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.

ParameterTypeDefaultDescription
readerOptional[Reader]NoneReader to read the documents
vector_dbOptional[VectorDb]NoneVector db to store the knowledge base
num_documentsint2Number of relevant documents to return on search
optimize_onOptional[int]1000Number of documents to optimize the vector db on
driverstr"knowledge"Driver for the Assistant knowledge

Function Reference

Properties

PropertyTypeDescription
document_listsIterator[List[Document]]Iterator that yields lists of documents in the knowledge base
async_document_listsAsyncIterator[List[Document]]Async iterator that yields lists of documents in the knowledge base

Search Methods

MethodParametersReturn TypeDescription
searchquery: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = NoneList[Document]Returns relevant documents matching a query
async_searchquery: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = NoneList[Document]Asynchronously returns relevant documents matching a query

Loading Methods

MethodParametersReturn TypeDescription
loadrecreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad the knowledge base to the vector db
aloadrecreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load the knowledge base to the vector db
load_documentsdocuments: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad documents to the knowledge base
async_load_documentsdocuments: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load documents to the knowledge base
load_documentdocument: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a single document to the knowledge base
async_load_documentdocument: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load a single document to the knowledge base
load_dictdocument: Dict[str, Any], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a dictionary representation of a document to the knowledge base
load_jsondocument: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a JSON representation of a document to the knowledge base
load_texttext: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a text to the knowledge base

Utility Methods

MethodParametersReturn TypeDescription
existsNoneboolReturns True if the knowledge base exists
deleteNoneboolClear the knowledge base

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.

ParameterTypeDefaultDescription
readerOptional[Reader]NoneReader to read the documents
vector_dbOptional[VectorDb]NoneVector db to store the knowledge base
num_documentsint2Number of relevant documents to return on search
optimize_onOptional[int]1000Number of documents to optimize the vector db on
driverstr"knowledge"Driver for the Assistant knowledge

Function Reference

Properties

PropertyTypeDescription
document_listsIterator[List[Document]]Iterator that yields lists of documents in the knowledge base
async_document_listsAsyncIterator[List[Document]]Async iterator that yields lists of documents in the knowledge base

Search Methods

MethodParametersReturn TypeDescription
searchquery: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = NoneList[Document]Returns relevant documents matching a query
async_searchquery: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = NoneList[Document]Asynchronously returns relevant documents matching a query

Loading Methods

MethodParametersReturn TypeDescription
loadrecreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad the knowledge base to the vector db
aloadrecreate: bool = False, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load the knowledge base to the vector db
load_documentsdocuments: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad documents to the knowledge base
async_load_documentsdocuments: List[Document], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load documents to the knowledge base
load_documentdocument: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a single document to the knowledge base
async_load_documentdocument: Document, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneAsynchronously load a single document to the knowledge base
load_dictdocument: Dict[str, Any], upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a dictionary representation of a document to the knowledge base
load_jsondocument: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a JSON representation of a document to the knowledge base
load_texttext: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = NoneNoneLoad a text to the knowledge base

Utility Methods

MethodParametersReturn TypeDescription
existsNoneboolReturns True if the knowledge base exists
deleteNoneboolClear the knowledge base