DIAL Platform
DIAL stands for Deterministic Integrator of Applications and Language Models. It is an enterprise-grade open-source AI orchestration platform, development studio, and application server.
Main Principles
From its inception, DIAL was designed to serve as a unified, secure, scalable and customizable business platform for GenAI applications.
Open-Source
DIAL is an open-source solution available under the permissive and free Apache License, Version 2.0.Low TCO
We aim to minimize technical complexity and licensing risks by utilizing community hardware, affordable storage solutions, and technologies.
Vendor-Agnostic
DIAL can operate on any cloud platform and on-prem, is model and domain agnostic enabling the highest level of flexibility.API-First
All DIAL features are available via API, which empowers the development of custom extensions.Scalable
DIAL does not require a centralized DB and relies on Redis and cloud storages making it an ideal platform for building web-scale businesses.
Modular
Start with a basic setup and scale up to a full ecosystem as needed. Go rapidly from prototyping to fully operational production applications.Small Tech Footprint
The system requires minimum resources to operate and can run equally smooth on clouds and personal laptops.
Secure
Sensitive information is managed according to industry best practices. Scans for dependencies, vulnerabilities, and licenses are required steps in the delivery process.Key Features
Customizable ChatCustomizable chat application for end-users, with ARBAC, extendable functionality and ability to add custom GenAI applications. Chat Overlay library allows embedding an iframe with AI conversation into your web application without an additional development.Learn more
Models ConnectivityAccess models from all major LLM providers, language models from the open-source community, alternative vendors, and fine-tuned micro models, as well as self-hosted or models listed on HuggingFace or DeepSeek. Use SDK to create adapters for additional models.Learn more
Business-Driven GenAI ApplicationsDIAL can be extended to meet specific business requirements. You can use SDK to create model adapters and GenAI applications, and even add new application types to build fully custom implementations. DIAL Chat supports custom components, data visualizers and custom UIs.Learn more
Application ServerDIAL acts as application server offering tools to develop, deploy, host and manage different types of GenAI applications. We take care of scalability, availability and resource optimization issues, as well as integration with existing systems and data sources.
MarketplaceIn DIAL Marketplace, you can showcase all your conversational agents. Additionally, it offers collaboration tools and supports Attribute and Role-Based Access Control (ARBAC) to streamline teamwork and ensure secure access to resources.Learn more
Unified APIUnified API, based on OpenAI API, gives access to all language and embedding models and applications. It helps create a unification layer where all models and applications are interchangeable, delivering a cohesive conversational experience and future-proof development of GenAI applications.Learn more
InterceptorsDIAL uses Interceptors to add custom logic to in/out requests for models and apps, enabling PII obfuscation, guardrails, safety checks, and beyond. Use SDK to develop Interceptors.Learn more
DIAL RAGDIAL provides access via both UI and API to enterprise-grade RAG with support for multiple input formats, ability to answer questions from text, tables, images and charts. Following an API-first approach, you can use it as a building block in your GenAI applications.Learn more
AI-Work-with-Your-DataDIAL includes applications such as DIALXL, Mindmap, StatGPT, and ChatHub that follow the AI-Work-with-Your-Data concept. These applications allow users not only query data but also do research and create new artifacts by interacting with it (visualize, analyze, interpret, transform, augment and more) using natural language.Learn more
MiddlewareDIAL ats as middleware including connectivity to main LLM vendors, observability tools, collection and visualization of users analytics, cost management with adaptable rate limits, ARBAC, load balancer, interceptors, persistent layer and much more.