Overview

Use the Cohere platform to build natural language understanding and generation into your product with a few lines of code. Cohere’s large language models can solve a broad spectrum of natural language use cases, including classification, semantic search, paraphrasing, summarization, and content generation. Through finetuning, users can create massive models customized to their use case and trained on their data.

The models can be accessed through the playground, SDKs, and the CLI tool.

Getting started

New to Machine Learning?

Learn some of the key concepts involved in language generation and understanding. These include tokens, embeddings, temperature, and likelihood.

Or, check out our Intro to Large Language Models guide for a visual overview of large language models and some of their applications.

Quickstart Guides

Jump into a project right away with our easy quickstart guides.

• Customer Support: Classify customer emails into four types of request.
• Intent Recognition: Classify the intent of customer inquiries.
• Sentiment Analysis: Analyze the sentiments of customer feedback about a product.
• Text Summarization: Summarize a passage from a news article into its main point.

Join the Co:mmunity

Co:mmunity- get help and share your experience!

Use Cases

Classify Text

Text classification is one of the most useful applications of Large Language Models (LLMs). They can classify text using a small number of examples (few-shot classification).

See the text classification with Classify tutorial which demonstrates the Classify endpoint.

See the text classification with Embeddings tutorial which demonstrates the Embed endpoint.

See the content moderation with Classify tutorial which demonstrates the Classify endpoint.

Summarize and Paraphrase Text

The Summarization and paraphrasing article walks you through using the Generate endpoint for summarization. See how to build this capability into a Slack bot in the Building an Arxiv Paper Summarizer Slack App guide.

Semantic Search

Learn how to use embeddings to build semantic search capabilities.

Extract Information from Text

Extract information from text using only a few examples.

Generate Text

LLMs can write coherent text like no other human technology before them could. We tune the inputs using prompt engineering techniques that get the model to produce useful outputs. Important text generations parameters include top-k and top-p. For an example on how to include this capability in your web application, see the React Tutorial using Generate.

API Reference

The Cohere Platform endpoints are:

• Generate: Generate text from a model in response to an input prompt.
• Embed: Retrieve the sentence embeddings from a representation model.
• Classify: Perform classification by using a few examples.

The Command Line Tool is an alternative to our web interface, which allows you to login to your Cohere account, manage API Keys, and run finetunes.

Responsible Use

The Responsible Use documentation aims to guide developers in using language models constructively and ethically. Toward this end, we've published guidelines for using our API safely, statistics regarding the environmental impact of pre-training our language models, as well as our processes around harm prevention.