Class: ChatBotService

ChatBotService()

The Chatbot module enables you to create custom chatbots. You can give it a name, a purpose and connect it to your document repository so that it informs its responses to users from your ingested documents.

Constructor

new ChatBotService()

Source:

Methods

call(user, message, chatbot_id, user_id, mode, session_idopt, previous_messagesopt, bot_document_idsopt, context_document_idsopt, engineopt) → {Promise.<Object>}

Parameters:
Name Type Attributes Default Description
user string The ID of the user accessing the Soffos API. This string will be used for throttling and profanity tracking. Soffos assumes that the owner of the api is an application (app) and that app has users. Soffos API will accept any string."
message string The user's message to the chatbot
chatbot_id string The chatbot's id.
user_id string A unique user id. It is recommended that your provide a UUID.
mode string The value can only be one of: open, closed, hybrid.
session_id string <optional>
null A unique session id for mapping the records to your application. It is recommended that you provide a UUID. If not provided, the system will not store any information regarding the call and will use the value of "previous_messages" as the conversation history.
previous_messages Array <optional>
null This field can be used to provide the conversation history. It is ignored if a "session_id" is provided, in which case the system will used the stored interactions from that session as conversation history.
bot_document_ids Array <optional>
null Here you can specify documents that describe the bot's background and its perception of itself.
context_document_ids Array <optional>
null Pass the ids of the documents that you wish to inform your bot with for the specific user/session. Applicable for closed and hybrid modes as described above.
engine string <optional>
null The LLM engine to be used.
Source:
Returns:
response - The agent's response session_name - The session's name which is generated after 3 interactions. messages - A list of the conversation's messages so far. context - The context that was made available to the agent for responding to the user's last message.
Type
Promise.<Object>
Example
Examples are available at "https://github.com/Soffos-Inc/soffosai-js/tree/master/samples"

setInputConfigs(name, message, chatbot_id, user_id, mode, session_idopt, previous_messagesopt, bot_document_idsopt, context_document_idsopt, engineopt)

Parameters:
Name Type Attributes Default Description
name string Reference name of this Service. It will be used by the Pipeline to reference this Service.
message string | InputConfig The user's message to the chatbot
chatbot_id string | InputConfig The chatbot's id.
user_id string | InputConfig A unique user id. It is recommended that your provide a UUID.
mode string | InputConfig The value can only be one of: open, closed, hybrid.
session_id string | InputConfig <optional>
null A unique session id for mapping the records to your application. It is recommended that you provide a UUID. If not provided, the system will not store any information regarding the call and will use the value of "previous_messages" as the conversation history.
previous_messages Array | InputConfig <optional>
null This field can be used to provide the conversation history. It is ignored if a "session_id" is provided, in which case the system will used the stored interactions from that session as conversation history.
bot_document_ids Array | InputConfig <optional>
null Here you can specify documents that describe the bot's background and its perception of itself.
context_document_ids Array | InputConfig <optional>
null Pass the ids of the documents that you wish to inform your bot with for the specific user/session. Applicable for closed and hybrid modes as described above.
engine string <optional>
null The LLM engine to be used.
Source: