welearn-database 1.3.0.dev2__tar.gz → 1.4.0.dev0__tar.gz

{welearn_database-1.3.0.dev2 → welearn_database-1.4.0.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: welearn-database
-Version: 1.3.0.dev2
+Version: 1.4.0.dev0
 Summary: All stuff related to relationnal database from the WeLearn project
 License: cc-by-sa-nc
 Author: Théo

{welearn_database-1.3.0.dev2 → welearn_database-1.4.0.dev0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "welearn-database"
-version = "1.3.0.dev2"
+version = "1.4.0.dev0"
 description = "All stuff related to relationnal database from the WeLearn project"
 authors = [
     {name = "Théo",email = "theo.nardin@cri-paris.org"}

{welearn_database-1.3.0.dev2 → welearn_database-1.4.0.dev0}/welearn_database/alembic/env.py

@@ -1,3 +1,4 @@
+import os
 from logging.config import fileConfig
 
 from alembic import context
@@ -75,6 +76,14 @@ def run_migrations_online() -> None:
     load_dotenv()
     connectable = create_sqlalchemy_engine()
 
+    if "prod" in os.getenv("PG_HOST").lower():
+        print("Connecting to production database for migrations!")
+        input("Press Enter to continue...")
+    elif "dev" in os.getenv("PG_HOST" "").lower():
+        print("Connecting to development database for migrations!")
+    else:
+        print("Connecting to unknown database for migrations!")
+
     with connectable.connect() as connection:
         context.configure(
             connection=connection,

welearn_database-1.4.0.dev0/welearn_database/alembic/versions/2ad4895b2674_data_collection.py

@@ -0,0 +1,100 @@
+"""data collection
+
+Revision ID: 2ad4895b2674
+Revises: 068312e7800c
+Create Date: 2026-01-16 15:55:41.447852
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "2ad4895b2674"
+down_revision: Union[str, None] = "068312e7800c"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "data_collection_campaign_management",
+        sa.Column(
+            "id", sa.Uuid(), server_default=sa.func.gen_random_uuid(), nullable=False
+        ),
+        sa.Column("is_active", sa.Boolean(), nullable=False),
+        sa.Column("end_at", postgresql.TIMESTAMP(), nullable=False),
+        sa.Column(
+            "created_at", postgresql.TIMESTAMP(), server_default="NOW()", nullable=False
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        schema="user_related",
+    )
+
+    op.add_column(
+        "chat_message",
+        sa.Column("role", sa.String(), nullable=False),
+        schema="user_related",
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("inferred_user_id", sa.Uuid(), nullable=False),
+        schema="user_related",
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("conversation_id", sa.Uuid(), nullable=False),
+        schema="user_related",
+    )
+    op.drop_constraint(
+        op.f("message_user_id_fkey"),
+        "chat_message",
+        schema="user_related",
+        type_="foreignkey",
+    )
+    op.create_foreign_key(
+        "message_inferred_user_id_fkey",
+        "chat_message",
+        "inferred_user",
+        ["inferred_user_id"],
+        ["id"],
+        source_schema="user_related",
+        referent_schema="user_related",
+    )
+    op.drop_column("chat_message", "user_id", schema="user_related")
+    op.add_column(
+        "returned_document",
+        sa.Column("is_clicked", sa.Boolean(), nullable=False),
+        schema="user_related",
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("returned_document", "is_clicked", schema="user_related")
+    op.add_column(
+        "chat_message",
+        sa.Column("user_id", sa.Uuid(), nullable=False),
+        schema="user_related",
+    )
+    op.drop_constraint(
+        "message_inferred_user_id_fkey",
+        "chat_message",
+        schema="user_related",
+        type_="foreignkey",
+    )
+    op.create_foreign_key(
+        op.f("message_user_id_fkey"),
+        "chat_message",
+        "user_profile",
+        ["user_id"],
+        ["id"],
+        source_schema="user_related",
+        referent_schema="user_related",
+    )
+    op.drop_column("chat_message", "conversation_id", schema="user_related")
+    op.drop_column("chat_message", "inferred_user_id", schema="user_related")
+    op.drop_column("chat_message", "role", schema="user_related")
+    op.drop_table("data_collection_campaign_management", schema="user_related")

welearn_database-1.4.0.dev0/welearn_database/alembic/versions/9b4f1da0c1f2_data_collection_for_focus_group.py

@@ -0,0 +1,76 @@
+"""data collection for focus group
+
+Revision ID: 9b4f1da0c1f2
+Revises: 2ad4895b2674
+Create Date: 2026-02-23 18:11:55.857517
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "9b4f1da0c1f2"
+down_revision: Union[str, None] = "2ad4895b2674"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column(
+        "chat_message",
+        sa.Column(
+            "is_retrieved_by_user",
+            sa.Boolean(),
+            nullable=False,
+            default=False,
+            server_default="False",
+        ),
+        schema="user_related",
+    )
+    op.add_column(
+        "chat_message",
+        sa.Column("original_feature_name", sa.String(), nullable=True),
+        schema="user_related",
+    )
+    op.create_table(
+        "filter_used_in_query",
+        sa.Column(
+            "id", sa.Uuid(), server_default=sa.func.gen_random_uuid(), nullable=False
+        ),
+        sa.Column("message_id", sa.Uuid(), nullable=False),
+        sa.Column(
+            "filter_type",
+            postgresql.ENUM(
+                "sdg",
+                "source",
+                name="filter_type",
+                schema="user_related",
+            ),
+            nullable=False,
+        ),
+        sa.Column("filter_value", sa.String(), nullable=False),
+        sa.ForeignKeyConstraint(
+            ["message_id"],
+            ["user_related.chat_message.id"],
+            name="filter_used_in_query_message_id_fkey",
+        ),
+        sa.PrimaryKeyConstraint("id"),
+        schema="user_related",
+    )
+
+
+def downgrade() -> None:
+    op.drop_column("chat_message", "is_retrieved_by_user", schema="user_related")
+    op.drop_column("chat_message", "original_feature_name", schema="user_related")
+    op.drop_constraint(
+        "filter_used_in_query_message_id_fkey",
+        "filter_used_in_query",
+        schema="user_related",
+        type_="foreignkey",
+    )
+    op.drop_table("filter_used_in_query", schema="user_related")
+    op.execute("DROP TYPE IF EXISTS user_related.filter_type")

{welearn_database-1.3.0.dev2 → welearn_database-1.4.0.dev0}/welearn_database/data/enumeration.py

@@ -38,3 +38,8 @@ class ExternalIdType(StrEnum):
     HANDLE = auto()
     SLUG = auto()
     QID = auto()
+
+
+class FilterType(StrEnum):
+    SDG = auto()
+    SOURCE = auto()

{welearn_database-1.3.0.dev2 → welearn_database-1.4.0.dev0}/welearn_database/data/models/user_related.py

@@ -2,10 +2,10 @@ from datetime import datetime
 from uuid import UUID
 
 from sqlalchemy import ForeignKey, func, types
-from sqlalchemy.dialects.postgresql import TIMESTAMP
+from sqlalchemy.dialects.postgresql import ENUM, TIMESTAMP
 from sqlalchemy.orm import Mapped, mapped_column, relationship
 
-from welearn_database.data.enumeration import DbSchemaEnum
+from welearn_database.data.enumeration import DbSchemaEnum, FilterType
 from welearn_database.data.models.document_related import WeLearnDocument
 
 from . import Base
@@ -90,8 +90,16 @@ class ChatMessage(Base):
         ForeignKey(f"{DbSchemaEnum.USER_RELATED.value}.inferred_user.id"),
         nullable=False,
     )
+    conversation_id = mapped_column(
+        types.Uuid,
+        nullable=False,
+    )
     role: Mapped[str]
     textual_content: Mapped[str]
+    is_retrieved_by_user: Mapped[bool] = mapped_column(
+        default=False, server_default="False"
+    )
+    original_feature_name: Mapped[str | None]
 
     created_at: Mapped[datetime] = mapped_column(
         TIMESTAMP(timezone=False),
@@ -129,6 +137,8 @@ class ReturnedDocument(Base):
         ),
         nullable=False,
     )
+    is_clicked: Mapped[bool] = mapped_column(default=False)
+
     welearn_document: Mapped["WeLearnDocument"] = relationship()
     chat_message: Mapped["ChatMessage"] = relationship()
 
@@ -159,6 +169,23 @@ class APIKeyManagement(Base):
     )
 
 
+class DataCollectionCampaignManagement(Base):
+    __tablename__ = "data_collection_campaign_management"
+    __table_args__ = {"schema": DbSchemaEnum.USER_RELATED.value}
+
+    id: Mapped[UUID] = mapped_column(
+        types.Uuid, primary_key=True, nullable=False, server_default="gen_random_uuid()"
+    )
+    is_active: Mapped[bool]
+    end_at: Mapped[datetime] = mapped_column(TIMESTAMP(timezone=False), nullable=False)
+    created_at: Mapped[datetime] = mapped_column(
+        TIMESTAMP(timezone=False),
+        nullable=False,
+        default=func.localtimestamp(),
+        server_default="NOW()",
+    )
+
+
 class Session(Base):
     __tablename__ = "session"
     __table_args__ = {"schema": "user_related"}
@@ -218,3 +245,27 @@ class EndpointRequest(Base):
         server_default="NOW()",
     )
     session = relationship("Session", foreign_keys=[session_id])
+
+
+class FilterUsedInQuery(Base):
+    __tablename__ = "filter_used_in_query"
+    __table_args__ = {"schema": DbSchemaEnum.USER_RELATED.value}
+
+    id: Mapped[UUID] = mapped_column(
+        types.Uuid, primary_key=True, nullable=False, server_default="gen_random_uuid()"
+    )
+    message_id = mapped_column(
+        types.Uuid,
+        ForeignKey(f"{DbSchemaEnum.USER_RELATED.value}.chat_message.id"),
+        nullable=False,
+    )
+    filter_type: Mapped[str] = mapped_column(
+        ENUM(
+            *(e.value.lower() for e in FilterType),
+            name="filter_type",
+            schema=DbSchemaEnum.USER_RELATED.value,
+        ),
+    )
+    filter_value: Mapped[str]
+
+    chat_message: Mapped["ChatMessage"] = relationship()