rag.chat.processQuery

The method generates a response to the user query within a chat. The history in the knowledge base chat is taken into account for the response.

caution

The method is available only in the ECMAScript 6 runtime and is asynchronous.

Syntax

The method accepts the following arguments:

Argument	Type	Description	Required
secretName	String	Name of the knowledge base secret.	Yes
chatId	Number	Chat identifier. Use the identifier returned by the $rag.chat.create method.	Yes
query	String	Text of the user query.	Yes
settings	Object	Query processing settings. By default, the settings from the chat are used. The settings format matches the format of the identically named object in the POST /api/knowledge-hub/chat/{chatId}/query request in the Tovie Data Agent API.	No
timeout	Number	Timeout in milliseconds for the method execution. If the timeout is exceeded, an error will occur. By default, the timeout is not set.	No

You can pass arguments to the method in different ways.

Positional arguments

Specify the arguments in order:

await $rag.query.processQuery("MyKnowledgeHub", 12345, "What does the Example service do?", undefined, 5000);

Via object

Pass an object whose fields match the names of the arguments:

await $rag.query.processQuery({
    secretName: "MyKnowledgeHub",
    chatId: 12345,
    query: "What does the Example service do?",
    timeout: 5000
});

Return value

The method returns an object with the result of the request processing. The response field contains the answer to the user question.

{
    "id": 11111,
    "chatId": 12345,
    "request": "What does the Example service do?",
    "status": "FINISHED",
    "createdAt": "2024-12-03T16:43:30.279222Z",
    "response": "The example service processes user requests …",
    "updatedAt": "2024-12-03T16:44:42.774798Z",
    "comment": null
}

The object has the same format as the response to the POST /api/knowledge-hub/chat/{chatId}/query request in the Tovie Data Agent API.

How to use

state: Answer
    intent!: /question
    scriptEs6:
        $client.chat = $client.chat || await $rag.chat.create("MyKnowledgeHub", "My chat");

        $rag.chat.processQuery("MyKnowledgeHub", $client.chat.id, $request.query)
            .then(chatResponse => {
                $conversationApi.sendTextToClient(chatResponse.response);
            })
            .catch(error => {
                $conversationApi.sendTextToClient("An error occured: " + error);
            });

In this state:

1. If there is no chat yet, the bot creates a chat.
2. The bot sends a response from the knowledge base to the user.

tip

For examples of working with the knowledge base and different ways to send requests to it, see Use in script.