The JSON Reader with asynchronous processing allows you to handle JSON files efficiently and integrate them with knowledge bases.

​
Code

examples/concepts/knowledge/readers/json_reader_async.py
import json
import asyncio
from pathlib import Path

from agno.agent import Agent
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.json_reader import JSONReader
from agno.vectordb.pgvector import PgVector

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

# Create test JSON data
json_path = Path("tmp/test.json")
json_path.parent.mkdir(exist_ok=True)
test_data = {
    "users": [
        {"id": 1, "name": "John Doe", "role": "Developer"},
        {"id": 2, "name": "Jane Smith", "role": "Designer"}
    ],
    "project": "Knowledge Base System"
}
json_path.write_text(json.dumps(test_data, indent=2))

knowledge = Knowledge(
    vector_db=PgVector(
        table_name="json_documents",
        db_url=db_url,
    ),
)

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

async def main():
    # Add JSON content to knowledge base
    await knowledge.add_content_async(
        path=json_path,
        reader=JSONReader(),
    )

    # Query the knowledge base
    await agent.aprint_response(
        "What information is available about the users?",
        markdown=True
    )

if __name__ == "__main__":
    asyncio.run(main())

​
Usage

1

Create a virtual environment

Open the Terminal and create a python virtual environment.
python3 -m venv .venv
source .venv/bin/activate
2

Install libraries

pip install -U sqlalchemy psycopg pgvector agno openai
3

Set environment variables

export OPENAI_API_KEY=xxx
4

Run PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agno/pgvector:16
5

Run Agent

python examples/concepts/knowledge/readers/json_reader_async.py

​
Params

ParameterTypeDefaultDescription
pathPathRequiredPath to JSON file to read
chunkboolFalseWhether to chunk the documents (overrides base Reader default)