Skip to main content

Agents

There are 3 types of agents that can be created: Chat, Content Creator and Business Analyst

Agents can be created and or edited from the following menu: Settings > Agent > Create Agent

More about Agents​

The required details for creating an agent are:

  • Name
  • Mode
    • Retriever: Chat agent enhanced by your documents, internet search and functions
    • Coder: Coding assistant for developers and data scientists enhanced by your programming documentation and code enviroments
    • Casual: Everyday agent for general purpose activities, image generation and files analysis
    • Planner: Agent that can plan and execute tasks leveraging other agents
  • Topics (Under Knowledge settings) - required only if retriever mode is selected

When retriever mode is selected the user has the ability to turn on Advanced reasoning to force the agent to explain its reasoning step by step.

When retriever or coder mode is selected the user has the ability to turn on Knowledge Settings to allow the agent to use the documentation to answer questions.

When planner mode is selected can select the agents that will be used to execute the tasks. A new section to performn the necessary operations appears in the Planner tools section.

Moreover, the retriever mode allows the user to turn on Internet search to allow the agent to search the internet for answers.

When casual mode is selected the user has the ability to turn on Image generation to allow the agent to generate images based on the user's request and Docs upload to allow the agent to analyze files bypassing the Knowledge Hub.

`Chat with agents modal settings.`

Knowledge Settings​

In the Knowledge Settings, you assign the topics to the agent and set the configuration of the agent and the knowledge hub. By default, new agents will not have any topics assigned to them. You will need to assign topics to the agent in order for it to be able to answer questions.

  • Topics: The topics that the agent will be able to answer questions about.
  • Max history (1-10): How many of the previous conversation will the agent remember to use for context.
  • Keywords for knowledge base query: Search through the documentation with the keywords of the question or the full question. ToothFairyAI recommends to use keywords for larger documents sets and full question for smaller documents sets.
  • Max keywords (1-10): Max number of keywords to use for the knowledge base query.
  • TopK: Max number of results to return from the knowledge base query.
  • Doc TopK (1-10): Max number of documents to extract from the initial knowledge base query by document id. Use this setting to reduce document bias in case especially of conflicting information.
  • Min retrieval accuracy: Minimum confidence level for the knowledge base query to return results.
  • Recency importance (0-5): How important is the recency of the document in the knowledge base query. This setting is used to give more weight to the most recent documents.
  • Keywords importance (0-5): How important are the keywords in the knowledge base query. This setting is used to give more weight to the documents that contain the keywords.

ToothFairyAI's AI Inner Knowledge validation​

ToothFairyAI's validation system, will only allow answers from AI Inner Knowledge that are verified. This feature is not how the other Aprovided bys operate. Other systems will use their own reasoning model which does not have these strict fact checking measures in place like what ToothFairyAI does.

The AI Inner Knowledge answers generated by ToothFairyAI are checked by an algorithmic mathematical logic pattern. This pattern references answers provided by what knowledge / documentation is available for the questions asked to it. This is done by converting question texts into 1024 dimension metrics which are then used to compared against an agents selected topics.

The recommended percentage of confidence level used by ToothFairyAI for providing an answer is 60%. This ensures that the output from an agent is accurate to the users questions. However the user can set the minimum retrieval accuracy to a higher percentage if they require a higher level of confidence in the answers provided by the agent.

Functions settings​

Only available for Chat agents

Functions allow agents to consume APIs and DBs as a data source. Moreover, depending on the type, the function can provide suggestions or generate static responses for greater controllability of the agent's responses including via referencing entire web pages within the chat message. Functions are automatically enabled for retriever agents while for casual and coder agents, the functionality is not available. See Settings > Functions for more details.

Planner tools​

Only available for Planner agents.

The section comprises the following fields:

  • Available agents for planning: The agents that will be used to execute the tasks. If none are selected the planner will not have access to any agent preventing the correct execution of any plan.
  • Planning instructions: Additional custom instructions that the planner can use to better understand the domain in which tasks will be executed and how to plan accordingly.
  • Max execution steps: The maximum amount of steps the planner can execute.
  • Max re-attempts: The maximum amount of times the planner can re-attempt a failed task. This applies to all agents including coder agents with code execution enabled

Execution environments settings​

Only available for Coder agents with code execution enabled

Code environments allow agents to leverage predefined docker images and code snippets to execute code. Once assigned to an agent, ToothFairyAI agents will automatically detect and use the most suitable environment for the task at hand.

Only available for Chat agents

  • Allow internet search: When enabled, the agent will be able to search the internet for answers.
  • Max search results: The maximum number of search results to return from the internet search.
  • Excluded domains from search: Domains to exclude from the internet search separated by a comma.
  • Allow deep search: When enabled, the agent will be able to search the internet for answers in depth while when disabled the agent will only search the summaries of the results.

Agent Character​

Only available for Chat agents

The Agent Character are the input fields about the agent purpose, goals and what it should and should not talk about.

  • Agent role: This is to set the purpose of the agent. Any additional istruction for the agent should be added here.
  • Default answer: If a response cannot be found, this will be the response that is provided.
  • Goals: This is how the agent will fullfil its role.
  • Inhibition passage: Subjects that you do not want the agent to talk about.
  • Pertinance passage: Subjects to force the agent to focus on.

Agent tools​

Only available for Chat agents

  • Short term memory: Enables conversation summarisation for context used at each step of the conversation.
  • Multilingual: Enables the multi-language capability for the agent to reply in over 120 languages, however this can impact performance so turn on only if necessary.
  • Generate charts: If requested the agent can generate charts, tables and mind maps. This feature is available only when using Sorcerer and Mystica models.
  • Generate images: This setting allows the agents to generate new images based on the user input. ToothFairyAI agents generate by default four images at each interaction allowing users to further refine the output. This feature is available only in casual mode
  • Enable images upload: This setting will allow the user to upload images to the agent. - this feature is available only in retriever and casual mode and only one image can be uploaded for each message. The images must be in .png, .jpg or .jpeg format.
  • Enable audio upload: This setting will allow the user to upload audio files to the agent. - this feature is available only in retriever and casual mode and only one audio file can be uploaded for each message. The audio files must be in .wav or .mp4 format.
  • Enable video upload: This setting will allow the user to upload video files to the agent. - this feature is available only in retriever and casual mode and only one video file can be uploaded for each message. The video files must be in .mp4 format.
  • Enable docs upload: This setting will allow the user to upload documents to the agent. - this feature is available only in casual mode with up to 10 files uploaded at each turn. The docs must be of one of the following formats: .pdf, .csv, .doc, .docx, .xls, .xlsx, .html, .txt, .md .
  • Enhance answers with NER: This setting will allow the agent to used named entities in the response. - this feature is available only in retriever mode.
  • Retrieve images from docs: This setting will allow the agent to retrieve images and display them in the response. - this feature is available only in retriever mode. This feature is available only when using Sorcerer and Mystica models.
Tools availability for planner agents

The following tools are not available for Planner agents:

  • Short term memory
  • Multilingual
  • Enhance ansers with NER
  • Retrieve images from docs

Planner agents must allow for image, docs, video and audio uploads to be enabled in case the user wants to start a plan from one or more files.

Moderation and Feedback​

  • Allow feedback: This option allows the user to thumb up or down a response to show if the generated response is correct or not.
  • Content moderation: When enabled, the agent will filter out any profanity from the response by responding back to the user with the moderation rule applied when necessary.
  • Moderation rules: The list of rules the agent will use to moderate the content. The user can add or remove rules from the list.

Advanced Settings​

  • Summarised memory: When enabled, the agent will only reference a summary of the conversation rather than the whole set of messages.

  • Temperature (0.01-1): Determines how creative the response will be, higher meaning most creative. Reduce this number to the lowest value to reduce hallucinations

  • Max output tokens (50-4096): Determines the number of tokes (characters set) in the response. The larger the number the longer and more detailed the responsed can be. If the number is set too low some answers might get truncated.

  • Plain text output: Removes any form of styling from the responses.

  • Show response time: Displays the time from the first word to the end of the last word in the response.

  • Show detected language: This setting will display the language that what used in the response.

  • Restrict access: When enabled, the agent will only be accessible to the users specified in the user access settings and the admins of the workspace. When this mode is enabled the agent will not be accessible to the public through the web-widget and all chats will be private by default.

Multimodal

When Multimodal is enabled, the agent will be able to generate responses with images, charts, tables and mind maps. This feature is available only when using Sorcerer and Mystica models.

Web Widget​

Only available for Chat agents

  • Splash Logo: A logo you would like displayed in the widget.
  • First chat message: The initial message displayed when the chat is started.
  • Show agent name: When ticked, the agent name is displayed in the chat message. This is very useful when agent hand-off is enabled.
  • Show splash message: When ticked, the first chat message is displayed as splash message in the middle of the chat.
  • Input placeholder: Text displayed in the user input field.
  • Loading placeholder: Text displayed when the agent is retrieving the answer.
  • Disclaimer: A statement that explains rules, limits, or warnings.
  • Icons colour in light mode: The global icon colour in light mode.
  • Icons colour in dark mode: The global icon colour in dark mode.
  • Splash background colour in light mode: The background colour of the top bar where the logo is displayed in light mode.
  • Splash background colour in dark mode: The background colour of the top bar where the logo is displayed in dark mode.
  • Favicon url: The url of the favicon to be displayed in the browser tab. The favicon should be a square image and must be in .ico or .png format.
  • Initial questions: A list of questions that the agent can answer when the chat is started. The user can create up to three questions separated by a semicolon.
  • Go to widget: The url of the page where the user can directly interact with the agent. Available only when the agent is Block external usage is ticked off.
  • Block external usage: Blocks the widget from public access.
Widget

Chat agents by default are provided with both the public url of the agent if enabled and the code to embed the agent into any web-page as a chat widget.

Hosting and models​

  • LLM provider: The provider used to host the agent. Currently only ToothFairyAI is available as a provider for Base and Pro plans. For Enterprise plans, the user can choose between ToothFairyAI and their own hosting.
  • Base model: The model used by the agent to provide answers and generate outputs for the Chat agent, Business analyst and Content Creator agents.
    • Sorcerer: The default model used by any agent fine-tuned by ToothFairyAI.
    • Mystica A larger model more powerful and more accurate however slower fine-tuned by ToothFairyAI.
    • Mistral 7b: A small but very capable model based created by Mistral team.
    • Mistral 8x7b: A larger model provided by Mistral team.
    • Llama 3 8b: The legacy model created by Meta AI in its smallest version.
    • Llama 3.1 8b: The latest model created by Meta AI in its smallest version and larger context window.
    • Gemma 2 9b: The latest open source model provided by Google
    • Gemma 2 27b: The largest open source model provided by Google
    • Llama 3 70b: The legacy model created by Meta AI in its larger version (not available for Base plan).
    • Mistral 8x22b: The largest open-sourced model provided by Mistral team (not available for Base plan).
    • Qwen 2 72b: The largest open-sourced model provided by the Qwen team (not available for Base plan).
    • Llama 3.1 70b: The latest model created by Meta AI in its largest version and larger context window (not available for Base plan).
    • Llama 3.1 405b: The largest open-sourced and state of the art model provided by Meta (not available for Base plan).
  • Functions provider: The provider used to host the functions. Currently only ToothFairyAI is available as a provider for Base and Pro plans. For Enterprise plans, the user can choose between ToothFairyAI and their own hosting.
  • Functions model: The model used by ToothFairyAI to select the functions to be used by the agent.
    • Sorcerer: The default model used by any agent fine-tuned by ToothFairyAI.
    • Mystica A larger model more powerful and more accurate however slower.

The models list can be expanded by 3rd party providers. Contact us for more information.

Local hosting

For Enterprise plans, the user can choose to host the agent and functions locally on their own servers or on a cloud provider of their choice. Contant us for more information.