Source Code Documentation

title: Task Detector emoji: ⚡ colorFrom: blue colorTo: red sdk: docker pinned: false app_port: 7860 short_description: AI Based Asistant from Chameleon Team, PiA

TaskDetector

Microsoft Teams conversation bot

Overview

Each message in a conversation is an Activity object of type messageType: message. When a user sends a message, Microsoft Teams posts the message activity to your bot. Teams sends a JSON object to your bot's messaging endpoint and Teams allows only one endpoint for messaging. Your bot examines the message to determine its type and responds accordingly.

Basic conversations are handled through the Bot Framework connector, a single REST API. This API enables your bot to communicate with Teams and other channels. The Bot Builder SDK provides the following features:

Easy access to the Bot Framework connector. Functionality to manage conversation flow and state. Simple ways to incorporate cognitive services, such as natural language processing (NLP). Your bot receives messages from Teams using the Text property and it sends single or multiple message responses to the users.

Technologies

FastAPI: A modern, fast (high-performance) web framework for building APIs with Python 3.6+ based on standard Python type hints.
MongoDB: A NoSQL database for storing user data.
Uvicorn: Uvicorn is an ASGI web server implementation for Python.
Pydantic: Pydantic is the most widely used data validation library for Python.
Motor: Motor presents a coroutine-based API for non-blocking access to MongoDB from Tornado or asyncio.
Beanie: Beanie - is an asynchronous Python object-document mapper (ODM) for MongoDB. Data models are based on Pydantic.
Docker: Docker is a set of platform as a service products that use OS-level virtualization to deliver software in packages called containers.

Setup and Installation

Prerequisites

Python 3.10+
Docker
Docker Compose
MongoDB
Git
FastAPI
Pydantic
Motor
Beanie
Uvicorn
TODO

Build and Run

Uvicorn (development mode)

Clone the repository

bash git clone https://github.com/pia-team/task-detector.git

Change the directory

bash cd task_detector

Environment

python environment

create and activate a virtual environment

```bash python -m venv venv

source venv/bin/activate ```

Conda environment

create and activate a conda environment

```bash conda create --name task_detector_env python=3.10 pytorch-cuda=12.1 pytorch cudatoolkit xformers -c pytorch -c nvidia -c xformers -y

conda activate task_detector_env

python3 -m ipykernel install --user --name=task_detector_env

```

Install dependencies

bash pip install -r requirements.txt

Create a .env file in the root directory and add the following environment variables

bash cp .env.default .env cp .env.default .env.prod

Run the application on local machine (development mode)

bash uvicorn app.main:app --host 0.0.0.0 --port 8001 --env-file .env

python (development mode)

bash python main-dev.py

Docker (development mode)

docker-compose.yaml file has three services: app, mongo, and mongo-express.

bash docker-compose up --build

Access the application

Open your browser and go to root url http://localhost:8001 to access the FastAPI application.
Open your browser and go to http://localhost:8001/api/v1/docs to access the Swagger UI.
Open your browser and go to http://localhost:8081 to access the MongoDB Express.

Folder Structure

```plaintext . ├── app │ ├── api │ ├── bots │ ├── config │ ├── entity │ ├── repository │ ├── service │ ├── security │ ├── utils │ ├── main.py ├── tests

```

APIs

POST /api/v1/login
POST /api/v1/users
GET /api/v1/users
PUT /api/v1/users
DELETE /api/v1/users
POST /api/v1/messages

Add new entity

TODO

Conclusion

This FastAPI MongoDB application is structured to provide a robust and scalable API solution. By leveraging Docker and CI/CD practices, the application can be easily deployed and maintained.

Feel free to contribute to this project by submitting issues or pull requests!

Welcome to task_detector_api