Minimal GraphRAG

Hi!

This is an example of vector and graph search featuring:

• SurrealDBVectorStore: for similarity/relevance search
• SurrealDBGraph: a langchain graph store
• SurrealDBGraphQAChain: a Question/Answering langchain chain class capable of querying the graph using LLM models

Running

Requirements:

• SurrealDB
• Ollama

You can run SurrealDB locally or start with a free SurrealDB cloud account.

For local, two options:

1. Install SurrealDB and run SurrealDB. Run in-memory with:

   surreal start -u root -p root

2. Run with Docker.

   docker run --rm --pull always -p 8000:8000 surrealdb/surrealdb:latest start

Then, using just from the root directory of this repository:

just install
just examples-graph ingest
just examples-graph chat

Or without just:

# install deps
cd examples/graph
poetry update

# run ingest script
poetry run run ingest

# run chat script
poetry run run chat

Future work

• demo the LLMGraphTransformer
• implement "few shot prompting": https://python.langchain.com/docs/tutorials/graph/#few-shot-prompting