LangChain Neo4j Integration

1AH05dvGA 7db EMySc9AAw

LangChain is a vast library for GenAI orchestration, it supports numerous LLMs, vector stores, document loaders and agents. It manages templates, composes components into chains and supports monitoring and observability.

The broad and deep Neo4j integration allows for vector search, cypher generation and database querying and knowledge graph construction.

When upgrading to LangChain 0.1.0+ make sure to read this article: Updating GraphAcademy Neo4j & LLM Courses to Langchain v0.1.

Installation

pip install langchain langchain-community
# pip install langchain-openai tiktoken
# pip install neo4j

Functionality Includes

Neo4jVector

The Neo4j Vector integration supports a number of operations

  • create vector from langchain documents

  • query vector

  • query vector with additional graph retrieval Cypher query

  • construct vector instance from existing graph data

  • hybrid search

from langchain.docstore.document import Document
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Neo4jVector
from langchain_openai import OpenAIEmbeddings

loader = TextLoader("../../modules/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, OpenAIEmbeddings(), url=url, username=username, password=password
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

Hybrid search combines vector search with fulltext search with re-ranking and de-duplication of the results.

from langchain.docstore.document import Document
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Neo4jVector
from langchain_openai import OpenAIEmbeddings

loader = TextLoader("../../modules/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, OpenAIEmbeddings(), url=url, username=username, password=password,
    search_type: 'hybrid'
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

Neo4j Graph

The Neo4j Graph integration is a wrapper for the Neo4j Python driver. It allows querying and updating the Neo4j databsae in a simplified manner from LangChain. Many integrations allow to use the Neo4j Graph as a source of data for LangChain.

from langchain_community.graphs import Neo4jGraph

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

QUERY = """
"MATCH (m:Movie)-[:IN_GENRE]->(:Genre {name:$genre})
RETURN m.title, m.plot
ORDER BY m.imdbRating DESC LIMIT 5"
"""

graph.query(QUERY, genre="action")

CypherQAChain

The CypherQAChain is a LangChain component that allows you to interact with a Neo4j graph database in natural language. Using an LLM and the graph schema it translates the user question into a Cypher query, executes it against the graph and uses the returned context information and the original question with a second LLM to generate a natural language response.

# pip install --upgrade --quiet  langchain
# pip install --upgrade --quiet  langchain-openai

from langchain.chains import GraphCypherQAChain
from langchain_community.graphs import Neo4jGraph
from langchain_openai import ChatOpenAI

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

# Insert some movie data
graph.query(
    """
MERGE (m:Movie {title:"Top Gun"})
WITH m
UNWIND ["Tom Cruise", "Val Kilmer", "Anthony Edwards", "Meg Ryan"] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True
)

chain.run("Who played in Top Gun?")

Advanced RAG Strategies

Besides the basic RAG strategy, the Neo4j Integration in LangChain supports advanced RAG strategies that allow for more complex retrieval strategies. These are also available as LangChain Templates.

pip install -U "langchain-cli[serve]"

langchain app new my-app --package neo4j-advanced-rag

# update server.py to add the neo4j-advanced-rag template as an endpoint
cat <<EOF > server.py
from fastapi import FastAPI
from langserve import add_routes

from neo4j_advanced_rag import chain as neo4j_advanced_chain

app = FastAPI()

# Add this
add_routes(app, neo4j_advanced_chain, path="/neo4j-advanced-rag")


if __name__ == "__main__":
    import uvicorn

    uvicorn.run(app, host="0.0.0.0", port=8000)
EOF

langchain serve
jfDNiPa5ccefX6h0HiVzJbqnlgAZgfPda90truHSfbwSs3JkfxZ xbA9mZE8y2fNf 3n5cgVhbdhN0ryuMoK2JNbMgTe1OLJMA6CQRhWBxzdKRLVurUFDndT7ki4vMh cdv3SAn040HTpab9XkzGj5Q

LangChain Templates

Langchain Templates are a set of preconfigured chains and components that can be used to build GenAI workflows and applications. You can test them interactively on the LangChain Playground and run them with LangServe to run as REST APIs, they also integrate with [LangSmith] for monitoring and observability.

By creating an application from templates, their source code is added to your application and you can modify them to fit your needs.

List of Templates

This Cypher template allows you to interact with a Neo4j graph database in natural language, using an OpenAI LLM.

It transforms a natural language question into a Cypher query (used to fetch data from Neo4j databases), executes the query, and provides a natural language response based on the query results.

The Cypher-FT Template additionally utilizes a full-text index for efficient mapping of text values to database entries, thereby enhancing the generation of accurate Cypher statements.

The Cypher Memory Template also features a conversational memory module that stores the dialogue history in the Neo4j graph database. The conversation memory is uniquely maintained for each user session, ensuring personalized interactions.

The Neo4j generation Template pairs LLM-based knowledge graph extraction using OpenAI functions, with Neo4j AuraDB, a fully managed cloud graph database.

This Neo4j Vector Memory Template allows you to integrate an LLM with a vector-based retrieval system using Neo4j as the vector store. Additionally, it uses the graph capabilities of the Neo4j database to store and retrieve the dialogue history of a specific user’s session. Having the dialogue history stored as a graph allows for seamless conversational flows but also gives you the ability to analyze user behavior and text chunk retrieval through graph analytics.

The Parent-Child Retriever Template allows you to balance precise embeddings and context retention by splitting documents into smaller chunks and retrieving their original or larger text information.

Using a Neo4j vector index, the package queries child nodes using vector similarity search and retrieves the corresponding parent’s text.

The Neo4j Semantic Layer Template is designed to implement an agent capable of interacting with a graph database like Neo4j through a semantic layer using OpenAI function calling. The semantic layer equips the agent with a suite of robust tools, allowing it to interact with the graph databas based on the user’s intent.

Semantic Layer

A semantic layer on top of a (graph) database doesn’t rely on automatic query generation but offers a number of APIs and tools to give the LLM access to the database and it’s structures.

Unlike automatically generated queries, these tools are safe to use as they are implemented using correct queries and interactions and only take parameters from the LLM.

Many cloud (llm) providers offer similar integrations either via function calling (OpenAI, Anthropic) or extensions (Google Vertex AI, AWS Bedrock).

Examples for such tools or functions include:

Conversational Memory

Storing the conversation, i.e. the flow of questions and answers of user sessions in a graph allows you to analyze the conversation history and use it to improve the user experience.

You can index embeddings for and link questions and answers back to the retrieved chunks and entities in the graph and use user feedback to re-rank those inputs for future similar questions.

DiffbotGraphTransformer

Creating a Knowledge Graph from unstructured data like PDF documents used to be a complex and time-consuming task that required training and using dedicated, large NLP models.

The Diffbot Graph Transformer is a tool that allows you to extract structured data from unstructured documents and transform it into a Knowledge Graph.

It will be augmented in the future with an LLM based graph transformer.

Videos & Tutorials