Add ChromaDB as a persistent Docker service

.docker/docker-compose.prod.yml

@@ -15,6 +15,7 @@ services:
     - CACHE_HEADER_TIME=0
     - CACHE_TIME=0
     - db_table=us_code_2025
+    - CHROMA_HOST=congress_chromadb
     restart: unless-stopped
   congress_viewer_app:
     volumes:
@@ -27,6 +28,8 @@ services:
     restart: unless-stopped
   congress_postgres:
     image: tianon/true
+  congress_chromadb:
+    restart: unless-stopped
 networks:
   parser:
     external:

.docker/docker-compose.yml

@@ -39,6 +39,7 @@ services:
     - db_user=parser
     - db_pass=parser
     - db_table=us_code_2025
+    - CHROMA_HOST=congress_chromadb
     build:
       context: ../backend
       dockerfile: .docker/Dockerfile
@@ -48,6 +49,7 @@ services:
     - "9091:8080"
     depends_on:
       - congress_postgres
+      - congress_chromadb
     networks:
       parser:
     entrypoint: "uvicorn"
@@ -85,13 +87,16 @@ services:
     container_name: congress_hillstack
     tty: true
     stdin_open: true
+    environment:
+    - FASTAPI_URL=http://congress_parser_fastapi:8080
     build:
       context: ../hillstack
       dockerfile: .docker/Dockerfile
     ports:
     - "3001:3001"
     depends_on:
       - congress_postgres
+      - congress_parser_fastapi
     networks:
       parser:
   congress_postgres:
@@ -107,9 +112,28 @@ services:
       - postgres-volume:/var/lib/postgresql/data
     networks:
       parser:
+  congress_chromadb:
+    image: chromadb/chroma:0.6.3
+    container_name: congress_chromadb
+    environment:
+      - IS_PERSISTENT=TRUE
+      - PERSIST_DIRECTORY=/chroma/chroma
+      - ANONYMIZED_TELEMETRY=False
+    volumes:
+      - chromadb-volume:/chroma/chroma
+    ports:
+      - "8000:8000"
+    networks:
+      parser:
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/api/v1/heartbeat"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
 networks:
   parser:
     external:
       name: docker_parser
 volumes:
   postgres-volume:
+  chromadb-volume:

backend/.alembic/versions/a1b2c3d4e5f6_add_user_interest.py

@@ -0,0 +1,107 @@
+"""Add user_interest and user_interest_usc_content tables
+
+Revision ID: a1b2c3d4e5f6
+Revises: c9d7e37be069
+Create Date: 2026-02-26 00:00:00.000000
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'a1b2c3d4e5f6'
+down_revision: Union[str, None] = 'c9d7e37be069'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        'user_interest',
+        sa.Column('user_interest_id', sa.Integer(), nullable=False),
+        sa.Column('user_id', sa.String(), nullable=True),
+        sa.Column('interest_text', sa.String(), nullable=True),
+        sa.Column(
+            'created_at',
+            sa.DateTime(),
+            server_default=sa.text('now()'),
+            nullable=True,
+        ),
+        sa.Column(
+            'updated_at',
+            sa.DateTime(),
+            server_default=sa.text('now()'),
+            nullable=True,
+        ),
+        sa.ForeignKeyConstraint(
+            ['user_id'],
+            ['sensitive.user_ident.user_id'],
+            ondelete='CASCADE',
+        ),
+        sa.PrimaryKeyConstraint('user_interest_id'),
+        schema='sensitive',
+    )
+    op.create_index(
+        'ix_sensitive_user_interest_user_id',
+        'user_interest',
+        ['user_id'],
+        schema='sensitive',
+    )
+
+    op.create_table(
+        'user_interest_usc_content',
+        sa.Column('user_interest_usc_content_id', sa.Integer(), nullable=False),
+        sa.Column('user_interest_id', sa.Integer(), nullable=True),
+        sa.Column('usc_ident', sa.String(), nullable=True),
+        sa.Column('match_source', sa.String(), nullable=True),
+        sa.Column('is_active', sa.Boolean(), nullable=True, server_default=sa.text('true')),
+        sa.Column('match_rank', sa.Integer(), nullable=True),
+        sa.Column(
+            'created_at',
+            sa.DateTime(),
+            server_default=sa.text('now()'),
+            nullable=True,
+        ),
+        sa.ForeignKeyConstraint(
+            ['user_interest_id'],
+            ['sensitive.user_interest.user_interest_id'],
+            ondelete='CASCADE',
+        ),
+        sa.PrimaryKeyConstraint('user_interest_usc_content_id'),
+        schema='sensitive',
+    )
+    op.create_index(
+        'ix_sensitive_user_interest_usc_content_user_interest_id',
+        'user_interest_usc_content',
+        ['user_interest_id'],
+        schema='sensitive',
+    )
+    op.create_index(
+        'ix_sensitive_user_interest_usc_content_usc_ident',
+        'user_interest_usc_content',
+        ['usc_ident'],
+        schema='sensitive',
+    )
+
+
+def downgrade() -> None:
+    op.drop_index(
+        'ix_sensitive_user_interest_usc_content_usc_ident',
+        table_name='user_interest_usc_content',
+        schema='sensitive',
+    )
+    op.drop_index(
+        'ix_sensitive_user_interest_usc_content_user_interest_id',
+        table_name='user_interest_usc_content',
+        schema='sensitive',
+    )
+    op.drop_table('user_interest_usc_content', schema='sensitive')
+    op.drop_index(
+        'ix_sensitive_user_interest_user_id',
+        table_name='user_interest',
+        schema='sensitive',
+    )
+    op.drop_table('user_interest', schema='sensitive')

backend/congress_db/models.py

@@ -321,6 +321,49 @@ class UserUSCContent(SensitiveBase):
     usc_ident = Column(String)
 
 
+class UserInterest(SensitiveBase):
+    """
+    Natural language interest statement for a user, used to auto-match USC sections
+    """
+
+    __tablename__ = "user_interest"
+
+    user_interest_id = Column(Integer, primary_key=True)
+
+    user_id = Column(
+        String,
+        ForeignKey("sensitive.user_ident.user_id", ondelete="CASCADE"),
+        index=True,
+    )
+    interest_text = Column(String)
+    created_at = Column(DateTime, server_default=func.now())
+    updated_at = Column(DateTime, server_default=func.now(), onupdate=func.now())
+
+
+class UserInterestUscContent(SensitiveBase):
+    """
+    USC content sections matched to a user's interest, either automatically or manually
+    """
+
+    __tablename__ = "user_interest_usc_content"
+
+    user_interest_usc_content_id = Column(Integer, primary_key=True)
+
+    user_interest_id = Column(
+        Integer,
+        ForeignKey(
+            "sensitive.user_interest.user_interest_id",
+            ondelete="CASCADE",
+        ),
+        index=True,
+    )
+    usc_ident = Column(String, index=True)
+    match_source = Column(String, default="auto")  # 'auto' or 'manual'
+    is_active = Column(Boolean, default=True)
+    match_rank = Column(Integer, nullable=True)
+    created_at = Column(DateTime, server_default=func.now())
+
+
 class UserLLMQuery(SensitiveBase):
     """
     Acts as a log of all user queries into legislation, for tracking purposes