From 16006be43d6e90d1e44e58bfaf0ee19241339c93 Mon Sep 17 00:00:00 2001
From: Vineeth Voruganti <13438633+VVoruganti@users.noreply.github.com>
Date: Thu, 12 Dec 2024 14:23:33 -0500
Subject: [PATCH] feat: Add alembic and indexes

---
 CHANGELOG.md                                  |   5 +
 alembic.ini                                   | 117 ++++++++++++++++++
 migrations/README                             |   1 +
 migrations/env.py                             |  95 ++++++++++++++
 migrations/script.py.mako                     |  26 ++++
 ...28084f472_add_indexes_for_messages_and_.py |  60 +++++++++
 pyproject.toml                                |   1 +
 src/agent.py                                  |   2 +-
 src/db.py                                     |  14 +--
 uv.lock                                       |  28 +++++
 10 files changed, 339 insertions(+), 10 deletions(-)
 create mode 100644 alembic.ini
 create mode 100644 migrations/README
 create mode 100644 migrations/env.py
 create mode 100644 migrations/script.py.mako
 create mode 100644 migrations/versions/c3828084f472_add_indexes_for_messages_and_.py

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 0236b80..8986711 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,11 @@ and this project adheres to [Semantic Versioning](http://semver.org/).
 
 ## [0.0.15]
 
+### Added
+
+- Alembic for handling database migrations
+- Additional indexes for reading Messages and Metamessages
+
 ### Fixed
 
 - Dialectic Streaming Endpoint properly sends text in `StreamingResponse`
diff --git a/alembic.ini b/alembic.ini
new file mode 100644
index 0000000..421e3fe
--- /dev/null
+++ b/alembic.ini
@@ -0,0 +1,117 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+# Use forward slashes (/) also on windows to provide an os agnostic path
+script_location = migrations
+
+# 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
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python>=3.9 or backports.zoneinfo library.
+# Any required deps can 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 migrations/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 "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+# version_path_separator = newline
+version_path_separator = os  # Use os.pathsep. Default configuration used for new projects.
+
+# 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
+
+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 exec runner, execute a binary
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = %(here)s/.venv/bin/ruff
+# ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[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/migrations/README b/migrations/README
new file mode 100644
index 0000000..98e4f9c
--- /dev/null
+++ b/migrations/README
@@ -0,0 +1 @@
+Generic single-database configuration.
\ No newline at end of file
diff --git a/migrations/env.py b/migrations/env.py
new file mode 100644
index 0000000..4dc2e25
--- /dev/null
+++ b/migrations/env.py
@@ -0,0 +1,95 @@
+import os
+import sys
+from logging.config import fileConfig
+from pathlib import Path
+
+from alembic import context
+from dotenv import load_dotenv
+from sqlalchemy import engine_from_config, pool
+
+# Import your models
+from src.db import Base
+
+# Add project root to Python path
+sys.path.append(str(Path(__file__).parents[1]))
+
+# Load environment variables
+load_dotenv()
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name, disable_existing_loggers=False)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+target_metadata = Base.metadata
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def get_url():
+    return os.getenv("CONNECTION_URI")
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    # url = config.get_main_option("sqlalchemy.url")
+    url = get_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:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    configuration = config.get_section(config.config_ini_section)
+    configuration["sqlalchemy.url"] = get_url()
+
+    connectable = engine_from_config(
+        configuration,
+        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/migrations/script.py.mako b/migrations/script.py.mako
new file mode 100644
index 0000000..fbc4b07
--- /dev/null
+++ b/migrations/script.py.mako
@@ -0,0 +1,26 @@
+"""${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, 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:
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    ${downgrades if downgrades else "pass"}
diff --git a/migrations/versions/c3828084f472_add_indexes_for_messages_and_.py b/migrations/versions/c3828084f472_add_indexes_for_messages_and_.py
new file mode 100644
index 0000000..96fded4
--- /dev/null
+++ b/migrations/versions/c3828084f472_add_indexes_for_messages_and_.py
@@ -0,0 +1,60 @@
+"""Add indexes for messages and metamessages for reads
+
+Revision ID: c3828084f472
+Revises:
+Create Date: 2024-12-12 13:41:40.156095
+
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+from sqlalchemy import text
+from alembic import op
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = "c3828084f472"
+down_revision: Union[str, None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # Add new indexes
+    op.create_index("idx_users_app_lookup", "users", ["app_id", "public_id"])
+    op.create_index("idx_sessions_user_lookup", "sessions", ["user_id", "public_id"])
+
+    op.create_index(
+        "idx_messages_session_lookup",
+        "messages",
+        ["session_id", "id"],
+        postgresql_include=[
+            "public_id",
+            "is_user",
+            "content",
+            "metadata",
+            "created_at",
+        ],
+    )
+
+    op.create_index(
+        "idx_metamessages_lookup",
+        "metamessages",
+        ["metamessage_type", sa.text("id DESC")],
+        postgresql_include=[
+            "public_id",
+            "content",
+            "message_id",
+            "created_at",
+            "metadata",
+        ],
+    )
+
+
+def downgrade() -> None:
+    # Remove new indexes
+    op.drop_index("idx_users_app_lookup", table_name="users")
+    op.drop_index("idx_sessions_user_lookup", table_name="sessions")
+    op.drop_index("idx_messages_session_lookup", table_name="messages")
+    op.drop_index("idx_metamessages_lookup", table_name="metamessages")
diff --git a/pyproject.toml b/pyproject.toml
index bd55c5d..5569074 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -21,6 +21,7 @@ dependencies = [
     "openai>=1.43.0",
     "anthropic>=0.36.0",
     "nanoid>=2.0.0",
+    "alembic>=1.14.0",
 ]
 [tool.uv]
 dev-dependencies = [
diff --git a/src/agent.py b/src/agent.py
index 90cc4c5..b01dd14 100644
--- a/src/agent.py
+++ b/src/agent.py
@@ -77,7 +77,7 @@ def stream(self):
             Provide a brief, matter-of-fact, and appropriate response to the query based on the context provided. If the context provided doesn't aid in addressing the query, return only the word "None". 
             """
             return self.client.messages.stream(
-                model="claude-3-5-sonnet-20240620",
+                model="claude-3-5-sonnet-20241022",
                 messages=[
                     {
                         "role": "user",
diff --git a/src/db.py b/src/db.py
index 2066921..aa5f91a 100644
--- a/src/db.py
+++ b/src/db.py
@@ -1,7 +1,9 @@
 import os
 
+from alembic import command
+from alembic.config import Config
 from dotenv import load_dotenv
-from sqlalchemy import MetaData, create_engine
+from sqlalchemy import MetaData
 from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine
 from sqlalchemy.orm import declarative_base
 
@@ -43,11 +45,5 @@ def scaffold_db():
     """use a sync engine for scaffolding the database. ddl operations are unavailable
     with async engines
     """
-    print(os.environ["CONNECTION_URI"])
-    engine = create_engine(
-        os.environ["CONNECTION_URI"],
-        pool_pre_ping=True,
-        echo=True,
-    )
-    Base.metadata.create_all(bind=engine)
-    engine.dispose()
+    alembic_cfg = Config("alembic.ini")
+    command.upgrade(alembic_cfg, "head")
diff --git a/uv.lock b/uv.lock
index 765af8c..626f838 100644
--- a/uv.lock
+++ b/uv.lock
@@ -5,6 +5,20 @@ resolution-markers = [
     "python_full_version >= '3.13'",
 ]
 
+[[package]]
+name = "alembic"
+version = "1.14.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "mako" },
+    { name = "sqlalchemy" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/00/1e/8cb8900ba1b6360431e46fb7a89922916d3a1b017a8908a7c0499cc7e5f6/alembic-1.14.0.tar.gz", hash = "sha256:b00892b53b3642d0b8dbedba234dbf1924b69be83a9a769d5a624b01094e304b", size = 1916172 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/cb/06/8b505aea3d77021b18dcbd8133aa1418f1a1e37e432a465b14c46b2c0eaa/alembic-1.14.0-py3-none-any.whl", hash = "sha256:99bd884ca390466db5e27ffccff1d179ec5c05c965cfefc0607e69f9e411cb25", size = 233482 },
+]
+
 [[package]]
 name = "annotated-types"
 version = "0.7.0"
@@ -428,6 +442,7 @@ name = "honcho"
 version = "0.0.15"
 source = { virtual = "." }
 dependencies = [
+    { name = "alembic" },
     { name = "anthropic" },
     { name = "fastapi", extra = ["standard"] },
     { name = "fastapi-pagination" },
@@ -455,6 +470,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
+    { name = "alembic", specifier = ">=1.14.0" },
     { name = "anthropic", specifier = ">=0.36.0" },
     { name = "fastapi", extras = ["standard"], specifier = ">=0.111.0" },
     { name = "fastapi-pagination", specifier = ">=0.12.24" },
@@ -685,6 +701,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b4/ee/6d9873144f860391fd1130be0e1e5a1dbd7e9d128da1c7baf1ae71babb99/jiter-0.6.1-cp39-none-win_amd64.whl", hash = "sha256:d465db62d2d10b489b7e7a33027c4ae3a64374425d757e963f86df5b5f2e7fc5", size = 202278 },
 ]
 
+[[package]]
+name = "mako"
+version = "1.3.8"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "markupsafe" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5f/d9/8518279534ed7dace1795d5a47e49d5299dd0994eed1053996402a8902f9/mako-1.3.8.tar.gz", hash = "sha256:577b97e414580d3e088d47c2dbbe9594aa7a5146ed2875d4dfa9075af2dd3cc8", size = 392069 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/bf/7a6a36ce2e4cafdfb202752be68850e22607fccd692847c45c1ae3c17ba6/Mako-1.3.8-py3-none-any.whl", hash = "sha256:42f48953c7eb91332040ff567eb7eea69b22e7a4affbc5ba8e845e8f730f6627", size = 78569 },
+]
+
 [[package]]
 name = "markdown-it-py"
 version = "3.0.0"