Page Comparison

What are the LLMs that can be used?

Any provisioned models can be connected to the system via config. So far all, OpenAI Models have been tested:

• GPT 3.5 - GPT 3.5-Turbo

• GPT 4-Turbo - GPT 4-Turbo

• GPT 4-Vision (in various minor versions)

• GPT-4o

Other LLM’s:

• Mistral AI - Zephyr AI

Can models be customised / bring our own models?

Yes, we even have customers that are doing this.

Is there a platform available for conducting automated tests and comparing results for custom models?

Yes, through benchmarking, it is possible to perform comparisons.

There is a documentation for this process: https://unique-ch.atlassian.net/wiki/x/AQDJIw

How can one train, test, and deploy a model for use with Unique’s solution?

So far, we have not directly trained a model ourselves; instead, our customers have undertaken this task. However, our Data-Science team has provided support and guidance to them throughout the process.

Does one need to use Azure AI Studio?

There's no need to restrict yourself to Azure AI Studio exclusively. As long as the model can be provisioned, we are capable of integrating it.

Is it possible to implement version control for models, such as maintaining a development version, publishing a beta version, and continuing to use a previous version?

Yes, within the system, each prompt allows for the selection of the model and its version at will. We practice this on a regular basis, especially with the release of new minor or preview versions from Azure OpenAI.

Can models be shared by user-groups?

Yes, it can be scoped by user-groups.

Can models be restricted by
user-groups?

Yes, it can be restricted by user-groups.

Can tokens consumption be followed by model or by user-groups?

This feature is currently under development and not available yet.

However, an Analytics Framework with downloadable CSV-Reports is already in place and covers these points:

• User Engagement

• Assistant Usage

• Most referenced files

Read more about this here: Analytics

A report incl. consumption by assistant/model is planned for Q2 2024.

Are there several types of prices depending on the models used ?

Our pricing model remains fixed, however, the costs of the underlying models set by Microsoft are subject to change and are transparently communicated back to you. Prices may fluctuate. We offer guidance on which prompts require specific models.

How is visibility kept on the costs related to the API usage?

We report the costs generated on the Subscription on a monthly basis. In the early days of the project, we can negotiate a faster rhythm.

Is it possible to set token limits for each model or user group, including actions like sending alerts or shutting down the API?

This feature is not available yet and currently under development, planned for Q3 2024.

Is it possible to grant standard access to ChatGPT-3.5, replacing the direct access currently provided to certain staff members?

Yes, this is even included in the base configuration of Unique. You can even give access to ChatGPT-4.

Is your solution offered on the MS Marketplace?

Unique is currently not offered in the MS Marketplace.

What test have been done to select the appropriate LLM models?

We conducted benchmarks using our documents, and our clients performed similar tests. This process helps us select the most suitable models for each prompt or use case. While we have evaluated other models, we found that they do not yet match the performance of GPT-4, especially in situations requiring RAG.

How is the bot communicating with Teams/Zoom/Google Meet?

It is joining the call as a meeting participant and recording the audio and video.

What is the output of the bot recording the meeting?

Recording of the meeting as video/audio, transcript, and statistics.

What happens if there is an interruption in the internet connection during a recording?

If there is no internet connection during a recording, the app does not upload anything. Once the device goes back online and the user opens the app, the upload process starts. If a recording fails, it is still stored on the phone, but the user has the option to delete it.

What happens if the app is closed unexpectedly during a recording?

The recording is immediately stopped and processed for uploading once the app is back in a consistent state.

Will there be a push notification or any other notification if there is an interruption in the recording?

We currently do not have push notifications implemented, but we have a short onboarding message that instructs users to go back to the app if something happens. We are also working on implementing a pause functionality for recordings.

What happens as soon as the recording is stopped?

The audio-file is transferred to the Unique Azure platform and the file is deleted on the phone.

Is the audio-file protected on the phone and only usable with the Unique App?

Yes.

What happens if a transfer to the Unique Azure platform gets interrupted (no connection, failure, no battery and other cases)

The audio files are stored on the Smartphone.

Can a failed transfer be deleted in the Azure Unique Application?

A failed transfer can be deleted from the phone (failed means it did not reach out Azure Unique Application, so there is no need for deletion there).

Could you provide a diagram of the data flow between the audio recording and Azure’s AI speech service?

Here is a nostalgic diagram that shows the data flows of the state machine with speech: Image Removed