This 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 by defining an appropriate
You need to define the following environment variables
Populating with data
If you want to populate the DB with some example data, you can run
The script process and stores sections of the text from the file
dune.txt into a Neo4j graph database.
First, the text is divided into larger chunks ("parents") and then further subdivided into smaller chunks ("children"), where both parent and child chunks overlap slightly to maintain context.
After storing these chunks in the database, embeddings for the child nodes are computed using OpenAI's embeddings and stored back in the graph for future retrieval or analysis.
Additionally, a vector index named
retrieval is created for efficient querying of these embeddings.
To use this package, you should first have the LangChain CLI installed:
pip install -U langchain-cli
To create a new LangChain project and install this as the only package, you can do:
langchain app new my-app --package neo4j-parent
If you want to add this to an existing project, you can just run:
langchain app add neo4j-parent
And add the following code to your
from neo4j_parent import chain as neo4j_parent_chain
add_routes(app, neo4j_parent_chain, path="/neo4j-parent")
(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"
If you are inside this directory, then you can spin up a LangServe instance directly by:
This will start the FastAPI app with a server is running locally at http://localhost:8000
We can access the template from code with:
from langserve.client import RemoteRunnable
runnable = RemoteRunnable("http://localhost:8000/neo4j-parent")