Merge pull request #9 from Azure-Samples/howie/init

code tested local, commented out file upload because of outage.   Need deployment test

Author: howieleung

.gitignore

@@ -0,0 +1,11 @@
+__pycache__/
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+.azure

README.md

@@ -1 +1,81 @@
-# azure-ai-projects-file-search
+# Sample Application using Agents from Azure AI Projects and File Search tool (Python)
+
+This sample includes a simple Python [Quart](https://quart.palletsprojects.com/en/latest/) app that streams responses from Azure AI Agents to an HTML/JS frontend using Server-Sent Events (SSEs). The application is configured to upload two documents under the `files` folder for use with the Azure AI Agents' File Search tool.
+
+The sample is designed for use with [Docker containers](https://www.docker.com/), both for local development and Azure deployment. For Azure deployment to [Azure Container Apps](https://learn.microsoft.com/azure/container-apps/overview), please use this [template](https://github.com/Azure-Samples/openai-chat-app-quickstart) and replace the `src` folder content with this application.
+
+## Application Flow
+
+This application utilizes agents from the azure-ai-projects SDK to interact with the Azure ML agents API. The following sequence diagram describes the interaction between each component in the system. More comprehensive logic related to thread management will be discussed in the next section:
+
+```mermaid
+sequenceDiagram
+    participant User
+    participant Browser
+    participant WebServer
+    participant APIServer
+
+    WebServer->>APIServer: upload_file_poll (post file API and poll by get)
+    APIServer-->>WebServer: return file
+    WebServer->>APIServer: create_vector_store_and_poll (post vector store API and poll by get)
+    APIServer-->>WebServer: return vector store
+    WebServer->>APIServer: create_agent (post assistant API)
+    APIServer-->>WebServer: return agent
+
+    User->>Browser: Open 'http://localhost:50505'
+    Browser->>WebServer: /index
+    WebServer-->>Browser: return HTML, JavaScript, CSS
+
+    User->>Browser: Type message and hit enter
+    Browser->>WebServer: /chat
+    WebServer->>APIServer: create_thread (post thread API)
+    APIServer-->>WebServer: return thread
+
+    WebServer->>APIServer: create_message (post message API)
+    APIServer-->>WebServer: return message
+
+    WebServer->>APIServer: create_stream (post run API)
+    APIServer-->>WebServer: return chunk
+    WebServer-->>Browser: return chunk  (thread_id, agent_id in cookie)
+```
+
+## Application Users and Thread Management
+
+As a web application, it is designed to serve multiple users on multiple browsers. This application uses cookies to ensure that the same thread is reused for conversations across multiple tabs in the same browser. If the browser is restarted, the old thread will continue to serve the user. However, if the application has a new agent after a server restart or a thread is deleted, a new thread will be created without requiring a browser refresh or signaling to the users.
+
+To achieve this, when users submit a message to the web server, the web server will create an agent, thread, and stream back a reply. The response contains `agent_id` and `thread_id` in cookies. As a result, each subsequent message sent to the web server will also contain these IDs. As long as the same agent is being used in the system and the thread can be retrieved in the cookie, the same thread will be used to serve the users.
+
+## Local Development
+
+1. Run `pip install -r requirements.txt`.
+
+2. Make sure that the `.env` file exists.
+
+3. Store the Azure AI Projects connection string in the `.env` file as `PROJECT_CONNECTION_STRING`.
+
+4. Run `az login`.
+
+5. Start the services with this command:
+
+    ```shell
+    python -m quart --app src.quartapp run --port 50505 --reload
+    ```
+
+6. Click 'http://localhost:50505' in the browser to run the application.
+
+
+## Example Run
+
+![File-Search-screenshot](assets/FileSearchAgent.png)
+
+## Deployment to Azure
+
+Follow these steps for deployment:
+1. Install [Docker Desktop](https://www.docker.com/products/docker-desktop/). If you opened this inside GitHub Codespaces or a Dev Container in VS Code, installation is not needed. ⚠️ If you're on an Apple M1/M2, you won't be able to run `docker` commands inside a Dev Container; either use Codespaces or do not open the Dev Container.
+2. Integrate this app using [template](https://github.com/Azure-Samples/openai-chat-app-quickstart) and follow the Azure Container App deployment steps there.
+3. Add an entry of environment variable, `PROJECT_CONNECTION_STRING` in `infra\aca.bicep`.
+4. When you visit the Azure Container App, you will see the deployment has a permission error in the `Console Log`.
+
+![Deployment-Error](assets/DeploymentError.png)
+
+To resolve this permission issue, you need to assign `Contributor` and `Cognitive Services OpenAI User` roles for this `object id` in the `Resource Group` of the `Azure AI Projects`.

assets/DeploymentError.png

@@ -0,0 +1,10 @@
+services:
+  app:
+    build:
+      context: ./src
+    env_file:
+      - .env
+    ports:
+      - 50505:50505
+    volumes:
+      - ./src:/code

assets/FileSearchAgent.png

@@ -0,0 +1,3 @@
+.git*
+.venv/
+**/*.pyc

docker-compose.yaml

@@ -0,0 +1,43 @@
+# ------------------- Stage 0: Base Stage ------------------------------
+FROM python:3.11-alpine AS base
+
+WORKDIR /code
+
+# Install tini, a tiny init for containers
+RUN apk add --update --no-cache tini
+
+# Install required packages for cryptography package
+# https://cryptography.io/en/latest/installation/#building-cryptography-on-linux
+RUN apk add gcc musl-dev python3-dev libffi-dev openssl-dev cargo pkgconfig
+
+
+# ------------------- Stage 1: Build Stage ------------------------------
+FROM base AS build
+
+COPY requirements.txt .
+
+ADD packages packages
+
+RUN pip3 install -r requirements.txt
+
+COPY . .
+
+# ------------------- Stage 2: Final Stage ------------------------------
+FROM base AS final
+
+RUN addgroup -S app && adduser -S app -G app
+
+COPY --from=build --chown=app:app /usr/local/lib/python3.11 /usr/local/lib/python3.11
+COPY --from=build --chown=app:app /usr/local/bin /usr/local/bin
+COPY --from=build --chown=app:app /code /code
+
+# Copy the files directory
+COPY --chown=app:app files /code/files
+
+# Set environment variables for Azure service principal
+
+USER app
+
+EXPOSE 50505
+
+ENTRYPOINT ["tini", "gunicorn", "quartapp:create_app()"]

src/.dockerignore

@@ -0,0 +1,51 @@
+# Information about product item_number: 1
+
+## Brand
+Contoso Galaxy Innovations
+
+## Category
+Smart Eyewear
+
+## Features
+- Augmented Reality interface
+- Voice-controlled AI assistant
+- HD video recording with 3D audio
+- UV protection and blue light filtering
+- Wireless charging with extended battery life
+
+## User Guide
+
+### 1. Introduction
+Introduction to your new SmartView Glasses
+
+### 2. Product Overview
+Overview of features and controls
+
+### 3. Sizing and Fit
+Finding your perfect fit and style adjustments
+
+### 4. Proper Care and Maintenance
+Cleaning and caring for your SmartView Glasses
+
+### 5. Break-in Period
+Adjusting to the augmented reality experience
+
+### 6. Safety Tips
+Safety guidelines for public and private spaces
+
+### 7. Troubleshooting
+Quick fixes for common issues
+
+## Warranty Information
+Two-year limited warranty on all electronic components
+
+## Contact Information
+Customer Support at [email protected]
+
+## Return Policy
+30-day return policy with no questions asked
+
+## FAQ
+- How to sync your SmartView Glasses with your devices
+- Troubleshooting connection issues
+- Customizing your augmented reality environment

src/Dockerfile

@@ -0,0 +1,51 @@
+# Information about product item_number: 2
+
+## Brand
+Contoso Quantum Comfort
+
+## Category
+Self-Warming Blanket
+
+## Features
+- Nano-fiber heating elements for even warmth distribution
+- Intelligent temperature control with machine learning preferences
+- Eco-friendly and energy-efficient design
+- Wireless and portable with up to 12 hours of battery life
+- Waterproof and machine washable material
+
+## User Guide
+
+### 1. Introduction
+Getting to know your new Self-Warming Blanket
+
+### 2. Product Overview
+How to set up and operate your blanket
+
+### 3. Sizing and Fit
+Selecting the ideal warmth setting for comfort
+
+### 4. Proper Care and Maintenance
+Care instructions to maintain warmth and softness
+
+### 5. Break-in Period
+What to expect during the first use
+
+### 6. Safety Tips
+Best practices for safe use
+
+### 7. Troubleshooting
+Common questions and solutions
+
+## Warranty Information
+Three-year warranty with free technical support
+
+## Contact Information
+Quantum Comfort Support at [email protected]
+
+## Return Policy
+45-day satisfaction guarantee with full refund
+
+## FAQ
+- How to pair the blanket with your smart home devices
+- Optimizing battery life for longer use
+- Adjusting blanket settings for different climates

src/__init__.py

@@ -0,0 +1,20 @@
+import multiprocessing
+import os
+
+from dotenv import load_dotenv
+
+load_dotenv()
+
+max_requests = 1000
+max_requests_jitter = 50
+log_file = "-"
+bind = "0.0.0.0:50505"
+
+if not os.getenv("RUNNING_IN_PRODUCTION"):
+    reload = True
+
+num_cpus = multiprocessing.cpu_count()
+workers = 1 #(num_cpus * 2) + 1
+worker_class = "uvicorn.workers.UvicornWorker"
+
+timeout = 120

src/files/product_info_1.md

@@ -0,0 +1,20 @@
+[project]
+name = "quartapp"
+version = "1.0.0"
+description = "Create a simple chat app using Quart and Azure AI Agents"
+dependencies = [
+    "quart",
+    "werkzeug",
+    "gunicorn",
+    "uvicorn[standard]",
+    "openai",
+    "azure-identity",
+    "aiohttp",
+    "python-dotenv",
+    "pyyaml",
+    "azure-ai-projects"
+    ]
+
+[build-system]
+requires = ["flit_core<4"]
+build-backend = "flit_core.buildapi"

src/files/product_info_2.md

@@ -0,0 +1,20 @@
+# Copyright (c) Microsoft. All rights reserved.
+# Licensed under the MIT license. See LICENSE.md file in the project root for full license information.
+
+import logging
+import os
+from quart import Quart
+
+
+def create_app():
+    if os.getenv("RUNNING_IN_PRODUCTION"):
+        logging.basicConfig(level=logging.INFO)
+    else:
+        logging.basicConfig(level=logging.DEBUG)
+
+    app = Quart(__name__)
+
+    from . import chat  # noqa
+
+    app.register_blueprint(chat.bp)
+    return app