Merge pull request #1 from mobiusml/app_implementation

Migrate chat_with_video Project from Aana SDK

.github/workflows/tests.yml

@@ -0,0 +1,33 @@
+name: Tests
+
+on:
+  push:
+    branches:
+      - '**'  # Runs on push to any branch
+  pull_request:
+    branches:
+      - '**'  # Runs on pull requests to any branch
+  workflow_dispatch:  # Allows for manual triggering
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v3
+    - name: Bootstrap poetry
+      run: |
+        curl -sSL https://install.python-poetry.org | python - -y
+    - name: Update PATH
+      run: echo "$HOME/.local/bin" >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        poetry install
+    - name: Test with pytest
+      run: poetry run pytest -vv

.vscode/settings.json

@@ -0,0 +1,13 @@
+{
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "python.analysis.packageIndexDepths": [
+        {
+            "name": "aana",
+            "depth": 10,
+        }
+    ],
+}

README.md

@@ -1,45 +1,6 @@
-# Aana Application Template
-
-[Aana SDK](https://github.com/mobiusml/aana_sdk) is a powerful framework for building multimodal applications. It facilitates the large-scale deployment of machine learning models, including those for vision, audio, and language, and supports Retrieval-Augmented Generation (RAG) systems. This enables the development of advanced applications such as search engines, recommendation systems, and data insights platforms.
-
-This repository contains a template that you can use to start building your own Aana application. It will help you get started with the Aana SDK and provide you with a basic structure for your application and its dependencies.
-
-## How to use this template
-
-1. Click on [Use this template](https://github.com/mobiusml/aana_app_template/generate).
-2. Give your repository a name and click on "Create repository". The name of the repository will also be the name of your application and the Python package.
-3. Wait for the first workflow to finish. This will rename the package to match the repository name.
-4. Clone the repository to your local machine and start building your application.
-5. Change the [LICENSE](/LICENSE) file to match your project's license. The default license is the Apache License 2.0.
-
-## Getting started
-
-The project template uses [Poetry](https://python-poetry.org/) for dependency management. To install the project, run the following commands:
-
-```bash
-poetry install
-```
-
-See [Tutorial](https://github.com/mobiusml/aana_sdk/blob/main/docs/tutorial.md) for more information on how to build your application.
-
-## Project structure
-
-```
-aana_chat_with_video/
-├── config/                   | various configs, including settings, deployments and endpoints
-│   ├── endpoints.py          | list of endpoints to deploy
-│   ├── deployments.py        | list of deployments (models) to deploy
-│   └── settings.py           | app settings
-├── core/                     | core models and functionality
-│   ├── models/               | data models
-│   └── prompts/              | prompt templates for LLMs
-├── deployments/              | custom deployments
-├── endpoints/                | endpoint classes for the app
-├── exceptions/               | custom exception classes
-├── utils/                    | various utility functionality
-└── app.py                    | main application file
-```
+# Chat with Video App
 
+**Chat with Video App** is a multimodal chat application that allows users to upload a video and ask questions about the video content based on the visual and audio information. See [Chat with Video Demo notebook](notebooks/chat_with_video_demo.ipynb) for more information.
 
 ## Installation
 
@@ -49,16 +10,9 @@ To install the project, follow these steps:
 
 2. Install additional libraries.
 
-```bash
-apt update && apt install -y libgl1
-```
-> **🗒️ Note**
->
-> For optimal performance, you should also install [PyTorch](https://pytorch.org/get-started/locally/) version >=2.1 appropriate for your system. You can continue directly to the next step, but it will install a default version that may not make optimal use of your system's resources, for example, a GPU or even some SIMD operations. Therefore we recommend choosing your PyTorch package carefully and installing it manually.
+For optimal performance, you should also install [PyTorch](https://pytorch.org/get-started/locally/) version >=2.1 appropriate for your system. You can continue directly to the next step, but it will install a default version that may not make optimal use of your system's resources, for example, a GPU or even some SIMD operations. Therefore we recommend choosing your PyTorch package carefully and installing it manually.
 
-> **🗒️ Note**
->
-> Some models use Flash Attention. Install Flash Attention library for better performance. See [flash attention installation instructions](https://github.com/Dao-AILab/flash-attention?tab=readme-ov-file#installation-and-features) for more details and supported GPUs.
+Some models use Flash Attention. Install Flash Attention library for better performance. See [flash attention installation instructions](https://github.com/Dao-AILab/flash-attention?tab=readme-ov-file#installation-and-features) for more details and supported GPUs.
 
 3. Install the package with poetry.
 
@@ -73,7 +27,7 @@ poetry install
 4. Run the app.
 
 ```bash
-aana deploy aana_chat_with_video.app:aana_app
+CUDA_VISIBLE_DEVICES="0" aana deploy aana_chat_with_video.app:aana_app
 ```
 
 ## Usage
@@ -83,14 +37,14 @@ To use the project, follow these steps:
 1. Run the app as described in the installation section.
 
 ```bash
-aana deploy aana_chat_with_video.app:aana_app
+CUDA_VISIBLE_DEVICES="0" aana deploy aana_chat_with_video.app:aana_app
 ```
 
 Once the application is running, you will see the message `Deployed successfully.` in the logs. It will also show the URL for the API documentation.
 
 > **⚠️ Warning**
 >
-> If the application is using GPU, make sure that the GPU is available and the application can access it.
+> The applications require 1 largs GPUs to run. GPU should have at least 48GB of memory.
 >
 > The applications will detect the available GPU automatically but you need to make sure that `CUDA_VISIBLE_DEVICES` is set correctly.
 > 
@@ -100,8 +54,4 @@ Once the application is running, you will see the message `Deployed successfully
 
 2. Send a POST request to the app.
 
-For example, if your application has `/summary` endpoint that accepts videos, you can send a POST request like this:
-
-```bash
-curl -X POST http://127.0.0.1:8000/summary -Fbody='{"video":{"url":"https://www.youtube.com/watch?v=VhJFyyukAzA"}}'
-```
+See [Chat with Video Demo notebook](notebooks/chat_with_video_demo.ipynb) for more information.

aana_chat_with_video/alembic.ini

@@ -0,0 +1,116 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = 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
+
+# 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-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# 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 alembic/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:alembic/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 = 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 = ruff
+ruff.options = --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+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

aana_chat_with_video/alembic/env.py

@@ -0,0 +1,85 @@
+from logging.config import fileConfig
+
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+
+from aana.configs.settings import settings
+from aana.storage.models.base import BaseEntity
+
+# 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)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+
+# Import all models to be included in the migration
+import aana.storage.models  # noqa: F401
+import aana_chat_with_video.storage.models  # noqa: F401
+
+target_metadata = BaseEntity.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 run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    Modified to use our existing db config module.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    engine = settings.db_config.get_engine()
+    context.configure(
+        url=engine.url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+        render_as_batched=True,
+    )
+
+    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.
+
+    """
+    config_section = config.get_section(config.config_ini_section, {})
+    engine = settings.db_config.get_engine()
+    config_section["sqlalchemy.url"] = engine.url
+    connectable = engine_from_config(
+        config_section,
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, target_metadata=target_metadata, render_as_batch=True
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

aana_chat_with_video/alembic/script.py.mako

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