embeddings

Uncover trends and compare languages easily

For ML teams looking to build their own text analysis applications, Embeddings offers high-performance and accuracy in English and 100+ languages.

Code sample that runs the Cohere API embed endpoint with only 9 lines
Using Cohere to categorize FAQs in a dashboard

What's possible with Embeddings

Semantic search

Build semantic search capability using conversational language.
Read the docs

Topic modeling

Cluster similar topics and discover thematic trends across a body of text sources.
See a Code Example

Recommendations

Build a recommendation engine and engage your users with more relevant content.
Read the docs

Multilingual Embeddings

Run topic modeling, semantic search, and recommendations across 100+ languages with just one model.
Read the docs

"It's next to impossible to gain access to Language AI and the experts building the technology. That’s why working with Cohere has been such a great experience. Anytime we have a new idea, their incredible team works with us to drive projects forward."

Carlos PerezCFO
Eficiencia Informativa

Why Embeddings

1

Embeddings performance

Cohere’s Embed model leads the industry in accuracy and performance, and works well with noisy datasets

2

Multilingual support

Over 100 languages are supported, so the same topics, products and issues are identified the same way in each


3

Scalability

Cohere Embed supports data compression, reducing storage and compute requirements

4

Flexible deployment

Cohere models can be accessed through a SaaS API, on cloud services (e.g. OCI, AWS SageMaker, Bedrock) and soon through private deployments (VPC and on-premise)

Simple APIs, powerful results

No matter your level of experience with ML/AI, the Cohere Platform makes it easy to classify text in your applications.

1import cohere
2co = cohere.Client('{apiKey}')
3
4faq_questions=[
5     "How much is a burger?",
6     "When do you close?",
7     "What are the hours",
8     "Do you have vegan options",
9     "What is the closest route"]
10
11response=co.embed(texts=faq_questions, input_type="search_query", model="embed-english-v3.0")
12print('Embeddings: {}'.format(response.embeddings))

Embeddings resources

Don’t want to code? Try our playground instead

Get started with Cohere today!

Reach out to us and let’s discuss your embedding needs.