• In order to use the agent, you need to first setup Milvus database. Follow the guide in the following link to set up a standalone version of Milvus database in Docker : https://milvus.io/docs/install_standalone-docker.md#Install-Milvus-in-Docker
• Also install Attu which is a milvus administration tool. You can run the following docker command to install Attu:

docker run -d -p 8000:3000 zilliz/attu:v2.5.6

It will run Attu on port 8000. You can access it by going to http://localhost:8000.

In the Milvus Address enter http://{milvus server IP}:19530 and you can keep the remaining values the same. Then click on Connect. You can now see the collections and the vectors stored in the Milvus database.

Note: milvus server IP will be the IP address of your machine and not localhost.

• After setting up Milvus, you can first run scraper.py to scrape the data from the website and store it in the database.
• Then you can either directly run main_starlette.py or if you prefer a UI you can run the following command:

chainlit run --port 8081 chainlit_ui.py