# Assistants

## Create an assistant The Assistant detail consists of these fields separated into 5 section, which are

### Assistant Setting * **Assistant Name:** Limit the text type to a maximum of 255 characters. * **Prompt:** Input your custom prompt instructions here. If you need some inspiration, we have a prompt library you can browse to see if something there might suit your needs. * **Type:** BOTs+ currently only supports Questions & Answers. * **Question Input Source:** Choose between generating answers based on the original question or a translated version into English. * **Greeting Message (optional):** *This setting only applies to the ASAP sandbox.* Show a pre-defined greeting message when a user starts a new session or opens the chat. This will not get sent out to external channels. * **Style**: Pick the temperature of the response from the LLM. Precise (temp = 0.2) causes the LLM to respond in more consistent ways based on the provided context. Create (temp = 0.8) causes the LLM to respond in more diverse and creative ways, while still referencing the provided context. * **Session Reset Timer**: When set to 0, this function is never time out. When a value is selected (1 - 12), the user's session will soft reset if no message is sent to BOT+ during that time period. ### Search & Fulfillments * **Fulfillments (optional):** Connect a fulfillment to attach to your assistant. BOTs+ will search the documents attached to these fulfilment in order to find relevant documents to send to the LLM as part of the Prompt payload. ### Answer Generation * **Model**: Pick your desired LLM. At the moment, BOTs+ only supports GPT-3.5 and GPT-4. * GPT-3.5 is suitable for most tasks however is weak when it comes to logic, pure creation, understanding of sciences, and handling of complex enquires. * GPT-4 is a better choice for long and complex questions, as well as sentiment analysis, working with numbers, and connecting the dots on discrete pieces of information. ### Validator * **Enable Validation:** enable to select validation method which default to KM Confidence Threshold

* KM Confidence Threshold option will filter out all searched chunks that are lower than the set score. * If disable this field, it means to ignore the validation and utilize all searched chunk, or as setting 0% of Confidence Threshold.

* **AI Goal Affirmation (optional):** A set of priority instructions that will be sent to the LLM. This is appended to the Prompt Payload towards the button, which tends to make the LLM give it a higher priority compared to the main Prompt Instructions. * **Fallback Message:** Provide a fallback message when the assistant cannot generate an answer using fulfillments, limit to 500 characters. ### Integration * **Event Webhook URL (optional):** Input your webhook URL for ASAP to send events to. ASAP only currently sends a session reset event. * **Response URL (optional):** If you are sending out to an external channel, please input the webhook URL here.