The main component of AI DIAL, which provides unified API to different chat completion and embedding models, assistants, and applications

A default UI for AI DIAL

Documentation for AI DIAL

Framework to create applications and model adapters for AI DIAL

EPAM AI DIAL Helm Repository

The project implements AI DIAL API for language models from Azure OpenAI

Static content and UI customizations for default AI DIAL UI

Continuous Integration instrumentation for AI DIAL components

The project implements AI DIAL API for language models from AWS Bedrock

The project implements AI DIAL API for language models and embeddings from Vertex AI

Model agnostic assistant/addon implementation for AI DIAL. It allows to use self-hosted OpenAI plugins as DIAL addons

Realtime analytics server for AI DIAL. The service consumes the logs stream AI DIAL Core, analyzes the conversation and writes the analytics to InfluxDB

Document Q&A system with multiple retrieval methods

Framework for creating interceptors for AI DIAL

Admin Panel API for AIDIAL Core

Authentication helper for AI DIAL

A python library designed for RAG (Retrieval-Augmented Generation) evaluation, where retrieval and generation metrics are calculated.

The project implements application which adapts calls from one DIAL Core to calls to another DIAL Core.

A UI for AI DIAL Admin Panel

A service for building and running Python applications as web services. It automates the process of fetching source files from AI DIAL storage, building Docker images, and deploying them as scalable web services using Knative.