Bot configurations
1. Configurations
Basic
Prompt
Define the prompt (instructions) that will guide the AI agent's behavior and responses. The prompt can include specific instructions, context information, and any other relevant details to help the agent understand the user's intent and provide accurate and relevant responses.
More tips on prompt writing in the Bots Section.
Advanced
Upload Logo
Format requirements: 1024 x 1024, .jpg, .png, 1MB max
Upload an image that will be associated with your AI servant or bot
Title
Name or title for your AI bot will be automatically derived from yout prompt. Alternatively, you can give your bot your own name.
Fault tolerance
Maximum amount of errors accumilated, will replenish after the function returns a correct response. Set to 0 by default.
Auto retry
Number of attemts to retry a function after a singular error. Set to 0 by default.
Number of output per request
Number of results the LLM generates from a single input. Set to 1 by default.
Image
Format requirements: 1024 x 1024, .jpg, .png, 1MB max
Upload an image that will be associated with your AI servant or bot
Servant type
Cutom: using RAG mechanism of Firstbot
Open AI Assistant: using Open AI RAG mechanism
Template: using template RAG mechanism
Title
Name or title for your AI bot.
Fault tolerance
Maximum amount of errors accumilated, will replenish after the function returns a correct response. Set to 0 by default.
Auto retry
Number of attemts to retry a function after a singular error. Set to 0 by default.
Number of output per request
Number of results the LLM generates from a single input. Set to 1 by default.
2. AI Model
When configuring your bot, you'll need to select a suitable AI model to power its intelligence and capabilities. Generally, you'll want to choose an AI model that best aligns with the intended purpose and use case of your bot.
Max tokens
Depending on the model used, requests will be limited to the specified maximum number of tokens shared between prompt and completion. Maximum number of tokens will define the size of input data that can be processed and the size of the response.
For more information, read Open AI's article about tokens.
Input type
Specify format of the data that your bot will receive from users. This can include options such as plain text or multimedia content (e.g., images, audio).
Choosing the appropriate input type ensures that your bot can properly process and respond to the information provided by users.
Pricing
The pricing for the AI model you select will depend on factors such as the model's complexity or the volume of usage.
Consider the pricing model and ensure that it aligns with your budget and the expected usage of your bot.
3. Memory
Memory Setting
Enabling memory (RAG) will allow your bot to remember your interactions and learn based on them, instead of only using the AI Model and the prompted instructions. This feature might be useful for more personalized user experience.
However, if you are creating a bot that should stay more objective and follow the prompt more strictly, you might consider disabling the memory feature.
Cutom RAG
Using a custom RAG mechanism. Porvides with a choice of embeding model.
Open AI Assistant*
Managing memory using Open AI RAG mechanism and embeding model. Open AI embeding model has high performance but is also more costly.
* Only available if you choose an AI Model from Open AI
Embeding Model
If you choose a custom RAG mechanism, you will be presented with 2 options of embeding models.
The choice of embedding model can significantly impact the agent's overall functionality, including its language understanding, knowledge management, dialogue coherence, generalization, and computational efficiency.
Text Embedding Ada
Good performance, medium price.
All MPNet Base V2
Performance less consistent but the price is more affordable.
4. Tool
Usage mode
Select usage mode to control what tools that are connected to your bot node will be ative. This feature is useful during testing and development of your agent.
Auto
The bot (LLM) automatically selects the most suitable tool.
None
The bot (LLM) does not use any tools, even if they are available or enabled.
JSON
The bot (LLM) must return a JSON object instead of a summarized text message. This is useful when chaining one bot to another.
5. Channel
Each bot can support 1 external channel of communication such as a Telegram or a Whatsapp Business chatbot to facilitate easier communication.
Telegram
Connecting your bot to a telegram bot is an easy way to provie more convenient and faster access to your agent. For detailed instructions, read the Tutorial.
Telegram bot token
Provide the API token for your Telegram bot. This allows your agent to send and receive messages through the Telegram platform.
WhatsApp
Connecting a WhatsApp account will require a Meta Developer account. To get help on the setup, contact us at [email protected] and we will instruct you through the process.
WhatsApp business ID
Enter the unique Business ID associated with your WhatsApp Business account. This ID is used to identify your agent within the WhatsApp ecosystem.
WhatsApp businss phone number
Specify the phone number linked to your WhatsApp Business account. This number will be used as the sender/recipient for all WhatsApp messages.
QR Code
After succesfully connecting one or multiple communication channels, a QR code to access chats through Telegram or Whatsapp will be displayed in this section.
6. Resources
After seting up your bot, if you connect it to Tools that require connections to other online platforms such as social media, all the connected and authorized accounts (e.g Facebook, Google, Pinterest) will be listed here.
For example, if you install a social media management tool, after you authorized your social media account, it will redirect to the engine from the Open Authorization permission page.
Last updated