NLP As A Microservice

This project is a sample demo of NLP as a service mono-repo microservice platform built using FastAPI, Streamlit and Hugging Face. The use cases are related to chatbot automation services.

Use Cases

• Next Query Recommendation
• Query Expansion
• Fallback Reduction

Features

• Files Upload and Download integrated with s3
• Services are in a mono repo microservice pattern
• Temporary and secured access to users for downloading processed files from s3 using presigned urls
• Dockerized application. Indiviual docker containers for each microservice
• Nginx Reverse Proxy to ensure security, scalability, flexibilty and web acceleration
• Microservice specific CI/CD using AWS Codecommit, CodePipeline
• AWS ECR to store the microservice images in the image repositories
• AWS EKS Fargate serverless deployment. Microservice specific deployment, service and ingress manifests provided
• Multipage streamlit application. Easy to add microservice specific streamlit frontend

Requirement

Please add AWS_SECRET_ACCESS_KEY and AWS_ACCESS_KEY_ID in the helpers.py in each indiviual microservice

Installation & Usage

$ git clone  https://github.com/karndeb/Fastapi-Streamlit-NLPService.git
# Use docker compose to start the services
$ docker-compose up
# Start the Streamlit server
$ streamlit run app.py

License

This project is licensed under the GPL-3.0 License - see the LICENSE.md file for details