Smarter Architecture at a glance

Scalable serverless Kubernetes compute infrastructure that is largely self-maintaining.
Countermeasures for common Internet and web intrusion strategies including SQL injection, cross-site request forgeries, brute force password attacks, distributed denial of service, cross-site scripting, clickjacking, host header corruptions. Additionally, Smarter goes to great pains to minimize its attack surface, primarily by only opening ports 80 and 443 to the public.
Python-Django customer web dashboard application for developing plugin-based API's deployed to custom domains.
LangChain managed LLM API requests. This provides a layer of abstraction between Smarter and underlying LLM vendor providers, and it also provides a simple means of standardizing Smarter customers' API format.
React sandbox chat UI for prototyping pre-production APIs. Also works as a skinnable stand-in production UI if customers want this.
customer api logging architecture implemented with Django models, signals and Celery tasks
Team management features
Configurable use-based billing features based on api calls as well as plugin usage.

Python Django

Most of Smarter is developed using Python's Django web framework with the following noteworthy additions:

Django-rest-knox , used for creating secure, performant REST APIs.
Django Celery. robust asynchronous compute layer using Celery, Redis and Kubernetes which can be leveraged for scheduled tasks like automated reports as well as real-time compute-intensive functions.
Pydantic , for extending Django's settings module to facilitate CI-CD friendly configuration data from multiple sources: environment variable, terraform, Kubernetes secrets, Github Actions secrets, etc.
Pandas, NumPy, SciPy and Levenshtein
OpenAI
LangChain

ReactJS chat application

The chat app in the dashboard sandbox is written in React. Complete source code and documentation is located here .

React app that leverages Vite.js , @chatscope/chat-ui-kit-react , and react-pro-sidebar .

Django Integration

Be aware that there are many considerations for getting React to work inside a Django project. You can read more here .

Webapp design features

robust, highly customizable chat features
A component model for implementing your own highly personalized OpenAI apps
Skinnable UI for each app
Includes default assets for each app
Small compact code base
Robust error handling for non-200 response codes from the custom REST API
Handles direct text input as well as file attachments
Info link to the OpenAI API official code sample
Build-deploy managed with Vite

Smarter REST API

Source code is located here

Not to be confused with Smarter's flagship product, customer-implemented custom REST API's, Smarter additionally has its own REST API, which is a Python Django project implementing Querium's proprietary Plugin model, along with additional models for commercializing the service.

API end points

Requirements

git . pre-installed on Linux and macOS
make . pre-installed on Linux and macOS.
Python 3.11 : for creating virtual environment used for building AWS Lambda Layer, and locally by pre-commit linters and code formatters.
NodeJS : used with NPM for local ReactJS developer environment, and for configuring/testing Semantic Release.
Docker Compose : used by an automated Terraform process to create the AWS Lambda Layer for OpenAI and LangChain.

Cloud engineers:

AWS account
AWS Command Line Interface
Terraform . If you're new to Terraform then see Getting Started With AWS and Terraform

Optional requirements:

OpenAI platform API key . If you're new to OpenAI API then see How to Get an OpenAI API Key
Google Maps API key . This is used the OpenAI API Function Calling coding example, " get_current_weather() ".
Pinecone API key . This is used for OpenAI API Embedding examples.