Diffbot GraphRAG LLM
by Kris NegulescuRecently, large language models (LLMs) have been trained with more and more data, leading to an increase in the number of parameters and the computing power needed. But, what if, instead of feeding the model more data, we purposefully trained it to rely less on its pretraining data and more on its ability to find external knowledge?
To test this idea, we fine-tuned LLama 3.3 70B to be an expert tool user of a real-time Knowledge Graph API, providing the first open-source implementation of a GraphRAG system that outperforms Google Gemini and ChatGPT. To learn more, see: https://github.com/diffbot/diffbot-llm-inference/.