LightRAG

Insert a PDF and a Wikipedia page into a LightRAG knowledge base and query it with an agent.

Prepare the sample input files in the directory where you will run the Python example:

mkdir -p data
curl --fail --location https://raw.githubusercontent.com/agno-agi/agno/8f36eaf2d18e91afa7b327eec66a3cd3685dcb87/cookbook/07_knowledge/testing_resources/cv_1.pdf --output data/cv_1.pdf

Code

lightrag_db.py
from os import getenv

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.wikipedia_reader import WikipediaReader
from agno.vectordb.lightrag import LightRag

vector_db = LightRag(
    api_key=getenv("LIGHTRAG_API_KEY"),
)

knowledge = Knowledge(
    name="My LightRag Knowledge Base",
    description="This is a knowledge base that uses a LightRag Vector DB",
    vector_db=vector_db,
)

knowledge.insert(
    name="CV",
    path="data/cv_1.pdf",
    metadata={"doc_type": "cv"},
)

knowledge.insert(
    name="Manchester United",
    topics=["Manchester United"],
    reader=WikipediaReader(),
)

knowledge.insert(
    name="Manchester United",
    url="https://en.wikipedia.org/wiki/Manchester_United_F.C.",
)

agent = Agent(
    knowledge=knowledge,
    search_knowledge=True,
    read_chat_history=False,
)

agent.print_response("What skills does Jordan Mitchell have?", markdown=True)

agent.print_response(
    "In what year did Manchester United change their name?", markdown=True
)

Usage

This example requires a running LightRAG server. LightRag connects to http://localhost:9621 by default. Pass server_url to use a different address.

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Install dependencies

uv pip install -U agno pypdf wikipedia beautifulsoup4 openai

Set environment variables

export LIGHTRAG_API_KEY="your-lightrag-api-key"
export OPENAI_API_KEY=xxx

Run Agent

python lightrag_db.py