LanceDB Vector Database

Use LanceDB as a vector database for your Knowledge Base.

Setup

uv pip install lancedb typer pypdf openai agno

Example

agent_with_knowledge.py

import typer
from typing import Optional
from rich.prompt import Prompt

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.lancedb import LanceDb
from agno.vectordb.search import SearchType

# LanceDB Vector DB
vector_db = LanceDb(
    table_name="recipes",
    uri="/tmp/lancedb",
    search_type=SearchType.keyword,
)

# Knowledge Base
knowledge_base = Knowledge(
    vector_db=vector_db,
)

def lancedb_agent(user: str = "user"):
    agent = Agent(
        knowledge=knowledge_base,
        debug_mode=True,
    )

    while True:
        message = Prompt.ask(f"[bold] :sunglasses: {user} [/bold]")
        if message in ("exit", "bye"):
            break
        agent.print_response(message, session_id=f"{user}_session")

if __name__ == "__main__":
    # Comment out after first run
    knowledge_base.insert(
        url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
    )

    typer.run(lancedb_agent)

Async Support ⚡

LanceDB also supports asynchronous operations, enabling concurrency and leading to better performance.

async_lance_db.py

# install lancedb - `pip install lancedb`
import asyncio

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.vectordb.lancedb import LanceDb

# Initialize LanceDB
vector_db = LanceDb(
    table_name="recipes",
    uri="tmp/lancedb",  # You can change this path to store data elsewhere
)

# Create knowledge base
knowledge_base = Knowledge(
    vector_db=vector_db,
)
agent = Agent(knowledge=knowledge_base, debug_mode=True)

if __name__ == "__main__":
    # Load knowledge base asynchronously
    asyncio.run(knowledge_base.ainsert(
            url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
        )
    )

    # Create and use the agent asynchronously
    asyncio.run(agent.aprint_response("How to make Tom Kha Gai", markdown=True))

Use ainsert() and aprint_response() methods with asyncio.run() for non-blocking operations in high-throughput applications.

LanceDb Params

Parameter	Type	Default	Description
uri	str	/tmp/lancedb	The URI to connect to.
table	LanceTable	-	The Lance table to use.
table_name	str	-	The name of the table to use.
connection	DBConnection	-	The database connection to use.
api_key	str	-	The API key to use.
embedder	Embedder	-	The embedder to use.
search_type	SearchType	vector	The search type to use.
distance	Distance	cosine	The distance to use.
nprobes	int	-	The number of probes to use. More Info
reranker	Reranker	-	The reranker to use. More Info
use_tantivy	bool	False	Deprecated. LanceDB now uses native FTS; this parameter is ignored.
on_bad_vectors	str	-	What to do if the vector is bad. One of "error", "drop", "fill", "null".
fill_value	float	-	The value to fill the vector with if on_bad_vectors is "fill".