You can imagine it like this: Hypothetically, when Wikipedia implemented the ERI, it would vectorize
all pages using an embedding method. All of Wikipedia’s data would remain with Wikipedia, including the
vector database (decentralized approach). Then, any AI Studio user could add Wikipedia as a data source to
significantly reduce the hallucination of the LLM in knowledge questions.
</MudText>
<MudText Typo="Typo.body1">
<b>Related links:</b>
</MudText>
<MudList T="string" Class="mb-6">
<MudListItem T="string" Icon="@Icons.Material.Filled.Link" Target="_blank" Href="https://github.com/MindWorkAI/ERI">ERI repository with example implementation in .NET and C#</MudListItem>
Hint: to allow this assistant to manage multiple presets, you must enable the preselection of values in the settings.
</MudText>
}
<MudText Typo="Typo.h4" Class="mb-3 mt-6">
Auto save
</MudText>
<MudText Typo="Typo.body1" Class="mb-3">
The ERI specification will change over time. You probably want to keep your ERI server up to date. This means you might want to
regenerate the code for your ERI server. To avoid having to make all inputs each time, all your inputs and decisions can be
automatically saved. Would you like this?
</MudText>
@if(this.AreServerPresetsBlocked)
{
<MudText Typo="Typo.body1" Class="mb-3">
Hint: to allow this assistant to automatically save your changes, you must enable the preselection of values in the settings.
</MudText>
}
<MudTextSwitch Label="Should we automatically save any input made?" Disabled="@this.AreServerPresetsBlocked" @bind-Value="@this.autoSave" LabelOn="Yes, please save my inputs" LabelOff="No, I will enter everything again or configure it manually in the settings" />
<MudTextField T="string" Disabled="@this.IsNoneERIServerSelected" @bind-Text="@this.serverName" Validation="@this.ValidateServerName" Immediate="@true" Label="ERI server name" HelperText="Please give your ERI server a name that provides information about the data source and/or its intended purpose. The name will be displayed to users in AI Studio." Counter="60" MaxLength="60" Variant="Variant.Outlined" Margin="Margin.Normal" UserAttributes="@USER_INPUT_ATTRIBUTES" Class="mb-3" OnKeyUp="() => this.ServerNameWasChanged()"/>
<MudTextField T="string" Disabled="@this.IsNoneERIServerSelected" @bind-Text="@this.serverDescription" Validation="@this.ValidateServerDescription" Immediate="@true" Label="ERI server description" HelperText="Please provide a brief description of your ERI server. Describe or explain what your ERI server does and what data it uses for this purpose. This description will be shown to users in AI Studio." Counter="512" MaxLength="512" Variant="Variant.Outlined" Margin="Margin.Normal" Lines="3" AutoGrow="@true" MaxLines="6" UserAttributes="@USER_INPUT_ATTRIBUTES" Class="mb-3"/>
<MudSelect Disabled="@this.IsNoneERIServerSelected" T="OperatingSystem" @bind-Value="@this.selectedOperatingSystem" Label="Operating system on which your ERI will run" Variant="Variant.Outlined" Margin="Margin.Dense" Validation="@this.ValidateOperatingSystem" Class="mb-1">
@foreach (var os in Enum.GetValues<OperatingSystem>())
<MudSelect Disabled="@this.IsNoneERIServerSelected" T="AllowedLLMProviders" @bind-Value="@this.allowedLLMProviders" Label="Allowed LLM providers for this data source" Variant="Variant.Outlined" Margin="Margin.Dense" Validation="@this.ValidateAllowedLLMProviders" Class="mb-1">
@foreach (var option in Enum.GetValues<AllowedLLMProviders>())
You can integrate additional libraries. Perhaps you want to evaluate the prompts in advance using a machine learning method or analyze them with a text
mining approach? Or maybe you want to preprocess images in the prompts? For such advanced scenarios, you can specify which libraries you want to use here.
It's best to describe which library you want to integrate for which purpose. This way, the LLM that writes the ERI server for you can try to use these
libraries effectively. This should result in less rework being necessary. If you don't know the necessary libraries, you can instead attempt to describe
the intended use. The LLM can then attempt to choose suitable libraries. However, hallucinations can occur, and fictional libraries might be selected.
</MudText>
<MudTextField Disabled="@this.IsNoneERIServerSelected" T="string" @bind-Text="@this.additionalLibraries" Label="(Optional) Additional libraries" HelperText="Do you want to include additional libraries? Then name them and briefly describe what you want to achieve with them." Variant="Variant.Outlined" Margin="Margin.Normal" Lines="3" AutoGrow="@true" MaxLines="12" UserAttributes="@USER_INPUT_ATTRIBUTES" Class="mb-3"/>
<MudText Typo="Typo.h4" Class="mt-9 mb-1">
Provider selection for generation
</MudText>
<MudText Typo="Typo.body1" Class="mb-2">
The task of writing the ERI server for you is very complex. Therefore, a very powerful LLM is needed to successfully accomplish this task.
Small local models will probably not be sufficient. Instead, try using a large cloud-based or a large self-hosted model.
</MudText>
<MudText Typo="Typo.body1" Class="mb-2">
<b>Important:</b> The LLM may need to generate many files. This reaches the request limit of most providers. Typically, only a certain number
of requests can be made per minute, and only a maximum number of tokens can be generated per minute. AI Studio automatically considers this.
<b>However, generating all the files takes a certain amount of time.</b> Local or self-hosted models may work without these limitations
and can generate responses faster. AI Studio dynamically adapts its behavior and always tries to achieve the fastest possible data processing.
AI Studio can save the generated code to the file system. You can select a base folder for this. AI Studio ensures that no files are created
outside of this base folder. Furthermore, we recommend that you create a Git repository in this folder. This way, you can see what changes the
AI has made in which files.
</MudText>
<MudText Typo="Typo.body1" Class="mb-2">
When you rebuild / re-generate the ERI server code, AI Studio proceeds as follows: All files generated last time will be deleted. All
other files you have created remain. Then, the AI generates the new files. <b>But beware:</b> It may happen that the AI generates a
file this time that you manually created last time. In this case, your manually created file will then be overwritten. Therefore,
you should always create a Git repository and commit or revert all changes before using this assistant. With a diff visualization,
you can immediately see where the AI has made changes. It is best to use an IDE suitable for your selected language for this purpose.
</MudText>
<MudTextSwitch Label="Should we write the generated code to the file system?" Disabled="@this.IsNoneERIServerSelected" @bind-Value="@this.writeToFilesystem" LabelOn="Yes, please write or update all generated code to the file system" LabelOff="No, just show me the code" />
<SelectDirectory Label="Base directory where to write the code" @bind-Directory="@this.baseDirectory" Disabled="@(this.IsNoneERIServerSelected || !this.writeToFilesystem)" DirectoryDialogTitle="Select the target directory for the ERI server" Validation="@this.ValidateDirectory" />
