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

• Create a Knowledge Base
• Define the NLU Data
• Create an Action to Query your Knowledge Base

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". We need to keep track of the information that was presented to resolve these mentions to the correct object.

In addition, users may want to obtain detailed information about objects during a conversation. For example, whether a restaurant has outside seating, or how expensive it is. In order to respond to those user requests, knowledge about the restaurant domain is needed. Since the information is subject to change, hard-coding the information isn’t the solution.

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.

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.

Once the data is defined in a json file, called, for example, data.json, you will be able to use this data file to create your InMemoryKnowledgeBase, which will be passed to the action that queries the knowledge base.

{
    "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
        }
    ]
}

Every object in your knowledge base should have at least the "name" and "id" fields to use the default implementation.

Define the NLU Data

In this section:

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

## intent:query_knowledge_base
- what [restaurants](object_type:restaurant) can you recommend?
- list some [restaurants](object_type:restaurant)
- can you name some [restaurants](object_type:restaurant) please?
- can you show me some [restaurant](object_type:restaurant) options
- list [German](cuisine) [restaurants](object_type:restaurant)
- do you have any [mexican](cuisine) [restaurants](object_type:restaurant)?
- do you know the [price range](attribute:price-range) of [that one](mention)?
- what [cuisine](attribute) is [it](mention)?
- do you know what [cuisine](attribute) the [last one](mention:LAST) has?
- does the [first one](mention:1) have [outside seating](attribute:outside-seating)?
- what is the [price range](attribute:price-range) of [Berlin Burrito Company](restaurant)?

Create an Action to Query your Knowledge Base

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)

Adding all the relevant pieces, the action is now able to query the knowledge base.