AgentKnowledge - Agno

AgentKnolwedge is the base class for all knowledge base classes in Agno. It provides common functionality and parameters that are inherited by all other knowledge base classes.

Parameter	Type	Default	Description
`reader`	`Optional[Reader]`	`None`	Reader to read the documents
`vector_db`	`Optional[VectorDb]`	`None`	Vector db to store the knowledge base
`num_documents`	`int`	`2`	Number of relevant documents to return on search
`optimize_on`	`Optional[int]`	`1000`	Number of documents to optimize the vector db on
`driver`	`str`	`"knowledge"`	Driver for the Assistant knowledge

Function Reference

Properties

Property	Type	Description
`document_lists`	`Iterator[List[Document]]`	Iterator that yields lists of documents in the knowledge base
`async_document_lists`	`AsyncIterator[List[Document]]`	Async iterator that yields lists of documents in the knowledge base

Search Methods

Method	Parameters	Return Type	Description
`search`	`query: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = None`	`List[Document]`	Returns relevant documents matching a query
`async_search`	`query: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = None`	`List[Document]`	Asynchronously returns relevant documents matching a query

Loading Methods

Method	Parameters	Return Type	Description
`load`	`recreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load the knowledge base to the vector db
`aload`	`recreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Asynchronously load the knowledge base to the vector db
`load_documents`	`documents: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load documents to the knowledge base
`async_load_documents`	`documents: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Asynchronously load documents to the knowledge base
`load_document`	`document: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load a single document to the knowledge base
`async_load_document`	`document: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Asynchronously load a single document to the knowledge base
`load_dict`	`document: Dict[str, Any], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load a dictionary representation of a document to the knowledge base
`load_json`	`document: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load a JSON representation of a document to the knowledge base
`load_text`	`text: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None`	`None`	Load a text to the knowledge base

Utility Methods

Method	Parameters	Return Type	Description
`exists`	None	`bool`	Returns True if the knowledge base exists
`delete`	None	`bool`	Clear the knowledge base

IBM WatsonX Arxiv

On this page

Function Reference
Properties
Search Methods
Loading Methods
Utility Methods