feat: add PostgreSQL schema and Alembic migrations

alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/versioning_bdd
+
+# 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
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be 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 <script_location>/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 "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# 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
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[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 module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+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

database.py

@@ -1,22 +1,31 @@
 import os
+from collections.abc import Generator
 
 from dotenv import load_dotenv
 from sqlalchemy import create_engine, text
+from sqlalchemy.orm import Session, declarative_base, sessionmaker
 
+
+# Charge les variables du fichier .env en développement local.
+# Sur Hugging Face Spaces, DATABASE_URL provient directement des secrets.
 load_dotenv()
 
+
 database_url = os.getenv("DATABASE_URL")
 
 if not database_url:
     raise RuntimeError("La variable DATABASE_URL est absente.")
 
-# SQLAlchemy doit utiliser explicitement le pilote psycopg.
+
+# SQLAlchemy doit utiliser explicitement le pilote Psycopg 3.
 sqlalchemy_database_url = database_url.replace(
     "postgresql://",
     "postgresql+psycopg://",
     1,
 )
 
+
+# Moteur de connexion partagé par l'application et Alembic.
 engine = create_engine(
     sqlalchemy_database_url,
     pool_pre_ping=True,
@@ -25,7 +34,32 @@ engine = create_engine(
 )
 
 
+# Classe de base utilisée par les modèles SQLAlchemy.
+Base = declarative_base()
+
+
+# Fabrique de sessions utilisée par les endpoints FastAPI.
+SessionLocal = sessionmaker(
+    bind=engine,
+    autocommit=False,
+    autoflush=False,
+)
+
+
+def get_db() -> Generator[Session, None, None]:
+    """Fournit une session SQLAlchemy puis la ferme après la requête."""
+
+    database_session = SessionLocal()
+
+    try:
+        yield database_session
+    finally:
+        database_session.close()
+
+
 def check_database_connection() -> bool:
+    """Vérifie que PostgreSQL répond correctement."""
+
     with engine.connect() as connection:
         result = connection.execute(text("SELECT 1"))
         return result.scalar_one() == 1

models.py

@@ -0,0 +1,141 @@
+from datetime import date, datetime, timezone
+
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import (
+    Boolean,
+    Column,
+    Date,
+    ForeignKey,
+    Integer,
+    String,
+    Text,
+    TIMESTAMP,
+    UniqueConstraint,
+    text,
+)
+from sqlalchemy.orm import relationship
+
+from database import Base
+
+
+# Configuration du modèle d'embeddings utilisé par Anderson.
+EMBEDDING_MODEL = "intfloat/multilingual-e5-small"
+EMBEDDING_DIMENSION = 384
+
+
+class Collection(Base):
+    """Collection regroupant plusieurs documents associés au même sujet."""
+
+    __tablename__ = "collections"
+
+    collection_id = Column(Integer, primary_key=True, index=True)
+    name = Column(String(100), nullable=False, unique=True)
+    description = Column(Text, nullable=True)
+    date_de_creation = Column(Date, nullable=False, default=date.today)
+    derniere_modification = Column(
+        TIMESTAMP(timezone=True),
+        nullable=False,
+        default=lambda: datetime.now(timezone.utc),
+        onupdate=lambda: datetime.now(timezone.utc),
+    )
+
+    # Les collections temporaires pourront être supprimées après 24 heures.
+    is_permanent = Column(Boolean, nullable=False, default=False, server_default=text("false"))
+    expires_at = Column(
+        TIMESTAMP(timezone=True),
+        nullable=False,
+        server_default=text("(now() + interval '24 hours')"),
+    )
+
+    # La suppression d'une collection supprime ses documents et leurs chunks.
+    documents = relationship(
+        "Document",
+        back_populates="collection",
+        cascade="all, delete-orphan",
+        passive_deletes=True,
+    )
+
+
+class Document(Base):
+    """Métadonnées d'un fichier uploadé puis découpé en chunks."""
+
+    __tablename__ = "documents"
+
+    # Un même fichier ne peut pas apparaître deux fois dans la même collection.
+    __table_args__ = (
+        UniqueConstraint(
+            "collection_id",
+            "title_document",
+            name="uq_documents_collection_title_document",
+        ),
+    )
+
+    document_id = Column(Integer, primary_key=True, index=True)
+    collection_id = Column(
+        Integer,
+        ForeignKey("collections.collection_id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
+
+    # Titre renseigné par l'utilisateur et nom original du fichier.
+    title = Column(String(100), nullable=False)
+    title_document = Column(String(255), nullable=False)
+
+    # Le fichier original n'est pas conservé, uniquement ses métadonnées.
+    mime_type = Column(String(100), nullable=False)
+    size_bytes = Column(Integer, nullable=False)
+
+    date_de_creation = Column(Date, nullable=False, default=date.today)
+    created_at = Column(
+        TIMESTAMP(timezone=True),
+        nullable=False,
+        default=lambda: datetime.now(timezone.utc),
+    )
+    num_of_chunks = Column(Integer, nullable=False, default=0, server_default=text("0"))
+
+    collection = relationship("Collection", back_populates="documents")
+    chunks = relationship(
+        "Chunk",
+        back_populates="document",
+        cascade="all, delete-orphan",
+        passive_deletes=True,
+    )
+
+
+class Chunk(Base):
+    """Fragment de texte vectorisé utilisé pour la recherche sémantique."""
+
+    __tablename__ = "chunks"
+
+    # La position permet de reconstruire l'ordre original des fragments.
+    __table_args__ = (
+        UniqueConstraint(
+            "document_id",
+            "position",
+            name="uq_chunks_document_position",
+        ),
+    )
+
+    chunk_id = Column(Integer, primary_key=True, index=True)
+    document_id = Column(
+        Integer,
+        ForeignKey("documents.document_id", ondelete="CASCADE"),
+        nullable=False,
+        index=True,
+    )
+
+    position = Column(Integer, nullable=False)
+    chunk_text = Column(Text, nullable=False)
+    taille_chunk = Column(Integer, nullable=False)
+
+    # Un seul modèle léger remplace les trois embeddings de l'ancien projet.
+    embedding = Column(Vector(dim=EMBEDDING_DIMENSION), nullable=False)
+
+    created_at = Column(
+        TIMESTAMP(timezone=True),
+        nullable=False,
+        default=lambda: datetime.now(timezone.utc),
+    )
+
+    document = relationship("Document", back_populates="chunks")

requirements.txt

@@ -1,3 +1,4 @@
+alembic==1.19.1
 annotated-doc==0.0.5
 annotated-types==0.8.0
 anyio==4.14.2
@@ -15,16 +16,42 @@ httptools==0.8.0
 httpx==0.28.1
 huggingface_hub==1.28.0
 idna==3.19
+Jinja2==3.1.6
+joblib==1.5.3
+Mako==1.4.1
+markdown-it-py==4.2.0
+MarkupSafe==3.0.3
+mdurl==0.1.2
+mpmath==1.3.0
+narwhals==2.25.0
+networkx==3.6.1
+numpy==2.5.2
 packaging==26.3
+pgvector==0.5.0
 psycopg==3.3.4
 psycopg-binary==3.3.4
 pydantic==2.13.4
 pydantic_core==2.46.4
+Pygments==2.21.0
 python-dotenv==1.2.3
 PyYAML==6.0.3
+regex==2026.7.19
+rich==15.0.0
+safetensors==0.8.0
+scikit-learn==1.9.0
+scipy==1.18.1
+sentence-transformers==6.0.0
+setuptools==84.0.0
+shellingham==1.5.4
 SQLAlchemy==2.0.52
 starlette==1.6.0
+sympy==1.14.0
+threadpoolctl==3.6.0
+tokenizers==0.22.2
+torch==2.13.0
 tqdm==4.70.0
+transformers==5.15.1
+typer==0.27.1
 typing-inspection==0.4.4
 typing_extensions==4.16.0
 tzdata==2026.3

versioning_bdd/README

@@ -0,0 +1 @@
+Generic single-database configuration.

versioning_bdd/env.py

@@ -0,0 +1,54 @@
+from logging.config import fileConfig
+
+from alembic import context
+
+from database import engine, sqlalchemy_database_url
+from models import Base
+
+
+# Objet de configuration Alembic provenant de alembic.ini.
+config = context.config
+
+
+# Configuration des logs Alembic.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+
+# Métadonnées utilisées pour détecter les changements dans models.py.
+target_metadata = Base.metadata
+
+
+def run_migrations_offline() -> None:
+    """Exécute les migrations sans ouvrir directement de connexion."""
+
+    context.configure(
+        url=sqlalchemy_database_url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+        compare_type=True,
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Exécute les migrations en utilisant le moteur SQLAlchemy."""
+
+    with engine.connect() as connection:
+        context.configure(
+            connection=connection,
+            target_metadata=target_metadata,
+            compare_type=True,
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

versioning_bdd/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[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 upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

versioning_bdd/versions/2d45c40205b1_create_initial_anderson_schema.py

@@ -0,0 +1,82 @@
+"""create initial Anderson schema
+
+Revision ID: 2d45c40205b1
+Revises: 
+Create Date: 2026-08-23 02:24:03.141963
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from pgvector.sqlalchemy import Vector
+
+
+# revision identifiers, used by Alembic.
+revision: str = '2d45c40205b1'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    op.execute("CREATE EXTENSION IF NOT EXISTS vector")
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('collections',
+    sa.Column('collection_id', sa.Integer(), nullable=False),
+    sa.Column('name', sa.String(length=100), nullable=False),
+    sa.Column('description', sa.Text(), nullable=True),
+    sa.Column('date_de_creation', sa.Date(), nullable=False),
+    sa.Column('derniere_modification', sa.TIMESTAMP(timezone=True), nullable=False),
+    sa.Column('is_permanent', sa.Boolean(), server_default=sa.text('false'), nullable=False),
+    sa.Column('expires_at', sa.TIMESTAMP(timezone=True), server_default=sa.text("(now() + interval '24 hours')"), nullable=False),
+    sa.PrimaryKeyConstraint('collection_id'),
+    sa.UniqueConstraint('name')
+    )
+    op.create_index(op.f('ix_collections_collection_id'), 'collections', ['collection_id'], unique=False)
+    op.create_table('documents',
+    sa.Column('document_id', sa.Integer(), nullable=False),
+    sa.Column('collection_id', sa.Integer(), nullable=False),
+    sa.Column('title', sa.String(length=100), nullable=False),
+    sa.Column('title_document', sa.String(length=255), nullable=False),
+    sa.Column('mime_type', sa.String(length=100), nullable=False),
+    sa.Column('size_bytes', sa.Integer(), nullable=False),
+    sa.Column('date_de_creation', sa.Date(), nullable=False),
+    sa.Column('created_at', sa.TIMESTAMP(timezone=True), nullable=False),
+    sa.Column('num_of_chunks', sa.Integer(), server_default=sa.text('0'), nullable=False),
+    sa.ForeignKeyConstraint(['collection_id'], ['collections.collection_id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('document_id'),
+    sa.UniqueConstraint('collection_id', 'title_document', name='uq_documents_collection_title_document')
+    )
+    op.create_index(op.f('ix_documents_collection_id'), 'documents', ['collection_id'], unique=False)
+    op.create_index(op.f('ix_documents_document_id'), 'documents', ['document_id'], unique=False)
+    op.create_table('chunks',
+    sa.Column('chunk_id', sa.Integer(), nullable=False),
+    sa.Column('document_id', sa.Integer(), nullable=False),
+    sa.Column('position', sa.Integer(), nullable=False),
+    sa.Column('chunk_text', sa.Text(), nullable=False),
+    sa.Column('taille_chunk', sa.Integer(), nullable=False),
+    sa.Column('embedding', Vector(dim=384), nullable=False),
+    sa.Column('created_at', sa.TIMESTAMP(timezone=True), nullable=False),
+    sa.ForeignKeyConstraint(['document_id'], ['documents.document_id'], ondelete='CASCADE'),
+    sa.PrimaryKeyConstraint('chunk_id'),
+    sa.UniqueConstraint('document_id', 'position', name='uq_chunks_document_position')
+    )
+    op.create_index(op.f('ix_chunks_chunk_id'), 'chunks', ['chunk_id'], unique=False)
+    op.create_index(op.f('ix_chunks_document_id'), 'chunks', ['document_id'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_chunks_document_id'), table_name='chunks')
+    op.drop_index(op.f('ix_chunks_chunk_id'), table_name='chunks')
+    op.drop_table('chunks')
+    op.drop_index(op.f('ix_documents_document_id'), table_name='documents')
+    op.drop_index(op.f('ix_documents_collection_id'), table_name='documents')
+    op.drop_table('documents')
+    op.drop_index(op.f('ix_collections_collection_id'), table_name='collections')
+    op.drop_table('collections')
+    # ### end Alembic commands ###