mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
163ef35dd1
Updated titles into a consistent format. Fixed links to the diagrams. Fixed typos. Note: The Templates menu in the navbar is now sorted by the file names. I'll try sorting the navbar menus by the page titles, not the page file names.
89 lines
2.6 KiB
Markdown
89 lines
2.6 KiB
Markdown
# Neo4j - vector memory
|
|
|
|
This 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.
|
|
|
|
|
|
## Environment Setup
|
|
|
|
You need to define the following environment variables
|
|
|
|
```
|
|
OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
|
|
NEO4J_URI=<YOUR_NEO4J_URI>
|
|
NEO4J_USERNAME=<YOUR_NEO4J_USERNAME>
|
|
NEO4J_PASSWORD=<YOUR_NEO4J_PASSWORD>
|
|
```
|
|
|
|
## Populating with data
|
|
|
|
If you want to populate the DB with some example data, you can run `python ingest.py`.
|
|
The script process and stores sections of the text from the file `dune.txt` into a Neo4j graph database.
|
|
Additionally, a vector index named `dune` is created for efficient querying of these embeddings.
|
|
|
|
|
|
## Usage
|
|
|
|
To use this package, you should first have the LangChain CLI installed:
|
|
|
|
```shell
|
|
pip install -U langchain-cli
|
|
```
|
|
|
|
To create a new LangChain project and install this as the only package, you can do:
|
|
|
|
```shell
|
|
langchain app new my-app --package neo4j-vector-memory
|
|
```
|
|
|
|
If you want to add this to an existing project, you can just run:
|
|
|
|
```shell
|
|
langchain app add neo4j-vector-memory
|
|
```
|
|
|
|
And add the following code to your `server.py` file:
|
|
```python
|
|
from neo4j_vector_memory import chain as neo4j_vector_memory_chain
|
|
|
|
add_routes(app, neo4j_vector_memory_chain, path="/neo4j-vector-memory")
|
|
```
|
|
|
|
(Optional) Let's now configure LangSmith.
|
|
LangSmith will help us trace, monitor and debug LangChain applications.
|
|
You can sign up for LangSmith [here](https://smith.langchain.com/).
|
|
If you don't have access, you can skip this section
|
|
|
|
```shell
|
|
export LANGCHAIN_TRACING_V2=true
|
|
export LANGCHAIN_API_KEY=<your-api-key>
|
|
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:
|
|
|
|
```shell
|
|
langchain serve
|
|
```
|
|
|
|
This will start the FastAPI app with a server is running locally at
|
|
[http://localhost:8000](http://localhost:8000)
|
|
|
|
We can see all templates at [http://127.0.0.1:8000/docs](http://127.0.0.1:8000/docs)
|
|
We can access the playground at [http://127.0.0.1:8000/neo4j-vector-memory/playground](http://127.0.0.1:8000/neo4j-parent/playground)
|
|
|
|
We can access the template from code with:
|
|
|
|
```python
|
|
from langserve.client import RemoteRunnable
|
|
|
|
runnable = RemoteRunnable("http://localhost:8000/neo4j-vector-memory")
|
|
```
|