The software provided in this project is offered ‘AS IS‘ without any representations or warranties, express or implied. The Developer makes no claims or promises about the quality, accuracy, reliability, or any other characteristic of this software. To the maximum extent permitted by applicable law, the Developer explicitly disclaims all warranties, whether expressed, implied, or statutory, including but not limited to warranties of merchantability, fitness for a particular purpose, and non-infringement. The Developer does not warrant that the software will meet your requirements, operate without interruption, achieve any intended result, be compatible or work with any other software, systems, or services, or be secure, accurate, complete, free of harmful code, or error-free. You assume all risks associated with the use of this software.
Commercial Exception
The disclaimer above applies to the free, publicly available version of this software. For clients with a paid commercial agreement, different terms and conditions may apply as specified in their individual contracts. If you have a paid agreement with us, please refer to that agreement for details on warranties, support, and other terms that may supersede or modify the above disclaimer
Public release for the Rhea API Explorer which demonstrates the Rhea Generative Framework Rest API specification in OpenAPI (3.0.1) format. A Swagger UI Bundle is used to explore the API.
We are proud to announce our AI powered live chat agents. Using the Rhea Generative Framework with our Rhea Embeddable module, you can embed AI powered live chat services directly on your website.
Rhea has a wide variety of applications and understanding the many use cases can be a challenge. We have prepared a selection of examples and use cases that highlight how Rhea’s functionality could be utilised; keep in mind that the scenarios themselves are conceptual.
This release brings the Rhea PWA Client to Android; replacing the previous Android implementation with a bubblewrap variant derived from our PWA 0.9.7 release.
Public release for the Rhea API Explorer which demonstrates the Rhea Generative Framework Rest API specification in OpenAPI (3.0.1) format. A Swagger UI Bundle is used to explore the API.
Introduces support for Rhea Speech Services; a self-hosted API service which provides speech-to-text and text-to-speech functionality. The Rhea Client reworks the previous browsers dependant TTS & STT functionality to demonstrate our custom solutions.
Take your customer service to the next level by utilising AI powered live chat agents with the Rhea Embeddable Client. Rhea can used to provide professional and tailored live chat functionality; with support to be trained on your content and workflow. Rhea can fulfil a range of scenarios from: enquiry handling, lead generation, real-time assistance and customer support.
Whether providing support or trying to capture enquiries, Rhea can be adapted to meet the needs of your clients at times that suite them with availability 24/7 AI powered agents never tire.
With the Rhea embeddable client, businesses can offer seamless live chat functionality, providing instant support and personalised interactions to their customers. Enhance customer engagement, improve satisfaction levels, and build strong relationships through AI-driven conversations.
Create your own AI assistants trained on your data
Build Persona’s, fine-tune responses and test chat interaction
The Rhea Embeddable client is used by your site visitors to interact with your integrations. To build, chat with and fine-tune your models and/or persona’s you use the Rhea Generative Framework and it’s optional assistant application the Rhea Generative Client.
Deploy fine-tuned models, persona’s and function handling with the embeddable client
Rhea’s output can be constrained to meet your requirements; whether you need a support agent that can guide users through various process, or additions to your onboarding processes such as AI powered enquiry handling.
Rhea Embeddable – Live chat functionality
Powerful Features at Your Fingertips
The Rhea Generative Client offers a range of powerful features to enhance your AI interactions:
Rhea’s live chat functionality along side enquiry handling services can feed data directly in to supported systems; by consuming RestAPI services, Rhea can gather required information that you define and process that data by submitting it directly to your systems.
Out-of-the-box support for the following integrations
Luna WMS (Rest API)
WordPress (Rest API)
Webhooks (Mattermost/Microsoft Teams)
SFTP transfers as JSON or XML
Email – emails the captured data in both plain text and with a JSON attachment.
Support for training on custom Rest API endpoints
Integrate with and expand on functionality
Rhea can be expanded and trained to integrate with your systems;
The Rhea Embeddable component is used in conjunction with the Rhea Generative Framework serving as the embeddable web-app; it enables a rich chat like experience for interacting with the Rhea Generative Framework. Designed to be used in a wide range of applications from; enquiries to lead capture, and other more complex tasks.
Designed to work for you, with your systems and your data
Rhea’s focus has been on extendibility and support to customise and tailor deployments to client needs.
The foundations of Rhea support backends such as: Microsoft Azure AI, OpenAI, Hugging Face, custom backends
These can be used individually or in combinations subject to your deployments
Rhea’s magic sauce sits atop the backend and drives the generation for message responses; constraining, sorting, evaluating and responding.
Customisable embeddable client
With many options you can customise deployments of the Rhea embeddable client, featuring options (as found in the Rhea Embeddable WordPress plugin):
URL
Authentication Token
Cryptographic Hash Secret
Additional CSS
Title
Sub-title
Call to action text
Allow chat contents to be exported/saved as a text file.
Enable the new chat button, clear the current chat contents and reloads.
Limit the length of messages sent, anything passed the length is truncated and replaced with: …
Limit the length of message responses, anything passed the length is truncated and replaced with: …
The embeddable client uses local assets from the plugin; disabling this requires additional CSP and CORS configuration.
Custom Chat UI Theme for your Brand
The Rhea Embeddable Client includes support for tailoring the theme to your brand.
Rhea Embeddable – AI powered agents and live chat
24/7 lead and enquiry capturing
With support to handle QA style questions and information gathering Rhea can serve as a 24/7 enquiry/support/lead generation assistant.
Train on your data and formulate responses tailored to your customers.
We are proud to announce our AI powered live chat agents. Using the Rhea Generative Framework with our Rhea Embeddable module, you can embed AI powered live chat services directly on your website.
Rhea has a wide variety of applications and understanding the many use cases can be a challenge. We have prepared a selection of examples and use cases that highlight how Rhea’s functionality could be utilised; keep in mind that the scenarios themselves are conceptual.
Disclaimer & Notices
Important: This service and it’s associated application is intended for use with Rhea Generative Framework (RGF), the Rhea project is comprised of several modules you can read more about them on the Rhea Generative Suite page.
The demonstration of the Rhea Embeddable client available on our site has various constraints imposed to prevent abuse:
It is intended as a demonstration only and as such Rhea has been constrained to find out what the matter is and then try to convert that in to an enquiry.
If you interested in other more specific demonstrations consider getting in touch with a description of your use case.
Messages sent to and responses from Rhea have a character limits.
There are limits on messages sent and responses received under the hood.
And hard limits that will results in truncated output with: …
You are subject to rate limits and hourly limits.
By using this the demo client you acknowledge the above and agree to play nice.
All demo output from the preview client is logged.
Logged data is stored no longer than 30 days.
Please do not share personal information through this preview of Rhea it is intended for public preview/demonstration purposes only.
Terms & Privacy Policy
Your use of the service and/or application: Rhea Generative Framework and it’s components from Oddineers Ltd. is subject to the following: Terms & Conditions and Privacy Policy.
By integrating the Rhea Generative client, businesses can unlock enhanced capabilities, including fine-tuned models and persona additions. These features allow businesses to tailor AI responses to match their specific requirements and further control AI-generated responses.
The Rhea Generative Client offers a range of powerful features that enhance AI offerings and interactions. These features include:
Chat-like interactions: Engage in natural, conversation-like interactions with AI systems, making it intuitive and user-friendly.
Code formatting: Easily include code blocks in messages without syntax highlighting, enabling seamless collaboration and sharing of code snippets.
Code copy to clipboard: Effortlessly copy code snippets generated by AI to the clipboard, streamlining workflow.
Persona creation and activation: Create and manage personas to define constraints for AI output, customising and fine-tuning generated responses according to specific needs.
Persona library: Access a rich library of predefined personas, making it convenient to select and apply constraints aligned with desired output.
Authentication configuration: Easily configure authentication URLs and tokens for secure and authorised access to AI services.
Theme support: Personalise workspace with a variety of themes to suit preferences and create a visually appealing environment.
Content editor with completions: Enjoy a comprehensive content editor with auto-completion capabilities, enhancing productivity and enabling effortless creation of AI-driven content.
Live Chat Functionality for Productivity Enhancement
The Rhea Generative Client can be utilised by employees to enhance productivity. By serving responses trained on their own datasets or utilising the Persona capabilities and model fine-tuning, businesses can generate responses adapted to their requirements. This functionality is particularly useful for front-of-office/front-of-house services, such as customer-facing live chat.
Live Chat services with the Rhea Embeddable Client: Empowering Businesses with AI Capabilities
The Rhea Embeddable Client offers live chat functionality, enabling businesses to engage with customers in real-time. Powered by AI, businesses can provide instant support and personalised interactions, enhancing customer engagement, improving satisfaction levels, and building strong relationships through AI-driven conversations.
Customisable Chat Interface for Natural Interactions
With its user-friendly messaging-like interface, the Rhea Embeddable Client enables businesses to engage in natural, conversation-like interactions with AI systems. Whether your chosen backend is OpenAI, Azure OpenAI, or HuggingFace LLMs, businesses can unlock the full potential of AI capabilities and receive intuitive and user-friendly responses.
Train, constrain and gather
Rhea supports the ability to ground her responses to only information you provide no deviations.
Train Rhea to capture new leads and politely reject everything else.
Constrain her knowledge to particular subjects or fields.
Gather information for a range of use cases such as lead capture.
Rhea features and capabilities
Persona’s Module
Personas can be used with the AI integration to shape and contain responses to specific subject areas. This module allows you to use several predefined persona’s or to create your own persona’s.
Persona’s can be installed on a user or global context:
User context means that the persona will be applied to that user’s response only.
Global context means that the persona will be applied to all users’ responses across the entire system.
Persona’s enables Rhea’s responses to be restricted to certain topics; limit responses and ensure certain personality traits. She can be trained to sign post users to particular types of content. If you have the right access she can query private data
Includes a Chromium Extension that can integrate with the Rhea RestAPI to allow you to save, edit and retrieve persona’s directly from the browser.
The Chrome extension enables secure communication to Rhea without needing to be logged in to Luna.
Rhea’s Rest API
The Rhea Generative Framework offers a comprehensive Rest API that includes the following capabilities:
Completions: Generate high-quality content based on user input and the AI model’s training data.
Chat: Facilitate natural, conversation-like interactions with AI systems for a seamless user experience. Converse and interact with Rhea over many topics or utilise personas to create focused “assistants” in particular subject areas.
Document Generation and enhancement: dedicated endpoints for document generation and enhancements. By supply document template data and client questionnaire data in specific formats Rhea can extrapolate and populate templates for review.
Persona Controls: Create and manage personas to customise and fine-tune AI-generated responses, aligning with specific requirements.
Instructive: Harass persona’s to generate content based on persona constraints, user input and the AI model’s training data.
Rhea Generative Framework enables rich and consistent framework for building with AI services such as OpenAI, Azure OpenAI, HuggingFace, self-hosted LLMs and more. Enabling businesses to harass AI LLM (large language models) for their needs.
Rhea provides tools and functionality to shape and constrain generated output to specific business functionality or needs.
Businesses desiring or requiring more private options can use the Rhea Generative Framework to host their own models with compatibility for Rest API following OpenAI’s API schema suitable as a drop in replacement.
Disclaimer & Notices
Please note that our API explorer and PWA client are both publicly accessible but consumption of the services requires authentication; access requires an invitation or interested parties can request access at present we are not providing a public signup method.
The Rhea Generative Client is a web-app available and designed to empower businesses by providing a user-friendly Chat UI and foundations to build your own AI powered integrations. Built to support seamless integration in to the Rhea Generative Framework whilst also being extendable for customisation.
The client application enables a rich chat like experience for interacting with the Rhea Generative Framework or other compatible services*. It simplifies B2B clients’ access and interaction with AI systems, facilitating the development of robust and versatile integrations.
A simple chat-like interface
With its user-friendly messaging-like interface, the Rhea Generative Client makes it easy to send and receive messages to and from authenticated endpoints. Seamlessly communicate with AI systems such as: OpenAI, Claude, Azure OpenAI, and models from Hugging face.
Seamless Interaction with Rhea Generative Framework
The Rhea Generative Client is a powerful client application designed to enhance your interactions with the Rhea Generative Framework and other compatible services. Whether you’re a business or an individual, this intuitive tool opens up a world of possibilities for leveraging AI capabilities in your projects.
Custom Chat UI Theme
The Rhea Generative Client includes 3 built-in themes; these are built using our simple and extendable theming framework to enable you to build bespoke theme with your distinct branding.
Demonstration for custom theme support: Purple/Green ThemeDemonstration for custom theme support: Greem/Purple ThemeDemonstration for custom theme support: White/Blue Theme
Note: custom branded themes are currently only available for the Rhea Embeddable – Live chat service; plans to allow custom theming/testing within the Rhea Generative Client are already in the works.
Rhea Generative Framework services and integrations
Powerful Features at Your Fingertips
The Rhea Generative Client offers a range of powerful features to enhance your AI offerings and interactions:
Chat-like Interactions: Engage in natural, conversation-like interactions with AI systems, making it intuitive and user-friendly.
Code Formatting: Easily include code blocks in your messages without syntax highlighting, enabling seamless collaboration and sharing of code snippets.
Code Copy to Clipboard: Effortlessly copy code snippets generated by AI to your clipboard, streamlining your workflow.
Persona Creation and Activation: Create and manage personas to define constraints for AI output, allowing you to customise and fine-tune the generated responses according to your specific needs.
Persona Library: Access a rich library of predefined personas, making it convenient to select and apply constraints that align with your desired output.
Authentication Configuration: Easily configure authentication URLs and tokens to ensure secure and authorised access to AI services.
Theme Support: Personalise your workspace with a variety of themes to suit your preferences and create a visually appealing environment.
Speech-to-text support*
Text-to-speech support*
* Note TTS and STT functionality is reliant on browser support; working browsers include Chrome and Edge, your experience will vary using other browsers.
The Rhea Generative Client can be used by your employee to enhance productivity. Dependant upon your deployments options you could serve responses trained on your own datasets. Or utilise our Persona capabilities and model fine-tuning to generate responses adapted to your requirements.
Front of office/front of house services
Rhea can be used for customer facing services like live chat. Build, train and fine-tine your own persona’s with the Rhea Generative Framework and accompanying Client then deploy the bot to your website with the Rhea Embeddable client all tailored to your purposes and to meet your strict quality requirements.
Enhanced Capabilities
By integrating the Rhea embeddable client, businesses can unlock enhanced capabilities, including:
Fine-tuned Models: Tailor AI responses to match your specific requirements. Fine-tune models to provide customised and contextually relevant outputs.
Persona Additions: Further control the AI-generated responses by adding additional personas. Fine-tune the AI system to align with your brand voice and style.
Engage with your customers more effectively
Take your customer service to the next level utilise live chat with the Rhea Embeddable Client, built on the foundation of the Rhea Generative Client. Offering live chat functionality, businesses can provide real-time assistance and support to their customers, powered by AI.
With the Rhea embeddable client, businesses can offer seamless live chat functionality, providing instant support and personalised interactions to their customers. Enhance customer engagement, improve satisfaction levels, and build strong relationships through AI-driven conversations.
Additionally we intend to allow the Rhea Generative Client to be used with your own services; we will release documentation to support this closer to the time.
The Rhea Generative Framework enables rich integration in to AI service such as OpenAI, Azure OpenAI and other open-source models enabling businesses to harness AI LLM (large language models) for their needs.
This release brings the Rhea PWA Client to Android; replacing the previous Android implementation with a bubblewrap variant derived from our PWA 0.9.7 release.
Public release for the Rhea API Explorer which demonstrates the Rhea Generative Framework Rest API specification in OpenAPI (3.0.1) format. A Swagger UI Bundle is used to explore the API.
Introduces support for Rhea Speech Services; a self-hosted API service which provides speech-to-text and text-to-speech functionality. The Rhea Client reworks the previous browsers dependant TTS & STT functionality to demonstrate our custom solutions.
*Note: by compatible services we are referring to the ability for an third party to build a backend that is compatible with the Rhea Generative Client’s Chat functionality. We will be providing documentation on how to support this soon.
To provide the best experiences, we use technologies like cookies to store and/or access device information. Consenting to these technologies will allow us to process data such as browsing behaviour or unique IDs on this site. Not consenting or withdrawing consent, may adversely affect certain features and functions.
Functional
Always active
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
Preferences
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
Statistics
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
Marketing
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.
