|
|
--- |
|
|
title: README |
|
|
emoji: 🏆 |
|
|
colorFrom: indigo |
|
|
colorTo: blue |
|
|
sdk: static |
|
|
pinned: false |
|
|
license: apache-2.0 |
|
|
short_description: Smarter vector search with metadata-aware traversal |
|
|
--- |
|
|
|
|
|
# Graph RAG |
|
|
|
|
|
Retrievers providing both **unstructured** (similarity-search on vectors) and |
|
|
**structured** (traversal of metadata properties). |
|
|
|
|
|
## About The Project |
|
|
|
|
|
Graph RAG provides retrievers combining vector-search (for unstructured similarity) and traversal (for structured relationships in metadata). |
|
|
These retrievers are implemented using the metadata search functionality of existing vector stores, **allowing you to traverse your existing vector store**! |
|
|
|
|
|
The core library (`graph-retriever`) supports can be used in generic Python applications, while `langchain-graph-retriever` provides [langchain](https://python.langchain.com/docs/introduction/)-specific functionality. |
|
|
|
|
|
<!-- GETTING STARTED --> |
|
|
## Getting Started with LangChain |
|
|
|
|
|
1. Install `langchain-graph-retriever` (or add to your Python dependencies). |
|
|
|
|
|
```sh |
|
|
pip install langchain-graph-retriever |
|
|
``` |
|
|
|
|
|
1. Wrap your existing vector store to enable graph retrieval: |
|
|
|
|
|
```python |
|
|
from langchain_graph_retriever import GraphRetriever |
|
|
|
|
|
retriever = GraphRetriever( |
|
|
# Adapt AstraDBVectorStore for use with Graph Retrievers. |
|
|
# Exposes functionality of the underlying store that is otherwise not available. |
|
|
store = store, |
|
|
# Define the relationships to navigate: |
|
|
# 1. From nodes with a list of `mentions` to the nodes with the corresponding `ids`. |
|
|
# 2. From nodes with a list of related `entities` to other nodes with the same entities. |
|
|
edges = [("mentions", "id"), "entities"], |
|
|
) |
|
|
|
|
|
retriever.invoke("where is Santa Clara?") |
|
|
``` |
