The CSVKnowledgeBase reads local CSV files, converts them into vector embeddings and loads them to a vector database.

​
Usage

We are using a local PgVector database for this example. Make sure it’s running

from agno.knowledge.csv import CSVKnowledgeBase
from agno.vectordb.pgvector import PgVector

knowledge_base = CSVKnowledgeBase(
    path="data/csv",
    # Table name: ai.csv_documents
    vector_db=PgVector(
        table_name="csv_documents",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
)

Then use the knowledge_base with an Agent:

from agno.agent import Agent
from knowledge_base import knowledge_base

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)
agent.knowledge.load(recreate=False)

agent.print_response("Ask me about something from the knowledge base")

​
Params

ParameterTypeDefaultDescription
pathUnion[str, Path]-Path to the CSV file
readerCSVReaderCSVReader()A CSVReader that reads the CSV file and converts it into Documents for the vector database

CSVKnowledgeBase is a subclass of the AgentKnowledge class and has access to the same params.

​
Developer Resources

CombinedCSV URLs