import streamlit as st
import weaviate
from llama_index import download_loader

WeaviateReader = download_loader('WeaviateReader')

Define the user inputs for connection details

st.sidebar.title('Connect to Your GRE Study Assistant')
username = st.sidebar.text_input('Username', '')
password = st.sidebar.text_input('Password', '', type='password')
cluster_id = st.sidebar.text_input('Cluster ID', '')
class_name = st.sidebar.text_input('Class Name', '')
property1 = st.sidebar.text_input('Property 1', '')
property2 = st.sidebar.text_input('Property 2', '')

Initialize WeaviateReader with the given credentials

resource_owner_config = weaviate.AuthClientPassword(
username = username,
password = password,
)

reader = WeaviateReader(f"https://{cluster_id}.semi.network/", auth_client_secret=resource_owner_config)

Load data using class_name and properties

if st.sidebar.button('Load data'):
documents = reader.load_data(
class_name=class_name,
properties=[property1, property2],
separate_documents=True
)

Display documents

st.write(documents)

Define a text area for a custom GraphQL query

query = st.sidebar.text_area('Enter your GraphQL query', """
{
Get {
<class_name> {


...
}
}
}
""")

Execute GraphQL query

if st.sidebar.button('Execute query'):
documents = reader.load_data(graphql_query=query, separate_documents=True)

Display documents

st.write(documents)

Use Vercel, Postgres, or Supabase. Nothing fancy