bert_conda

Perform Sentiment Analysis with BERT and Qwak

Overview

This project demonstrates how to label sentiment in a text prompt using a pre-trained BERT model with Qwak's Machine Learning Platform.

It showcases how to:

• Define the QwakModel class
• Initialize the pre-trained BERT model
• Predict phrase sentiment using Qwak's API

The code is designed to work seamlessly with Qwak's platform and serves as a practical example.

How to Test Locally

1. Clone the Repository: Clone this GitHub repository to your local machine.

2. Install Dependencies: Make sure you have the required dependencies installed, as specified in the conda.yml file.

   conda env create -f main/conda.yaml
   conda activate bert_sentiment_analysis

3. Install and Configure the Qwak SDK: Use your account Qwak API Key to set up your SDK locally.

   pip install qwak-sdk
   qwak configure

4. Run the Model Locally: Execute the following command to test the model locally:

   python test_model_locally.py

How to Run Remotely on Qwak

1. Build on the Qwak Platform:

   Create a new model on Qwak using the command:

   qwak models create "BERT Sentiment Analysis" --project "Sample Project"

   Initiate a model build with:

   qwak models build --model-id <your-model-id> ./bert_conda

2. Deploy the Model on the Qwak Platform with a Real-Time Endpoint:

   To deploy your model via the CLI, use the following command:

   qwak models deploy realtime --model-id <your-model-id> --build-id <your-build-id>

3. Test the Live Model with a Sample Request:

   Install the Qwak Inference SDK:

   pip install qwak-inference

   Call the Real-Time endpoint using your Model ID from the Qwak platform:

   python test_live_mode.py <your-qwak-model-id>

Project Structure

.
├── main                   # Main directory containing core code
│   ├── __init__.py        # An empty file that indicates this directory is a Python package
│   ├── model.py           # Defines the Credit Risk Model
│   └── conda.yaml         # Conda environment configurationdata
|
├── test_model_locally.py  # Script to test the model locally
├── test_live_model.py     # Script to test the live model with a sample REST request
└── README.md              # Documentation

Try Qwak's MLOps Platform for Free

Are you looking to deploy your machine learning models in a production-ready environment within minutes? Qwak offers a seamless platform to build, train, and deploy your models with ease.

Whether you're a data scientist, ML engineer, or developer, Qwak provides the tools and support to take your models from development to deployment effortlessly. Explore the platform and start deploying your models today. Try Qwak for free!