From the course: Knowledge Graph Data Engineering for Generative AI Use Cases

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Missing data

Missing data - Neo4j Tutorial

From the course: Knowledge Graph Data Engineering for Generative AI Use Cases

Start my 1-month free trial Buy for my team

Missing data

“

- [Instructor] We will now need to transform our unstructured data into data we can connect to our model, so we can use our AI to query against our repository of knowledge. Looking at the unstructured data, we can see there are four main data types. We have customer ID, order ID, review ID, and the actual rating. Now we can add all of these into a dataset as new columns. We'll of course also eventually need to set up a data pipeline to source customer reviews, either in a document store, vector store or file storage like S3 for us to source the data from and then populate our graph when we move into production. So we already have the first two as nodes, customer ID and order ID in other datasets. But now we need to add ratings as a new node in our design document, and we will need to connect it to the event it is connected to, which is the purchase order number in our case. But that's already in the model. We need to have all of these in our dataset so that this information can…

Contents