diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
new file mode 100644
index 0000000..2f54cd4
--- /dev/null
+++ b/.github/workflows/test.yml
@@ -0,0 +1,43 @@
+name: Backend Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: "3.11"
+
+    - name: Install Dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r backend/requirements.txt
+
+    - name: Run Schema Migrations and Tests
+      env:
+        ENV_FILE: ".env"
+        PYTHONPATH: "backend"
+        DATABASE_URL: ${{ secrets.TEST_DATABASE_URL }}
+        SUPABASE_URL: ${{ secrets.TEST_SUPABASE_URL }}
+        SUPABASE_KEY: ${{ secrets.TEST_SUPABASE_KEY }}
+        SUPABASE_JWT_SECRET: ${{ secrets.TEST_SUPABASE_JWT_SECRET }}
+        # Default mock values for other keys
+        HF_API_URL: "https://router.huggingface.co/hf-inference/models/sentence-transformers/all-MiniLM-L6-v2/pipeline/feature-extraction"
+        HF_API_KEY: "mock"
+        LLM_API_URL: "https://api.groq.com/openai/v1/chat/completions"
+        LLM_API_KEY: "mock"
+        LLM_MODEL: "mock"
+      run: |
+        cd backend
+        export PYTHONPATH=$PYTHONPATH:.
+        alembic upgrade head
+        pytest app/tests/
diff --git a/backend/.gitignore b/backend/.gitignore
index 1541da5..cf50bd5 100644
--- a/backend/.gitignore
+++ b/backend/.gitignore
@@ -1,2 +1,8 @@
 __pycache__/
-.env
\ No newline at end of file
+.env
+.env.dev
+.venv/
+venv/
+.pytest_cache/
+*.pyc
+.DS_Store
diff --git a/backend/Dockerfile b/backend/Dockerfile
index 0ea938d..88994d2 100644
--- a/backend/Dockerfile
+++ b/backend/Dockerfile
@@ -15,8 +15,10 @@ COPY requirements.txt .
 RUN pip install --no-cache-dir --upgrade pip \
     && pip install --no-cache-dir -r requirements.txt
 
-COPY . .
+# Copy start script
+COPY start.sh .
+RUN chmod +x start.sh
 
 EXPOSE 8000
 
-CMD uvicorn app.main:app --host 0.0.0.0 --port ${PORT:-8000} --proxy-headers
+CMD ["./start.sh"]
diff --git a/backend/alembic.ini b/backend/alembic.ini
new file mode 100644
index 0000000..807ded2
--- /dev/null
+++ b/backend/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/alembic
+
+# 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
diff --git a/backend/alembic/README b/backend/alembic/README
new file mode 100644
index 0000000..98e4f9c
--- /dev/null
+++ b/backend/alembic/README
@@ -0,0 +1 @@
+Generic single-database configuration.
\ No newline at end of file
diff --git a/backend/alembic/env.py b/backend/alembic/env.py
new file mode 100644
index 0000000..45da8f3
--- /dev/null
+++ b/backend/alembic/env.py
@@ -0,0 +1,58 @@
+import os
+import sys
+from logging.config import fileConfig
+
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+
+from alembic import context
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from app.core.config import settings
+from app.db.database import Base
+import app.models
+
+config = context.config
+
+config.set_main_option("sqlalchemy.url", settings.DATABASE_URL)
+
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+target_metadata = Base.metadata
+
+
+def run_migrations_offline() -> None:
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()
diff --git a/backend/alembic/script.py.mako b/backend/alembic/script.py.mako
new file mode 100644
index 0000000..1101630
--- /dev/null
+++ b/backend/alembic/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"}
diff --git a/backend/alembic/versions/af24fc97a432_initial_migration.py b/backend/alembic/versions/af24fc97a432_initial_migration.py
new file mode 100644
index 0000000..043890f
--- /dev/null
+++ b/backend/alembic/versions/af24fc97a432_initial_migration.py
@@ -0,0 +1,79 @@
+"""Initial migration
+
+Revision ID: af24fc97a432
+Revises:
+Create Date: 2026-03-19 10:47:49.482533
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import pgvector.sqlalchemy
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'af24fc97a432'
+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('users',
+    sa.Column('id', sa.UUID(), nullable=False),
+    sa.Column('supabase_id', sa.String(), nullable=True),
+    sa.Column('name', sa.String(), nullable=False),
+    sa.Column('email', sa.String(), nullable=False),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('email'),
+    sa.UniqueConstraint('id')
+    )
+    op.create_index(op.f('ix_users_supabase_id'), 'users', ['supabase_id'], unique=True)
+    op.create_table('documents',
+    sa.Column('id', sa.UUID(), nullable=False),
+    sa.Column('user_id', sa.UUID(), nullable=False),
+    sa.Column('filename', sa.String(), nullable=False),
+    sa.Column('file_url', sa.String(), nullable=False),
+    sa.Column('pages', sa.Integer(), nullable=True),
+    sa.Column('created_at', sa.DateTime(timezone=True), server_default=sa.text('now()'), nullable=False),
+    sa.Column('status', sa.Enum('processing', 'ready', 'failed', name='documentstatus'), nullable=False),
+    sa.ForeignKeyConstraint(['user_id'], ['users.id'], ),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('id')
+    )
+    op.create_index('ix_documents_user_id', 'documents', ['user_id'], unique=False)
+    op.create_table('chunks',
+    sa.Column('id', sa.UUID(), nullable=False),
+    sa.Column('document_id', sa.UUID(), nullable=False),
+    sa.Column('chunk_index', sa.Integer(), nullable=False),
+    sa.Column('text', sa.Text(), nullable=False),
+    sa.ForeignKeyConstraint(['document_id'], ['documents.id'], ),
+    sa.PrimaryKeyConstraint('id'),
+    sa.UniqueConstraint('id')
+    )
+    op.create_index('ix_chunks_document_id', 'chunks', ['document_id'], unique=False)
+    op.create_table('embeddings',
+    sa.Column('chunk_id', sa.UUID(), nullable=False),
+    sa.Column('vector', pgvector.sqlalchemy.vector.VECTOR(dim=384), nullable=False),
+    sa.ForeignKeyConstraint(['chunk_id'], ['chunks.id'], ),
+    sa.PrimaryKeyConstraint('chunk_id')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('embeddings')
+    op.drop_index('ix_chunks_document_id', table_name='chunks')
+    op.drop_table('chunks')
+    op.drop_index('ix_documents_user_id', table_name='documents')
+    op.drop_table('documents')
+    op.drop_index(op.f('ix_users_supabase_id'), table_name='users')
+    op.drop_table('users')
+    # ### end Alembic commands ###
diff --git a/backend/app/core/config.py b/backend/app/core/config.py
index 8f35890..d761034 100644
--- a/backend/app/core/config.py
+++ b/backend/app/core/config.py
@@ -1,3 +1,4 @@
+import os
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 class Settings(BaseSettings):
@@ -17,9 +18,10 @@ class Settings(BaseSettings):
   ALLOWED_ORIGINS: str = "http://localhost:5173,http://localhost:5174"
 
   model_config = SettingsConfigDict(
-      env_file=".env",
+      env_file=os.getenv("ENV_FILE", ".env"),
       env_file_encoding='utf-8',
-      case_sensitive=True
+      case_sensitive=True,
+      extra='ignore'
     )
 
 settings = Settings()
diff --git a/backend/app/db/init_db.py b/backend/app/db/init_db.py
deleted file mode 100644
index 21f76d4..0000000
--- a/backend/app/db/init_db.py
+++ /dev/null
@@ -1,15 +0,0 @@
-from app.db.database import Base, engine
-from app.models.user import User
-from app.models.chunk import Chunk
-from app.models.document import Document
-from app.models.embedding import Embedding
-
-
-def init_db():
-  print("Creating Tables...")
-  Base.metadata.create_all(bind=engine)
-  print("Database successfully initialized.")
-
-
-if __name__ == "__main__":
-  init_db()
diff --git a/backend/app/tests/conftest.py b/backend/app/tests/conftest.py
new file mode 100644
index 0000000..2a1cc50
--- /dev/null
+++ b/backend/app/tests/conftest.py
@@ -0,0 +1,36 @@
+import pytest
+from fastapi.testclient import TestClient
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+
+from app.main import app
+from app.core.config import settings
+from app.db.database import get_db
+
+# The settings.DATABASE_URL will be populated by `.env.dev` natively if
+# ENV_FILE is specified during test run, or standard `.env` otherwise.
+engine = create_engine(settings.DATABASE_URL)
+TestingSessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
+
+def override_get_db():
+    try:
+        db = TestingSessionLocal()
+        yield db
+    finally:
+        db.close()
+
+app.dependency_overrides[get_db] = override_get_db
+
+@pytest.fixture(scope="module")
+def client():
+    with TestClient(app) as c:
+        yield c
+
+@pytest.fixture(scope="module")
+def db_session():
+    """Provides a database session for testing."""
+    session = TestingSessionLocal()
+    try:
+        yield session
+    finally:
+        session.close()
diff --git a/backend/app/tests/test_main.py b/backend/app/tests/test_main.py
new file mode 100644
index 0000000..23ba6dc
--- /dev/null
+++ b/backend/app/tests/test_main.py
@@ -0,0 +1,12 @@
+from fastapi.testclient import TestClient
+from app.main import app
+
+client = TestClient(app)
+
+def test_health_check():
+    """
+    Test the health check endpoint to ensure the API is running.
+    """
+    response = client.get("/")
+    assert response.status_code == 200
+    assert response.json() == {"message": "Easy study running"}
diff --git a/backend/requirements.txt b/backend/requirements.txt
index 1dfe14a..6c1bb2e 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -1,7 +1,9 @@
+alembic==1.18.4
 annotated-doc==0.0.4
 annotated-types==0.7.0
 anyio==4.12.1
 bcrypt==5.0.0
+cachetools==6.2.6
 certifi==2026.1.4
 cffi==2.0.0
 charset-normalizer==3.4.4
@@ -11,6 +13,7 @@ cryptography==46.0.4
 deprecation==2.1.0
 ecdsa==0.19.1
 fastapi==0.128.0
+fsspec==2026.2.0
 google-auth==2.48.0
 google-auth-oauthlib==1.2.4
 greenlet==3.3.1
@@ -21,7 +24,13 @@ httpcore==1.0.9
 httpx==0.28.1
 hyperframe==6.1.0
 idna==3.11
+iniconfig==2.3.0
 lxml==6.0.2
+Mako==1.3.10
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+mdurl==0.1.2
+mmh3==5.2.0
 multidict==6.7.1
 numpy==2.4.2
 oauthlib==3.3.1
@@ -29,6 +38,7 @@ packaging==26.0
 passlib==1.7.4
 pgvector==0.4.2
 pillow==12.1.0
+pluggy==1.6.0
 postgrest==2.27.3
 propcache==0.4.1
 psycopg2-binary==2.9.11
@@ -38,9 +48,15 @@ pycparser==3.0
 pydantic==2.12.5
 pydantic-settings==2.12.0
 pydantic_core==2.41.5
+Pygments==2.19.2
+pyiceberg==0.10.0
 PyJWT==2.11.0
 PyMuPDF==1.26.7
+pyparsing==3.3.2
 pypdf==6.7.0
+pyroaring==1.0.3
+pytest==9.0.2
+python-dateutil==2.9.0.post0
 python-dotenv==1.2.1
 python-jose==3.5.0
 python-multipart==0.0.22
@@ -48,15 +64,20 @@ python-pptx==1.0.2
 realtime==2.27.3
 requests==2.32.5
 requests-oauthlib==2.0.0
+rich==14.3.2
 rsa==4.9.1
 setuptools==82.0.0
 six==1.17.0
+sortedcontainers==2.4.0
 SQLAlchemy==2.0.46
 starlette==0.50.0
+storage3==2.27.3
 StrEnum==0.4.15
+strictyaml==1.7.3
 supabase==2.27.3
 supabase-auth==2.27.3
 supabase-functions==2.27.3
+tenacity==9.1.4
 typing-inspection==0.4.2
 typing_extensions==4.15.0
 urllib3==2.6.3
diff --git a/backend/start.sh b/backend/start.sh
new file mode 100644
index 0000000..7be84f9
--- /dev/null
+++ b/backend/start.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+# Run migrations
+echo "Running database migrations..."
+alembic upgrade head
+
+# Start the application
+echo "Starting FastAPI server..."
+exec uvicorn app.main:app --host 0.0.0.0 --port ${PORT:-8000} --proxy-headers