The development process of PhariaAI applications
| For a more hands-on approach to app development with PhariaAI, start with the Quick start guide: building PhariaAI applications to get your application up and running quickly. |
Developing and deploying a custom PhariaAI application follows an iterative process similar to other software development workflows. While the phases below are presented sequentially, you can adapt and revisit them as needed based on your application’s requirements.
This article provides an overview of the key development phases and links to detailed documentation for each step.
Infrastructure prerequisites
Ensure that your PhariaAI installation PhariaAI Installation & Configuration Guide has the following core components enabled:
-
PhariaOS for deployment and management of your application.
-
PhariaAssistant for rendering your application UI.
-
PhariaInference API for model serving and inference. See our Model recommendations for PhariaAssistant guide to help you choose the right model for your application.
-
PhariaEngine for building and deploying Skills.
-
PhariaData for data management utilities such as file management and file transformation.
Data setup, processing, and management
During the process of building a custom PhariaAI application, you need to set up and process data for one or more operations:
-
for model training
-
for creation of document collections for document search
-
for experimentation during development of your Skills and applications
We provide the PhariaData application to help you manage this data, including file ingestion for dataset creation and other file transformations.
We also provide a vector database, called PhariaDocument Index, to support Retrieval Augmented Generation (RAG) setups. With PhariaDocument Index, you can:
-
create document collections with metadata
-
leverage powerful semantic and hybrid search functionality to retrieve relevant documents and contexts
See Creating collections of files for further details.
Skill development and deployment
PhariaEngine is designed to facilitate the development and deployment of your Skills. It provides an interface for Skills to interact with as part of a unified runtime environment. See the PhariaEngine documentation for details.
To explore the integration of a Skill into a custom PhariaAI application, see the Quick start guide: building PhariaAI applications.
Development and deployment of the application service and UI
To initiate the development and deployment of your PhariaAI applications, see our quick start guide for a streamlined process. This guide provides a comprehensive tutorial to get you started efficiently.
Tracing, debugging, and evaluating the application and Skills
You can trace, debug, and evaluate your Skills and application service during development and in production using PhariaStudio. We provide a portal and an SDK to help you do this.
See the PhariaStudio documentation for details.
Application feedback
See Collecting user feedback in PhariaAI applications for details on how to store application feedback in the PhariaAssistant API’s database.
Troubleshooting guide
For any issues you encounter during the development and deployment process, see the Troubleshooting guide for common error solutions and best practices.