GraphAcademy

Neo4j & LLM Fundamentals

Neo4j and Generative AI

Vectors & Semantic Search

Introduction to Langchain

Using LLMs for Query Generation

Adding the Neo4j Vector Retriever

In this optional challenge, add the movie plots vector retriever to the movie trailer agent you created previously.

To complete the code you will need to update the movie trailer agent to:

  1. Create the Neo4jVector from the moviePlots vector index.

  2. Create the RetrievalQA chain using the Neo4jVector as the retriever.

  3. Update the tools to use the RetrievalQA chain.

Here is the code for the movie trailer agent
python
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_react_agent
from langchain.tools import Tool
from langchain import hub
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain.schema import StrOutputParser
from langchain_community.tools import YouTubeSearchTool
from langchain_neo4j import Neo4jChatMessageHistory, Neo4jGraph
from uuid import uuid4

SESSION_ID = str(uuid4())
print(f"Session ID: {SESSION_ID}")

llm = ChatOpenAI(openai_api_key="sk-...")

graph = Neo4jGraph(
    url="bolt://localhost:7687",
    username="neo4j",
    password="pleaseletmein"
)

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a movie expert. You find movies from a genre or plot.",
        ),
        ("human", "{input}"),
    ]
)

movie_chat = prompt | llm | StrOutputParser()

youtube = YouTubeSearchTool()

def get_memory(session_id):
    return Neo4jChatMessageHistory(session_id=session_id, graph=graph)

def call_trailer_search(input):
    input = input.replace(",", " ")
    return youtube.run(input)

tools = [
    Tool.from_function(
        name="Movie Chat",
        description="For when you need to chat about movies. The question will be a string. Return a string.",
        func=movie_chat.invoke,
    ),
    Tool.from_function(
        name="Movie Trailer Search",
        description="Use when needing to find a movie trailer. The question will include the word trailer. Return a link to a YouTube video.",
        func=call_trailer_search,
    ),
]

agent_prompt = hub.pull("hwchase17/react-chat")
agent = create_react_agent(llm, tools, agent_prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

chat_agent = RunnableWithMessageHistory(
    agent_executor,
    get_memory,
    input_messages_key="input",
    history_messages_key="chat_history",
)

while True:
    q = input("> ")

    response = chat_agent.invoke(
        {
            "input": q
        },
        {"configurable": {"session_id": SESSION_ID}},
    )
    
    print(response["output"])
Here is the code for the movie plots vector retriever
python
from langchain.chains import RetrievalQA
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_neo4j import Neo4jGraph, Neo4jVector

OPENAI_API_KEY = "sk-..."

llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY)

embedding_provider = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)

graph = Neo4jGraph(
    url="bolt://localhost:7687",
    username="neo4j",
    password="pleaseletmein"
)

movie_plot_vector = Neo4jVector.from_existing_index(
    embedding_provider,
    graph=graph,
    index_name="moviePlots",
    embedding_node_property="plotEmbedding",
    text_node_property="plot",
)

plot_retriever = RetrievalQA.from_llm(
    llm=llm,
    retriever=movie_plot_vector.as_retriever()
)

response = plot_retriever.invoke(
    {"query": "A movie where a mission to the moon goes wrong"}
)

print(response)
Click to reveal the solution

There is no right or wrong way to complete this challenge. Here is one potential solution.

python
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain.chains import RetrievalQA
from langchain.agents import AgentExecutor, create_react_agent
from langchain.tools import Tool
from langchain import hub
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain.schema import StrOutputParser
from langchain_community.tools import YouTubeSearchTool
from langchain_neo4j import Neo4jChatMessageHistory, Neo4jGraph, Neo4jVector
from uuid import uuid4

SESSION_ID = str(uuid4())
print(f"Session ID: {SESSION_ID}")

OPENAI_API_KEY = "sk-..."

llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY)

embedding_provider = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)

graph = Neo4jGraph(
    url="bolt://localhost:7687",
    username="neo4j",
    password="pleaseletmein"
)

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a movie expert. You find movies from a genre or plot.",
        ),
        ("human", "{input}"),
    ]
)

movie_chat = prompt | llm | StrOutputParser()

youtube = YouTubeSearchTool()

movie_plot_vector = Neo4jVector.from_existing_index(
    embedding_provider,
    graph=graph,
    index_name="moviePlots",
    embedding_node_property="plotEmbedding",
    text_node_property="plot",
)

plot_retriever = RetrievalQA.from_llm(
    llm=llm,
    retriever=movie_plot_vector.as_retriever()
)

def get_memory(session_id):
    return Neo4jChatMessageHistory(session_id=session_id, graph=graph)

def call_trailer_search(input):
    input = input.replace(",", " ")
    return youtube.run(input)

tools = [
    Tool.from_function(
        name="Movie Chat",
        description="For when you need to chat about movies. The question will be a string. Return a string.",
        func=movie_chat.invoke,
    ),
    Tool.from_function(
        name="Movie Trailer Search",
        description="Use when needing to find a movie trailer. The question will include the word trailer. Return a link to a YouTube video.",
        func=call_trailer_search,
    ),
    Tool.from_function(
        name="Movie Plot Search",
        description="For when you need to compare a plot to a movie. The question will be a string. Return a string.",
        func=plot_retriever.invoke,
    ),
]

agent_prompt = hub.pull("hwchase17/react-chat")
agent = create_react_agent(llm, tools, agent_prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)

chat_agent = RunnableWithMessageHistory(
    agent_executor,
    get_memory,
    input_messages_key="input",
    history_messages_key="chat_history",
)

while True:
    q = input("> ")

    response = chat_agent.invoke(
        {
            "input": q
        },
        {"configurable": {"session_id": SESSION_ID}},
    )
    
    print(response["output"])

Summary

In this optional challenge, you added the movie plots vector retriever to the movie trailer agent you created previously.

In the next module, you will learn how to use an LLM to generate Cypher and improve the responses of an LLM.

Summary

In this optional challenge, you added the movie plots vector retriever to the movie trailer agent you created previously.

In the next module, you will learn how to use an LLM to generate Cypher and improve the responses of an LLM.