Run scalable, enterprise-grade generative AI workloads with Cohere Command R & R+, now accessible in Amazon Bedrock

In November 2023, we made two new Cohere fashions accessible in Amazon Bedrock (Cohere Command Gentle and Cohere Embed English). Right now, we’re asserting the addition of two extra Cohere fashions in Amazon Bedrock; Cohere Command R and Command R+.

Organizations want generative synthetic intelligence (generative AI) fashions to securely work together with data saved of their enterprise knowledge sources. Each Command R and Command R+ are highly effective, scalable giant language fashions (LLMs), purpose-built for real-world, enterprise-grade workloads. These fashions are multilingual and are centered on balancing excessive effectivity with robust accuracy to excel at capabilities reminiscent of Retrieval-Augmented Era (RAG), and power use to allow enterprises to maneuver past proof-of-concept (POC), and into manufacturing utilizing synthetic intelligence (AI).

Command R is a scalable multilingual generative mannequin focusing on RAG and power use to allow production-scale AI for enterprises. Command R+ is a state-of-the-art RAG-optimized mannequin designed to sort out enterprise-grade workloads and optimize enterprise AI purposes. Command R+ is optimized for superior RAG to offer enterprise-ready, extremely dependable, and verifiable responses as a consequence of in-line citations which come customary with this mannequin. With these new Cohere fashions in Bedrock, you possibly can scale with AI to shortly find essentially the most related data to assist duties throughout enterprise capabilities like finance, human assets (HR), gross sales, advertising, and buyer assist, amongst others, in a spread of enterprise sectors. Device use can be accessible in Command R+. Command R+ is a powerful multilingual mannequin, and equally to Command R, contains a tokenizer that compresses non-English textual content significantly better than the tokenizer used for different fashions available in the market.

Getting began with Command R and Command R+
To get began with each fashions in Amazon Bedrock, you first must get entry to the fashions. Within the Amazon Bedrock console, select Mannequin entry, after which select Handle mannequin entry. Subsequent, select your most well-liked mannequin(s), after which select Save adjustments. As you possibly can see, you now have six Cohere fashions to select from in Amazon Bedrock – together with Command R and Command R+ – supplying you with larger alternative and adaptability to make use of the optimum fashions to your particular enterprise wants.

Upon getting entry to your most well-liked mannequin, you need to use the mannequin in Amazon Bedrock. Refresh the bottom fashions desk to view the up to date standing.

The fashions have been educated to reply within the language of the person reminiscent of English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese language, and Arabic. Right here’s an instance:

Immediate

<s>"Écris une description de produit pour une voiture électrique en 50 à 75 mots"

Output

Découvrez la voiture électrique qui va révolutionner votre façon de conduire.
Avec son design élégant, cette voiture offre une expérience de conduite distinctive
avec une accélération puissante et une autonomie impressionnante. Sa
technologie avancée vous garantit une cost rapide et une fiabilité inégalée.
Avec sa conception innovante et sturdy, cette voiture est parfaite pour les 
trajets urbains et les longues distances. Profitez d'une conduite silencieuse
et vivez l'expérience de la voiture électrique!

Programmatically work together with Command R and Command R+
It’s also possible to use AWS Command Line Interface (CLI) and AWS Software program Growth Package (SDK) to make numerous calls utilizing Amazon Bedrock APIs. Following, is a pattern code in Python that interacts with Amazon Bedrock Runtime APIs with AWS SDK. Taking the identical textual content era immediate I used earlier, right here is the way it appears to be like when used programmatically. On this instance I’m interacting with the Command R mannequin. Again to Python, I first run the ListFoundationModels API name to find the modelId for Command R.

import boto3
import json
import numpy

bedrock = boto3.shopper(service_name="bedrock", region_name="us-east-1")

listModels = bedrock.list_foundation_models(byProvider="cohere")
print("n".be part of(checklist(map(lambda x: f"{x['modelName']} : { x['modelId'] }", listModels['modelSummaries']))))

Operating this code offers the checklist:

Command : cohere.command-text-v14
Command Gentle : cohere.command-light-text-v14
Embed English : cohere.embed-english-v3
Embed Multilingual : cohere.embed-multilingual-v3
Command R: cohere.command-r-v1:0
Command R+: cohere.command-r-plus-v1:0

From this checklist, I choose cohere.command-r-v1:0 mannequin ID and write the code to generate the textual content as proven earlier on this publish.

import boto3
import json

bedrock = boto3.shopper(service_name="bedrock-runtime", region_name="us-east-1")

immediate = """
<s>Écris une description de produit pour une voiture électrique en 50 à 75 mots

physique = json.dumps({
    "immediate": immediate,
    "max_tokens": 512,
    "top_p": 0.8,
    "temperature": 0.5,
})

modelId = "cohere.command-r-v1:0"

settle for = "software/json"
contentType = "software/json"

response = bedrock.invoke_model(
    physique=physique,
    modelId=modelId,
    settle for=settle for,
    contentType=contentType
)

print(json.masses(response.get('physique').learn()))

You may get JSON formatted output as like:

Découvrez la voiture électrique qui va révolutionner votre façon de conduire.
Avec son design élégant, cette voiture offre une expérience de conduite distinctive
avec une accélération puissante et une autonomie impressionnante. Sa
technologie avancée vous garantit une cost rapide et une fiabilité inégalée.
Avec sa conception innovante et sturdy, cette voiture est parfaite pour les 
trajets urbains et les longues distances. Profitez d'une conduite silencieuse
et vivez l'expérience de la voiture électrique!

Now Accessible

Command R and Command R+ fashions, together with different Cohere fashions, can be found at this time in Amazon Bedrock within the US East (N. Virginia) and US West (Oregon) Areas; examine the full Area checklist for future updates.

Go to our group.aws web site to seek out deep-dive technical content material and to find how our Builder communities are utilizing Amazon Bedrock of their options. Give Command R and Command R+ a attempt within the Amazon Bedrock console at this time and ship suggestions to AWS re:Publish for Amazon Bedrock or via your ordinary AWS Assist contacts.

– Veliswa.