Customization

The SimpleKGPipeline class is designed to be easily customizable to fit different use cases. You can provide your own implementations for components in the pipeline, or use the existing components to generate your own pipelines.

In this optional module, you will learn how to modify the knowledge graphA representation of real-world entities and their relationships, stored according to organizing principles, typically in a graph database. pipeline to suit your own use case, including:

• Creating custom data loaders.
• Implementing custom chunking and text splitting strategies.
• Enhanced entity resolution.
• Using different LLMsA model trained on text to predict the next token, and so to generate language. and embeddingInformation represented as a numerical vector, positioned so that similar information sits close together. models.

If you are ready, let's get going!