
+    op.execute("""
+        INSERT INTO entity_plugin_status (entity_id, plugin_id, processed_at)
+        SELECT DISTINCT 
+            e.id as entity_id,
+            p.id as plugin_id,
+            e.last_scan_at as processed_at
+        FROM entities e
+        JOIN metadata_entries me ON e.id = me.entity_id
+        JOIN plugins p ON p.name = 'builtin_vlm'
+        WHERE me.source = 'vlm'
+    """)
+
+
+def downgrade() -> None:
+    # 删除索引
+    op.drop_index('idx_entity_plugin_plugin_id', table_name='entity_plugin_status')
+    op.drop_index('idx_entity_plugin_entity_id', table_name='entity_plugin_status')
+    
+    # 删除表
+    op.drop_table('entity_plugin_status')

memos/migrations/alembic/versions/d10c55fbb7d2_add_index_for_entity_file_type_group_.py

@@ -0,0 +1,44 @@
+"""Add index for entity file_type_group and file_created_at
+
+Revision ID: d10c55fbb7d2
+Revises: 31a1ad0e10b3
+Create Date: 2025-01-20 23:59:42.021204
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy import inspect
+
+# revision identifiers, used by Alembic.
+revision: str = 'd10c55fbb7d2'
+down_revision: Union[str, None] = '31a1ad0e10b3'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('entities')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+
+    if 'idx_file_type_group' not in existing_index_names:
+        op.create_index("idx_file_type_group", "entities", ["file_type_group"])
+
+    if 'idx_file_created_at' not in existing_index_names:
+        op.create_index("idx_file_created_at", "entities", ["file_created_at"])
+
+
+def downgrade() -> None:
+    conn = op.get_bind()
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('entities')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+
+    if 'idx_file_type_group' in existing_index_names:
+        op.drop_index("idx_file_type_group", "entities")
+
+    if 'idx_file_created_at' in existing_index_names:
+        op.drop_index("idx_file_created_at", "entities")

memos/migrations/alembic/versions/f8f158182416_add_active_app_index.py

@@ -0,0 +1,75 @@
+"""add_active_app_index
+
+Revision ID: f8f158182416
+Revises: 04acdaf75664
+Create Date: 2024-12-30 14:42:06.165967
+
+"""
+from typing import Sequence, Union
+from urllib.parse import urlparse
+
+from alembic import op
+import sqlalchemy as sa
+import sqlite_vec
+from sqlalchemy import inspect
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'f8f158182416'
+down_revision: Union[str, None] = '04acdaf75664'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def get_db_type():
+    config = op.get_context().config
+    url = config.get_main_option("sqlalchemy.url")
+    return urlparse(url).scheme
+
+
+def upgrade() -> None:
+    if get_db_type() != 'sqlite':
+        return
+
+    # 获取 bind 连接
+    conn = op.get_bind()
+    
+    # 直接在连接上加载扩展
+    conn.connection.enable_load_extension(True)
+    sqlite_vec.load(conn.connection)
+    
+    # 检查索引是否存在
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('metadata_entries')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+    
+    # 如果索引不存在，才创建
+    if 'idx_metadata_active_app' not in existing_index_names:
+        conn.execute(
+            sa.text('''
+            CREATE INDEX idx_metadata_active_app 
+            ON metadata_entries(key, entity_id, value) 
+            WHERE key = 'active_app'
+            ''')
+        )
+
+
+def downgrade() -> None:
+    if get_db_type() != 'sqlite':
+        return
+
+    # 获取连接
+    conn = op.get_bind()
+    
+    # 直接在连接上加载扩展
+    conn.connection.enable_load_extension(True)
+    sqlite_vec.load(conn.connection)
+    
+    # 检查索引是否存在
+    inspector = inspect(conn)
+    existing_indexes = inspector.get_indexes('metadata_entries')
+    existing_index_names = [idx['name'] for idx in existing_indexes]
+    
+    # 如果索引存在，才删除
+    if 'idx_metadata_active_app' in existing_index_names:
+        conn.execute(sa.text('DROP INDEX idx_metadata_active_app'))

memos/migrations/alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = %(here)s/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to alembic/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:alembic/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# sqlalchemy.url = sqlite:///~/.memos/database.db
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S