Skip to main content
A knowledge store is a searchable collection of documents. It takes a query and returns the documents that match it. Mantle ships faiss, qdrant, and milvus stores. Write your own when your search backend is none of those, or subclass a built-in to change how it searches.
Mantle checks each knowledge_stores: entry when you run rasa train, but it does not query a knowledge store yet. The search_knowledge tool reads only the local index built from references/. See What’s next. You can write and register a knowledge store now so it is ready, but nothing calls its search method yet.

Before you start

Put your code in a package next to agent.yml: a folder named addons/ with an empty __init__.py file. Start rasa from the project root so the package can be imported.

Subclass KnowledgeStore

Import Document, KnowledgeStore, KnowledgeStoreSettings, SearchRequest, SearchResult, and SearchResultList from rasa.api.knowledge.v1. Implement connect and search. The base class keeps the embeddings client in self.embeddings, so you do not need to override __init__.
addons/custom_knowledge_store.py
This example searches a list held in code, so it runs as written. Replace FAQ_DOCUMENTS with a load from your index. The example matches words and ignores request.threshold. A vector store would use the threshold to drop weak matches. Add an embeddings model group in integrations.yml and name it in the entry. The group must be a text embeddings model:
integrations.yml
Each entry under knowledge_stores: accepts exactly three keys: id, type, and embeddings. Any other key fails validation, so a store that needs its own connection settings cannot take them yet. Store ids must be unique.

Subclass the built-in FAISS store

To change how the faiss store returns results and keep the rest, subclass FAISSStore. This example returns at most three hits:
addons/custom_faiss_store.py
integrations.yml
Keep type set to the class path, because the built-in name faiss selects the built-in class. Unlike other stages, knowledge_stores has no key for settings such as an index path. A built-in FAISS store that needs an index path cannot be configured from integrations.yml yet.

Methods

Versioning

The import rasa.api.knowledge.v1 is the version. YAML names only the class. See Custom integrations: Versioning.