Memgraph

import os

from langchain_community.chains.graph_qa.memgraph import MemgraphQAChain
from langchain_community.graphs import MemgraphGraph
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI

url = os.environ.get("MEMGRAPH_URI", "bolt://localhost:7687")
username = os.environ.get("MEMGRAPH_USERNAME", "")
password = os.environ.get("MEMGRAPH_PASSWORD", "")

graph = MemgraphGraph(
    url=url, username=username, password=password, refresh_schema=False
)

# Drop graph
graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
graph.query("DROP GRAPH")
graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")

# Creating and executing the seeding query
query = """
    MERGE (g:Game {name: "Baldur's Gate 3"})
    WITH g, ["PlayStation 5", "Mac OS", "Windows", "Xbox Series X/S"] AS platforms,
            ["Adventure", "Role-Playing Game", "Strategy"] AS genres
    FOREACH (platform IN platforms |
        MERGE (p:Platform {name: platform})
        MERGE (g)-[:AVAILABLE_ON]->(p)
    )
    FOREACH (genre IN genres |
        MERGE (gn:Genre {name: genre})
        MERGE (g)-[:HAS_GENRE]->(gn)
    )
    MERGE (p:Publisher {name: "Larian Studios"})
    MERGE (g)-[:PUBLISHED_BY]->(p);
"""

graph.query(query)

graph.refresh_schema()

print(graph.get_schema)

chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    model_name="gpt-4-turbo",
    allow_dangerous_requests=True,
)

response = chain.invoke("Which platforms is Baldur's Gate 3 available on?")
print(response["result"])

response = chain.invoke("Is Baldur's Gate 3 available on Windows?")
print(response["result"])

# Return the result of querying the graph directly
chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    return_direct=True,
    allow_dangerous_requests=True,
    model_name="gpt-4-turbo",
)

response = chain.invoke("Which studio published Baldur's Gate 3?")
print(response["result"])

# Return all the intermediate steps of query execution
chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    allow_dangerous_requests=True,
    return_intermediate_steps=True,
    model_name="gpt-4-turbo",
)

response = chain.invoke("Is Baldur's Gate 3 an Adventure game?")
print(f"Intermediate steps: {response['intermediate_steps']}")
print(f"Final response: {response['result']}")

# Limit the maximum number of results returned by query
chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    top_k=2,
    allow_dangerous_requests=True,
    model_name="gpt-4-turbo",
)

response = chain.invoke("What genres are associated with Baldur's Gate 3?")
print(response["result"])

chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    model_name="gpt-4-turbo",
    allow_dangerous_requests=True,
)

response = chain.invoke("Is Baldur's Gate 3 available on PS5?")
print(response["result"])

MEMGRAPH_GENERATION_TEMPLATE = """Your task is to directly translate natural language inquiry into precise and executable Cypher query for Memgraph database. 
You will utilize a provided database schema to understand the structure, nodes and relationships within the Memgraph database.
Instructions: 
- Use provided node and relationship labels and property names from the
schema which describes the database's structure. Upon receiving a user
question, synthesize the schema to craft a precise Cypher query that
directly corresponds to the user's intent. 
- Generate valid executable Cypher queries on top of Memgraph database. 
Any explanation, context, or additional information that is not a part 
of the Cypher query syntax should be omitted entirely. 
- Use Memgraph MAGE procedures instead of Neo4j APOC procedures. 
- Do not include any explanations or apologies in your responses. 
- Do not include any text except the generated Cypher statement.
- For queries that ask for information or functionalities outside the direct
generation of Cypher queries, use the Cypher query format to communicate
limitations or capabilities. For example: RETURN "I am designed to generate
Cypher queries based on the provided schema only."
Schema: 
{schema}

With all the above information and instructions, generate Cypher query for the
user question. 
If the user asks about PS5, Play Station 5 or PS 5, that is the platform called PlayStation 5.

The question is:
{question}"""

MEMGRAPH_GENERATION_PROMPT = PromptTemplate(
    input_variables=["schema", "question"], template=MEMGRAPH_GENERATION_TEMPLATE
)

chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    cypher_prompt=MEMGRAPH_GENERATION_PROMPT,
    graph=graph,
    model_name="gpt-4-turbo",
    allow_dangerous_requests=True,
)

response = chain.invoke("Is Baldur's Gate 3 available on PS5?")
print(response["result"])

from langchain_core.documents import Document
from langchain_experimental.graph_transformers import LLMGraphTransformer

text = """
    Charles Robert Darwin was an English naturalist, geologist, and biologist,
    widely known for his contributions to evolutionary biology. His proposition that
    all species of life have descended from a common ancestor is now generally
    accepted and considered a fundamental scientific concept. In a joint
    publication with Alfred Russel Wallace, he introduced his scientific theory that
    this branching pattern of evolution resulted from a process he called natural
    selection, in which the struggle for existence has a similar effect to the
    artificial selection involved in selective breeding. Darwin has been
    described as one of the most influential figures in human history and was
    honoured by burial in Westminster Abbey.
"""

llm = ChatOpenAI(temperature=0, model_name="gpt-4-turbo")
llm_transformer = LLMGraphTransformer(llm=llm)
documents = [Document(page_content=text)]
graph_documents = llm_transformer.convert_to_graph_documents(documents)

print(graph_documents)

# Empty the database
graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
graph.query("DROP GRAPH")
graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")

# Create KG
graph.add_graph_documents(graph_documents)

llm_transformer_filtered = LLMGraphTransformer(
    llm=llm,
    allowed_nodes=["Person", "Nationality", "Concept"],
    allowed_relationships=["NATIONALITY", "INVOLVED_IN", "COLLABORATES_WITH"],
)
graph_documents_filtered = llm_transformer_filtered.convert_to_graph_documents(
    documents
)

print(f"Nodes:{graph_documents_filtered[0].nodes}")
print(f"Relationships:{graph_documents_filtered[0].relationships}")

# Drop graph
graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
graph.query("DROP GRAPH")
graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")

# Store to Memgraph with Entity label
graph.add_graph_documents(graph_documents, baseEntityLabel=True)

# Drop graph
graph.query("STORAGE MODE IN_MEMORY_ANALYTICAL")
graph.query("DROP GRAPH")
graph.query("STORAGE MODE IN_MEMORY_TRANSACTIONAL")

# Store to Memgraph with source included
graph.add_graph_documents(graph_documents, include_source=True)

chain = MemgraphQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    model_name="gpt-4-turbo",
    allow_dangerous_requests=True,
)
print(chain.invoke("Who Charles Robert Darwin collaborated with?")["result"])