Knowledge Base Actions

Warning: This feature is experimental. We introduce experimental features to get feedback from our community, so we encourage you to try it out! However, the functionality might be changed or removed in the future. If you have feedback (positive or negative) please share it with us on the forum.

Using `ActionQueryKnowledgeBase`

Knowledge base actions enable you to handle the following kind of conversations:

A common problem in conversational AI is that users do not only refer to certain objects by their names, but also use reference terms such as “the first one” or “it”.

To handle the above challenges, Rasa can be integrated with knowledge bases. To use this integration, you can create a custom action that inherits from ActionQueryKnowledgeBase, a pre-written custom action that contains the logic to query a knowledge base for objects and their attributes.

You can find a complete example in examples/knowledgebasebot ( knowledge base bot), as well as instructions for implementing this custom action below.

Create a Knowledge Base

The data used to answer the user’s requests will be stored in a knowledge base. A knowledge base can be used to store complex data structures. We suggest you get started by using the InMemoryKnowledgeBase.

To initialize an InMemoryKnowledgeBase, you need to provide the data in a json file. The following example contains data about restaurants and hotels.

{
    "restaurant": [
        {
            "id": 0,
            "name": "Donath",
            "cuisine": "Italian",
            "outside-seating": true,
            "price-range": "mid-range"
        },
        {
            "id": 1,
            "name": "Berlin Burrito Company",
            "cuisine": "Mexican",
            "outside-seating": false,
            "price-range": "cheap"
        },
        {
            "id": 2,
            "name": "I due forni",
            "cuisine": "Italian",
            "outside-seating": true,
            "price-range": "mid-range"
        }
    ],
    "hotel": [
        {
            "id": 0,
            "name": "Hilton",
            "price-range": "expensive",
            "breakfast-included": true,
            "city": "Berlin",
            "free-wifi": true,
            "star-rating": 5,
            "swimming-pool": true
        },
        {
            "id": 1,
            "name": "Hilton",
            "price-range": "expensive",
            "breakfast-included": true,
            "city": "Frankfurt am Main",
            "free-wifi": true,
            "star-rating": 4,
            "swimming-pool": false
        },
        {
            "id": 2,
            "name": "B&B",
            "price-range": "mid-range",
            "breakfast-included": false,
            "city": "Berlin",
            "free-wifi": false,
            "star-rating": 1,
            "swimming-pool": false
        }
    ]
}

Define the NLU Data

In this section:

we will introduce a new intent, query_knowledge_base
we will to annotate mention entities so that our model detects indirect mentions of objects like “the first one”

For the bot to understand that the user wants to retrieve information from the knowledge base, you need to define a new intent. We will call it query_knowledge_base.

Create an Action to Query your Knowledge Base

To create your own knowledge base action, you need to inherit ActionQueryKnowledgeBase and pass the knowledge base to the constructor of ActionQueryKnowledgeBase.

from rasa_sdk.knowledge_base.storage import InMemoryKnowledgeBase
from rasa_sdk.knowledge_base.actions import ActionQueryKnowledgeBase

class MyKnowledgeBaseAction(ActionQueryKnowledgeBase):
    def __init__(self):
        knowledge_base = InMemoryKnowledgeBase("data.json")
        super().__init__(knowledge_base)

How It Works

ActionQueryKnowledgeBase looks at both the entities that were picked up in the request as well as the previously set slots to decide what to query for.

Query the Knowledge Base for Objects

In order to query the knowledge base for any kind of object, the user’s request needs to include the object type.

Query the Knowledge Base for an Attribute of an Object

If the user wants to obtain specific information about an object, the request should include both the object and attribute of interest.

Resolve Mentions

Following along from the above example, users may not always refer to restaurants by their names. Users can either refer to the object of interest by its name or use indirect references.

Customization

You can overwrite the following two functions of ActionQueryKnowledgeBase to customize what the bot says to the user:

utter_objects()
utter_attribute_value()

See the example bot for an example implementation of an InMemoryKnowledgeBase.