app.py

import os
import streamlit as st
from langchain_community.graphs import Neo4jGraph
from langchain_groq import ChatGroq
from langchain.chains import GraphCypherQAChain
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
NEO4J_URI = os.getenv("NEO4J_URI")
NEO4J_USERNAME = os.getenv("NEO4J_USERNAME")
NEO4J_PASSWORD = os.getenv("NEO4J_PASSWORD")
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

# Initialize Neo4j graph
graph = Neo4jGraph(url=NEO4J_URI, username=NEO4J_USERNAME, password=NEO4J_PASSWORD)

# Load movie dataset into Neo4j
moview_query = """
LOAD CSV WITH HEADERS FROM
'https://raw.githubusercontent.com/tomasonjo/blog-datasets/main/movies/movies_small.csv' as row
MERGE(m:Movie{id:row.movieId})
SET m.released = date(row.released),
    m.title = row.title,
    m.imdbRating = toFloat(row.imdbRating)
FOREACH (director in split(row.director, '|') | 
    MERGE (p:Person {name:trim(director)})
    MERGE (p)-[:DIRECTED]->(m))
FOREACH (actor in split(row.actors, '|') | 
    MERGE (p:Person {name:trim(actor)})
    MERGE (p)-[:ACTED_IN]->(m))
FOREACH (genre in split(row.genres, '|') | 
    MERGE (g:Genre {name:trim(genre)})
    MERGE (m)-[:IN_GENRE]->(g))
"""
graph.query(moview_query)
graph.refresh_schema()

# Initialize LLM
llm = ChatGroq(groq_api_key=GROQ_API_KEY, model_name="Gemma2-9b-It")

# Create QA Chain
chain = GraphCypherQAChain.from_llm(graph=graph, llm=llm, verbose=True)

# Streamlit UI
st.title("Movie Director Finder")

query = st.text_input("Enter your query:", "Who was the director of the movie Casino")
if st.button("Find Director"):
    response = chain.invoke({"query": query})
    st.write(response)