Since GPT-3 began to show an unexpected “understanding ability,” we have been engaged in research, exploration, and sharing on the complementary combination of Graph + LLM technology. As of now, we had made many leading contributions to the LlamaIndex and Langchain projects. Starting from this article, we will share some of our periodic successes and methods with everyone.

Introduce the brand new ipython-ngql python package that enhances your ability to connect to NebulaGraph from your Jupyter Notebook or iPython. Now we can do%ngql MATCH p=(n:player)->() RETURN p to query from Jupyter Notebook and %ng_draw to render the result.

How Graph could help build better In-context Learning LLM Applications.

Introducing a new project! ng_ai: NebulaGraph’s graph algorithm suite, a user-friendly high-level Python Algorithm API for NebulaGraph. Its goal is to enable data scientist users of NebulaGraph to perform graph-related algorithmic tasks with minimal code.

How NebulaGraph helps build social network systems.

An attempt to use ChatGPT to generate code for a data scraper to predict sports events with the help of the NebulaGraph graph database and graph algorithms.

This post was initially published in https://www.nebula-graph.io/posts/predict-fifa-world-cup-with-chatgpt-and-nebulagraph

How could we model data in Tabular sources and ETL it to NebulaGraph? This article demonstrates an end-to-end example of doing so with dbt.