init. project

2026-04-13 11:34:23 +08:00
commit c7c0659a85
202 changed files with 31196 additions and 0 deletions
--- a/rag-web-ui/backend/alembic/versions/initial_schema.py
+++ b/rag-web-ui/backend/alembic/versions/initial_schema.py
@@ -0,0 +1,148 @@
+"""initial schema
+
+Revision ID: initial_schema
+Revises: 
+Create Date: 2024-01-13 15:00:00.000000
+
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import mysql
+
+# revision identifiers, used by Alembic.
+revision: str = 'initial_schema'
+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:
+    # Create users table
+    op.create_table(
+        'users',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('email', sa.String(255), nullable=False),
+        sa.Column('username', sa.String(255), nullable=False),
+        sa.Column('hashed_password', sa.String(255), nullable=False),
+        sa.Column('is_active', sa.Boolean(), nullable=True, default=True),
+        sa.Column('is_superuser', sa.Boolean(), nullable=True, default=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.PrimaryKeyConstraint('id'),
+        sa.UniqueConstraint('email'),
+        sa.UniqueConstraint('username')
+    )
+
+    # Create knowledge_bases table
+    op.create_table(
+        'knowledge_bases',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('name', sa.String(255), nullable=False),
+        sa.Column('description', mysql.LONGTEXT(), nullable=True),
+        sa.Column('user_id', sa.Integer(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['user_id'], ['users.id'], ),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create documents table
+    op.create_table(
+        'documents',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('file_path', sa.String(255), nullable=False),
+        sa.Column('file_name', sa.String(255), nullable=False),
+        sa.Column('file_size', sa.Integer(), nullable=True),
+        sa.Column('content_type', sa.String(100), nullable=True),
+        sa.Column('file_hash', sa.String(64), nullable=True),
+        sa.Column('knowledge_base_id', sa.Integer(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['knowledge_base_id'], ['knowledge_bases.id'], ),
+        sa.PrimaryKeyConstraint('id'),
+        sa.UniqueConstraint('knowledge_base_id', 'file_name', name='uq_kb_file_name')
+    )
+
+    # Create document_chunks table
+    op.create_table(
+        'document_chunks',
+        sa.Column('id', sa.String(64), nullable=False),
+        sa.Column('kb_id', sa.Integer(), nullable=False),
+        sa.Column('file_name', sa.String(255), nullable=False),
+        sa.Column('metadata', sa.JSON(), nullable=True),
+        sa.Column('hash', sa.String(64), nullable=False),
+        sa.Column('created_at', sa.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP')),
+        sa.Column('updated_at', sa.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP')),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create chats table
+    op.create_table(
+        'chats',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('title', sa.String(255), nullable=False),
+        sa.Column('user_id', sa.Integer(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['user_id'], ['users.id'], ),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create chat_knowledge_bases table (association table)
+    op.create_table(
+        'chat_knowledge_bases',
+        sa.Column('chat_id', sa.Integer(), nullable=False),
+        sa.Column('knowledge_base_id', sa.Integer(), nullable=False),
+        sa.ForeignKeyConstraint(['chat_id'], ['chats.id'], ),
+        sa.ForeignKeyConstraint(['knowledge_base_id'], ['knowledge_bases.id'], ),
+        sa.PrimaryKeyConstraint('chat_id', 'knowledge_base_id')
+    )
+
+    # Create messages table
+    op.create_table(
+        'messages',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('chat_id', sa.Integer(), nullable=False),
+        sa.Column('role', sa.String(50), nullable=False),
+        sa.Column('content', mysql.LONGTEXT(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['chat_id'], ['chats.id'], ),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create processing_tasks table
+    op.create_table(
+        'processing_tasks',
+        sa.Column('id', sa.Integer(), nullable=False),
+        sa.Column('knowledge_base_id', sa.Integer(), nullable=False),
+        sa.Column('document_id', sa.Integer(), nullable=False),
+        sa.Column('status', sa.String(50), nullable=False, default='pending'),
+        sa.Column('error_message', sa.Text(), nullable=True),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('updated_at', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['document_id'], ['documents.id'], ),
+        sa.ForeignKeyConstraint(['knowledge_base_id'], ['knowledge_bases.id'], ),
+        sa.PrimaryKeyConstraint('id')
+    )
+
+    # Create indexes
+    op.create_index('idx_kb_file_name', 'document_chunks', ['kb_id', 'file_name'])
+    op.create_index('idx_hash', 'document_chunks', ['hash'])
+    op.create_index('idx_file_hash', 'documents', ['file_hash'])
+
+def downgrade() -> None:
+    # Drop indexes
+    op.drop_index('idx_hash', table_name='document_chunks')
+    op.drop_index('idx_kb_file_name', table_name='document_chunks')
+    op.drop_index('idx_file_hash', table_name='documents')
+
+    # Drop tables in reverse order
+    op.drop_table('processing_tasks')
+    op.drop_table('messages')
+    op.drop_table('chat_knowledge_bases')
+    op.drop_table('chats')
+    op.drop_table('document_chunks')
+    op.drop_table('documents')
+    op.drop_table('knowledge_bases')
+    op.drop_table('users')