generate prompts for LLMs to extract relevant entities from job descriptions and also to classify web pages given only a few examples of human scores.
This notebook demonstrates how to use Cohere's generative models to extract Entities from text. This demonstrates Named Entity Recognition (NER) of entities which are harder to isolate using other NLP methods (and where pre-training provides the model with some context on these entities). This also demonstrates the broader usecase of sturctured generation based on providing multiple examples in the prompt.
In our prompt, we'll present the model with examples for the type of output we're after. We basically get a set of data, and label them ourselves.
We'll create a prompt that demonstrates the task to the model. The prompt contains the examples above, and then presents the input text and asks the model to extract the movie name.
