Organize information for more effective content moderation, analysis and chat bot experiences.

Access large language models that can understand text and take appropriate action — like highlight a post that violates your community guidelines, or trigger accurate chatbot responses. Just set your parameters, and Classify will do the rest.

How it works

The power of understanding

Classify uses cutting-edge machine learning to analyze and bucket text into specific categories. Build automated text classifiers into your application to do things like identify toxic language, automatically route customer queries, or detect breaking trends in product reviews.

What's possible with Classify

Keep your community safe

Use Classify to identify hate speech, abusive language, spam, profanity, or anything that meets user-provided filters.

Harness intent recognition

Leverage Classify to triage inbound chatbot or email requests to understand user intent and automatically issue responses.

Serve your customers better

Save time by tasking Classify to route inbound customer support requests to their respective teams.

Access industry-leading sentiment analysis

Develop a stronger customer affinity by classifying posts, reviews, etc to understand how they perceive your company/brand.

Integrate large language models into your builds

We’ve made an API that can be used in different libraries that fit every stack. No matter your level of developer experience, Cohere makes it easy to build machine learning into your application with our Python, Node, and Go SDKs.

Multiple platforms supported

We support all common languages through native SDK support or encapsulated REST calls, see examples

Large language models

Our models have been trained on billions of words, allowing them to understand nuance and context.

import cohere
from cohere.classify import Example
co = cohere.Client('{apiKey}')
response = co.classify(
inputs=["this movie was great", "this movie was bad"],
examples=[Example("love this movie", "Positive Review"), Example("I would watch this movie again with my friends", "Positive Review"), Example("I would watch this movie again", "Positive Review"), Example("I liked this movie", "Positive Review"), Example("This is my favourite movie", "Positive Review"), Example("I would not recommend this movie to my friends", "Negative Review"), Example("I did not want to finish the movie", "Negative Review"), Example("Hate this movie", "Negative Review"), Example("We made it only a quarter way through before we stopped", "Negative Review"), Example("Worst movie of all time", "Negative Review"), Example("Movie lacked any originality or depth", "Neutral Review"), Example("This movie was okay", "Neutral Review"), Example("This movie was neither amazing or terrible", "Neutral Review"), Example("I would not watch this movie again but it was not a waste of time", "Neutral Review"), Example("This movie was nothing special", "Neutral Review")])
print('The confidence levels of the labels are: {}'.format(response.classifications))

Make it yours

Our models have read billions and billions of words. But they can be made even more effective with a little input from you. Our finetuning feature allows you to tweak our base models to make them more applicable to your specific task or domain.

Get Started

Create an account instantly to get started. You can also contact us to design a custom package for your business.

Create an Account