feat: database models and Alembic migrations — User, Recording, Transcription, Protocol, PromptTemplate, ExportFile

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/app/config.py

@@ -0,0 +1,28 @@
+from pydantic_settings import BaseSettings
+
+
+class Settings(BaseSettings):
+    database_url: str = "postgresql+asyncpg://meetproto:changeme@db:5432/meetproto"
+    redis_url: str = "redis://redis:6379/0"
+    jwt_secret: str = "change-this-to-a-random-secret"
+    jwt_algorithm: str = "HS256"
+    jwt_expire_minutes: int = 1440
+    whisper_model: str = "large-v3"
+    whisper_device: str = "cuda"
+    whisper_compute_type: str = "float16"
+    litellm_model: str = "openrouter/meta-llama/llama-3.1-70b-instruct"
+    litellm_api_key: str = ""
+    litellm_api_base: str = ""
+    upload_dir: str = "/app/uploads"
+    export_dir: str = "/app/exports"
+    retention_days: int = 90
+    telegram_bot_token: str = ""
+    telegram_webhook_url: str = ""
+    app_host: str = "0.0.0.0"
+    app_port: int = 8000
+    app_url: str = "http://localhost:8000"
+
+    model_config = {"env_file": ".env", "extra": "ignore"}
+
+
+settings = Settings()

backend/app/database.py

@@ -0,0 +1,11 @@
+from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
+
+from app.config import settings
+
+engine = create_async_engine(settings.database_url, echo=False)
+async_session = async_sessionmaker(engine, expire_on_commit=False)
+
+
+async def get_db():
+    async with async_session() as session:
+        yield session

backend/app/models/__init__.py

@@ -0,0 +1,23 @@
+from app.models.base import Base
+from app.models.export_file import ExportFile, ExportFormat
+from app.models.prompt_template import PromptTemplate, TemplateType
+from app.models.protocol import Protocol, ProtocolStatus
+from app.models.recording import Recording, RecordingSource, RecordingStatus
+from app.models.transcription import Transcription
+from app.models.user import User, UserRole
+
+__all__ = [
+    "Base",
+    "User",
+    "UserRole",
+    "Recording",
+    "RecordingSource",
+    "RecordingStatus",
+    "Transcription",
+    "Protocol",
+    "ProtocolStatus",
+    "PromptTemplate",
+    "TemplateType",
+    "ExportFile",
+    "ExportFormat",
+]

backend/app/models/base.py

@@ -0,0 +1,21 @@
+import uuid
+from datetime import datetime
+
+from sqlalchemy import DateTime, func
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
+
+
+class Base(DeclarativeBase):
+    pass
+
+
+class TimestampMixin:
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), server_default=func.now()
+    )
+
+
+class UUIDMixin:
+    id: Mapped[uuid.UUID] = mapped_column(
+        primary_key=True, default=uuid.uuid4
+    )

backend/app/models/export_file.py

@@ -0,0 +1,26 @@
+import enum
+import uuid
+
+from sqlalchemy import BigInteger, Enum, ForeignKey, String
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class ExportFormat(str, enum.Enum):
+    docx = "docx"
+    pdf = "pdf"
+    md = "md"
+
+
+class ExportFile(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "export_files"
+
+    protocol_id: Mapped[uuid.UUID] = mapped_column(
+        ForeignKey("protocols.id", ondelete="CASCADE")
+    )
+    format: Mapped[ExportFormat] = mapped_column(Enum(ExportFormat))
+    file_path: Mapped[str] = mapped_column(String(1000))
+    file_size: Mapped[int] = mapped_column(BigInteger)
+
+    protocol: Mapped["Protocol"] = relationship(back_populates="export_files")

backend/app/models/prompt_template.py

@@ -0,0 +1,28 @@
+import enum
+
+from sqlalchemy import Boolean, Enum, String, Text
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class TemplateType(str, enum.Enum):
+    client_survey = "client_survey"
+    client_intro = "client_intro"
+    internal = "internal"
+    custom = "custom"
+
+
+class PromptTemplate(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "prompt_templates"
+
+    name: Mapped[str] = mapped_column(String(255))
+    description: Mapped[str] = mapped_column(String(1000), default="")
+    type: Mapped[TemplateType] = mapped_column(Enum(TemplateType))
+    system_prompt: Mapped[str] = mapped_column(Text)
+    user_prompt: Mapped[str] = mapped_column(Text)
+    output_schema: Mapped[dict] = mapped_column(JSONB, default=dict)
+    is_default: Mapped[bool] = mapped_column(Boolean, default=False)
+
+    protocols: Mapped[list["Protocol"]] = relationship(back_populates="template")

backend/app/models/protocol.py

@@ -0,0 +1,39 @@
+import enum
+import uuid
+from datetime import datetime
+
+from sqlalchemy import DateTime, Enum, ForeignKey, String, Text, func
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class ProtocolStatus(str, enum.Enum):
+    generating = "generating"
+    done = "done"
+    error = "error"
+
+
+class Protocol(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "protocols"
+
+    transcription_id: Mapped[uuid.UUID] = mapped_column(
+        ForeignKey("transcriptions.id", ondelete="CASCADE")
+    )
+    template_id: Mapped[uuid.UUID] = mapped_column(
+        ForeignKey("prompt_templates.id")
+    )
+    content: Mapped[dict] = mapped_column(JSONB, default=dict)
+    raw_text: Mapped[str] = mapped_column(Text, default="")
+    llm_model: Mapped[str] = mapped_column(String(100))
+    status: Mapped[ProtocolStatus] = mapped_column(
+        Enum(ProtocolStatus), default=ProtocolStatus.generating
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), server_default=func.now(), onupdate=func.now()
+    )
+
+    transcription: Mapped["Transcription"] = relationship(back_populates="protocols")
+    template: Mapped["PromptTemplate"] = relationship(back_populates="protocols")
+    export_files: Mapped[list["ExportFile"]] = relationship(back_populates="protocol")

backend/app/models/recording.py

@@ -0,0 +1,40 @@
+import enum
+import uuid
+
+from sqlalchemy import BigInteger, Enum, ForeignKey, Interval, String
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class RecordingSource(str, enum.Enum):
+    web = "web"
+    telegram = "telegram"
+    lensa = "lensa"
+
+
+class RecordingStatus(str, enum.Enum):
+    uploaded = "uploaded"
+    processing = "processing"
+    done = "done"
+    error = "error"
+
+
+class Recording(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "recordings"
+
+    user_id: Mapped[uuid.UUID] = mapped_column(ForeignKey("users.id"))
+    title: Mapped[str] = mapped_column(String(500))
+    file_path: Mapped[str] = mapped_column(String(1000))
+    file_size: Mapped[int] = mapped_column(BigInteger)
+    duration: Mapped[float | None] = mapped_column(nullable=True)
+    format: Mapped[str] = mapped_column(String(20))
+    source: Mapped[RecordingSource] = mapped_column(Enum(RecordingSource))
+    status: Mapped[RecordingStatus] = mapped_column(
+        Enum(RecordingStatus), default=RecordingStatus.uploaded
+    )
+
+    user: Mapped["User"] = relationship(back_populates="recordings")
+    transcription: Mapped["Transcription | None"] = relationship(
+        back_populates="recording", uselist=False
+    )

backend/app/models/transcription.py

@@ -0,0 +1,23 @@
+import uuid
+
+from sqlalchemy import ForeignKey, Interval, String, Text
+from sqlalchemy.dialects.postgresql import JSONB
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class Transcription(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "transcriptions"
+
+    recording_id: Mapped[uuid.UUID] = mapped_column(
+        ForeignKey("recordings.id", ondelete="CASCADE"), unique=True
+    )
+    text: Mapped[str] = mapped_column(Text)
+    segments: Mapped[dict] = mapped_column(JSONB, default=list)
+    language: Mapped[str | None] = mapped_column(String(10), nullable=True)
+    whisper_model: Mapped[str] = mapped_column(String(50))
+    processing_time: Mapped[float | None] = mapped_column(nullable=True)
+
+    recording: Mapped["Recording"] = relationship(back_populates="transcription")
+    protocols: Mapped[list["Protocol"]] = relationship(back_populates="transcription")

backend/app/models/user.py

@@ -0,0 +1,25 @@
+import enum
+
+from sqlalchemy import Boolean, Enum, String
+from sqlalchemy.orm import Mapped, mapped_column, relationship
+
+from app.models.base import Base, TimestampMixin, UUIDMixin
+
+
+class UserRole(str, enum.Enum):
+    admin = "admin"
+    user = "user"
+
+
+class User(UUIDMixin, TimestampMixin, Base):
+    __tablename__ = "users"
+
+    username: Mapped[str] = mapped_column(String(150), unique=True, index=True)
+    email: Mapped[str] = mapped_column(String(255), unique=True, index=True)
+    password_hash: Mapped[str] = mapped_column(String(255))
+    role: Mapped[UserRole] = mapped_column(
+        Enum(UserRole), default=UserRole.user
+    )
+    is_active: Mapped[bool] = mapped_column(Boolean, default=True)
+
+    recordings: Mapped[list["Recording"]] = relationship(back_populates="user")