Overview
The Unique FinanceGPT is a white-label application that allows end users to chat against their organization’s knowledge base for various use cases.
The main chat interface displays two components: Spaces and Chat History.
Spaces serve as environments where end users interact with an AI Assistant. A Space is created for each use case. For example:
Chat with GPT
Research Stock Investment Opportunities
Chat with a set of ingested files from the Knowledge Base.
Ingested files can be files synced via external data sources such as Sharepoint, or files uploaded directly into the Knowledge Base.
Chat with uploaded file(s)
Uploaded files are files that are uploaded directly in the Chat interface and not in the Knowledge Base.
Chat History displays past conversations they've had, enabling users to revisit discussions and continue prompting.
Configuring a Space
Configuring a Space involves specifying the following:
[Space Name] Text Field
The Space name refers to the unique identifier to each chat environment. It that helps distinguish between different use cases or topics for end-user interactions. This text will appear in the chat interface navigation.
Suggestion: Choose a short name that reflects the specific use case or topic of the Space.
[About Space] Text Field
The About Space text serves as a brief description or introduction to the purpose and objectives of the Space. This text will appear in the Space’s user interface.
Suggestion: Describe the focus or goal of the Space. It should help orient users and provides context for their interactions within the environment.
[Space Usage Recommendation] Text Field
The Space Usage Recommendation text provides essential insights and cautions that users should acknowledge before initiating prompts within the Space.
AI Assistant
Read AI Assistants and Modules .
Import/Export Functionality
The import/export feature is essential for managing AI Assistants across different environments, such as testing and production. This feature allows users to seamlessly transfer an AI Assistant configuration from one environment to another.
Use Case
When users have configured an AI Assistant in the testing environment and are ready to deploy it to the production environment, they can utilize the import/export functionality to streamline this process.
How It Works
Export Configuration from Environment A (e.g. testing environment):
Navigate to the testing environment where the AI Assistant is configured.
Click on the “Export AI Assistant” button.
A .txt file containing the configuration details will be downloaded to your system.
Import Configuration to Environment B (e.g. production environment):
Go to the Space in the production environment where you want to replicate the AI Assistant configuration.
Click on the blue cloud icon located next to the modules selection.
Select the previously downloaded .txt file from your system.
The AI Assistant configuration will be imported and applied to the Space in the production environment.
Advanced Settings
Advanced Settings encompass a range of configuration options and controls that allow admin users to customize and fine-tune the behavior of the Space and its associated components.
Module selection
"modelChoosing": "BY_PROMPT"
When users commit a prompt in a Space where the Assistant contains more than one module, the system will need to choose which module to generate a response. This setting proposes two approaches:
BY_FUNCTION_CALL: Module selection is done with the function calling approach of OpenAI (link to this page https://platform.openai.com/docs/guides/function-calling ). Only possible if OpenAI models are used.BY_PROMPT: In this case, the module descriptions are included into the system message of the LLM call to select the most appropriate module. This options is needed in case a LLM is used that does not allow function calling in the style of OpenAI.
Pin a Space in the navigation
"isPinned": true
When setting is set to true, the Space will be pinned at the top of the navigation for all members of the Space in the organization.
Enable PDF Viewer functionality
"showPdfHighlighting": true
When setting is set to true, and the user selects a reference, the application will open a PDF Viewer which highlights the content which the Assistant used to generate a response.
Knowledge Scopes
The Knowledge Scope is a specific set of rules that determine the scope of accessible information for users within the Space.
There are two main benefits:
Controlling the information accessible within a Space to ensure users are only presented with relevant content.
Focusing the AI Assistant's knowledge within a defined scope can lead to more accurate and relevant responses to user queries, improving overall user experience and satisfaction.
At the moment, defining the Knowledge Scope of a Space can only be configured via API.
Upload in Chat
The Upload in Chat functionality toggle enables users to upload files directly within the chat interface of the Space.
Suggested Prompts
Suggested Prompts are predefined queries or conversation starters recommended for users to initiate interactions with the AI Assistant within the Space. They help guide users who may be unsure about what to ask or discuss.
A Suggested Prompt contains a title and prompt line. The title appears above the input field of the chat interface. When a user selects a title, it will pre-fill the input field with the prompt line.
Suggestion: Offer a variety of prompts covering common topics or tasks related to the Space's objectives.
Members
Members represent the individual users or group of users granted access to the Space.
Only members of the Space can view the Space in their chat interface navigation and interact with it.
By default the user that creates the space is added as a member to that space.
When there are no members added in a Space, all users in the organization can view the Space in their chat interface navigation and interact with it.
Author |
|---|