Blog AWS Indonesia

Menjalankan tugas penalaran kompleks dengan Mistral Large, kini tersedia di Amazon Bedrock

Update 4/4/2024: Kami telah mengupdate post ini dan menambahkan informasi tentang ketersediaan Amazon Bedrock di Region Paris, dan menambahkan link baru untuk panduan inference request.

Bulan lalu, kami mengumumkan ketersediaan dua model AI Mistral yang berkinerja tinggi, Mistral 7B dan Mixtral 8x7B di Amazon Bedrock. Mistral 7B, sebagai model dasar (foundation model) pertama dari Mistral, mendukung tugas pembuatan teks berbahasa Inggris dengan kemampuan koding alami. Mixtral 8x7B adalah model Mixture-of-Experts (MoE) yang populer, berkualitas tinggi, dan ideal untuk rangkuman teks, tanya jawab, klasifikasi teks, pelengkapan teks, dan pembuatan kode.

Hari ini, kami mengumumkan ketersediaan Mistral Large di Amazon Bedrock. Mistral Large ideal untuk tugas-tugas kompleks yang membutuhkan kemampuan penalaran substansial, atau yang sangat spesifik, seperti Pembuatan Teks Sintetis atau Pembuatan Kode.

Pada AWS Summit Paris hari ini, kami mengumumkan ketersediaan Amazon Bedrock di Region Paris, ini menambah daftar berita yang menarik.

Apa yang perlu Anda ketahui tentang Mistral Large:

  • Mahir dalam bahasa Inggris, Prancis, Spanyol, Jerman, dan Italia, dengan pemahaman nuansa tentang tata bahasa dan konteks budaya.
  • Memiliki jendela konteks token 32K yang memungkinkan pemanggilan informasi yang tepat dari dokumen besar.
  • Kemampuan mengikuti instruksi yang tepat memungkinkan Anda merancang kebijakan moderasi Anda – developer di Mistral AI menggunakannya untuk mengatur moderasi sistem-level dari demonstrator asisten beta mereka, le Chat. Interaksi pertama Anda dengan Large Language Models (LLM) berpusat pada prompt. Seni membuat prompt yang efektif sangat penting untuk menghasilkan respons yang diinginkan dari LLM, dan Mistral AI memiliki panduan dengan contoh prompt yang menunjukkan berbagai kemampuan prompt.

Memulai dengan Mistral Large

Untuk memulai dengan Mistral Large di Bedrock, Anda pertama-tama harus mendapatkan akses ke model ini. Di konsol Amazon Bedrock, pilih Model access, lalu pilih Manage model access. Selanjutnya, pilih Mistral Large, lalu pilih Save changes.

Setelah Anda mendapatkan akses ke Mistral Large, Anda dapat menggunakan model tersebut di Bedrock. Refresh tabel model dasar untuk melihat status yang diperbarui.

Untuk melihat aspek penalaran kompleks dari Mistral Large, saya mencoba prompt berikut di bagian Playgrounds:

Prompt:

<s>[INST]Calculate the difference in payment dates between the two customers whose payment amounts are closest to each other in the given dataset:
{
"transaction_id":{"0":"T1001","1":"T1002","2":"T1003","3":"T1004","4":"T1005"},
"customer_id":{"0":"C001","1":"C002","2":"C003","3":"C002","4":"C001"},
"payment_amount":{"0":125.5,"1":89.99,"2":120.0,"3":54.3,"4":210.2},
"payment_date":{"0":"2021-10-05","1":"2021-10-06","2":"2021-10-07","3":"2021-10-05","4":"2021-10-08"},
"payment_status":{"0":"Paid","1":"Unpaid","2":"Paid","3":"Paid","4":"Pending"}
}[/INST]

Output:

To find the difference in payment dates between the two customers whose payment amounts are closest to each other, we first need to identify those two customers.

The payment amounts are:
– T1001: $125.50
– T1002: $89.99
– T1003: $120.00
– T1004: $54.30
– T1005: $210.20

The two closest payment amounts are $125.50 (T1001) and $120.00 (T1003). The difference between these amounts is $5.50.

The payment dates for these transactions are:
– T1001: 2021-10-05
– T1003: 2021-10-07

To find the difference between these dates, subtract the earlier date from the later date. The result is 2 days. So, the difference in payment dates between the two customers whose payment amounts are closest to each other is 2 days.

Sebelumnya dalam posting ini saya menyebutkan bahwa Mistral Large mahir secara native dalam beberapa bahasa, dengan pemahaman bernuansa tentang tata bahasa dan konteks budaya. Saya menguji pemahaman model terhadap bahasa Prancis:

Prompt:

<s>[INST]Lequel est le plus lourd une livre de fer ou un kilogramme de plume[/INST]

Output:

Une livre de fer pèse environ 0.453 kilogramme, tandis qu'un kilogramme de plumes pèse 1 kilogramme. Donc, un kilogramme de plumes est plus lourd qu'une livre de fer. Cependant, il est important de noter que le volume occupé par un kilogramme de plumes serait beaucoup plus grand que le volume occupé par une livre de fer, car les plumes sont beaucoup moins denses que le fer.

Berinteraksi secara pemrograman dengan Mistral Large

Anda juga dapat menggunakan AWS Command Line Interface (CLI) dan AWS Software Development Kit (SDK) untuk membuat berbagai panggilan menggunakan Amazon Bedrock API. Berikut adalah contoh kode dalam Python yang berinteraksi dengan Amazon Bedrock Runtime API menggunakan AWS SDK. Jika Anda menentukan dalam prompt bahwa “You will only respond with a JSON object with the key X, Y, and Z.”, Anda dapat menggunakan format keluaran JSON dalam permrosesan berikutnya dengan mudah:

import boto3
import json

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

prompt = """
<s>[INST]You are a summarization system that can provide summaries with associated confidence 
scores. In clear and concise language, provide three short summaries of the following essay, 
along with their confidence scores. You will only respond with a JSON object with the key Summary 
and Confidence. Do not provide explanations.[/INST]
# Essay: 
The generative artificial intelligence (AI) revolution is in full swing, and customers of all sizes and across industries are taking advantage of this transformative technology to reshape their businesses. From reimagining workflows to make them more intuitive and easier to enhancing decision-making processes through rapid information synthesis, generative AI promises to redefine how we interact with machines. It’s been amazing to see the number of companies launching innovative generative AI applications on AWS using Amazon Bedrock. Siemens is integrating Amazon Bedrock into its low-code development platform Mendix to allow thousands of companies across multiple industries to create and upgrade applications with the power of generative AI. Accenture and Anthropic are collaborating with AWS to help organizations—especially those in highly-regulated industries like healthcare, public sector, banking, and insurance—responsibly adopt and scale generative AI technology with Amazon Bedrock. This collaboration will help organizations like the District of Columbia Department of Health speed innovation, improve customer service, and improve productivity, while keeping data private and secure. Amazon Pharmacy is using generative AI to fill prescriptions with speed and accuracy, making customer service faster and more helpful, and making sure that the right quantities of medications are stocked for customers.

To power so many diverse applications, we recognized the need for model diversity and choice for generative AI early on. We know that different models excel in different areas, each with unique strengths tailored to specific use cases, leading us to provide customers with access to multiple state-of-the-art large language models (LLMs) and foundation models (FMs) through a unified service: Amazon Bedrock. By facilitating access to top models from Amazon, Anthropic, AI21 Labs, Cohere, Meta, Mistral AI, and Stability AI, we empower customers to experiment, evaluate, and ultimately select the model that delivers optimal performance for their needs.

Announcing Mistral Large on Amazon Bedrock
Today, we are excited to announce the next step on this journey with an expanded collaboration with Mistral AI. A French startup, Mistral AI has quickly established itself as a pioneering force in the generative AI landscape, known for its focus on portability, transparency, and its cost-effective design requiring fewer computational resources to run. We recently announced the availability of Mistral 7B and Mixtral 8x7B models on Amazon Bedrock, with weights that customers can inspect and modify. Today, Mistral AI is bringing its latest and most capable model, Mistral Large, to Amazon Bedrock, and is committed to making future models accessible to AWS customers. Mistral AI will also use AWS AI-optimized AWS Trainium and AWS Inferentia to build and deploy its future foundation models on Amazon Bedrock, benefitting from the price, performance, scale, and security of AWS. Along with this announcement, starting today, customers can use Amazon Bedrock in the AWS Europe (Paris) Region. At launch, customers will have access to some of the latest models from Amazon, Anthropic, Cohere, and Mistral AI, expanding their options to support various use cases from text understanding to complex reasoning.

Mistral Large boasts exceptional language understanding and generation capabilities, which is ideal for complex tasks that require reasoning capabilities or ones that are highly specialized, such as synthetic text generation, code generation, Retrieval Augmented Generation (RAG), or agents. For example, customers can build AI agents capable of engaging in articulate conversations, generating nuanced content, and tackling complex reasoning tasks. The model’s strengths also extend to coding, with proficiency in code generation, review, and comments across mainstream coding languages. And Mistral Large’s exceptional multilingual performance, spanning French, German, Spanish, and Italian, in addition to English, presents a compelling opportunity for customers. By offering a model with robust multilingual support, AWS can better serve customers with diverse language needs, fostering global accessibility and inclusivity for generative AI solutions.

By integrating Mistral Large into Amazon Bedrock, we can offer customers an even broader range of top-performing LLMs to choose from. No single model is optimized for every use case, and to unlock the value of generative AI, customers need access to a variety of models to discover what works best based for their business needs. We are committed to continuously introducing the best models, providing customers with access to the latest and most innovative generative AI capabilities.

“We are excited to announce our collaboration with AWS to accelerate the adoption of our frontier AI technology with organizations around the world. Our mission is to make frontier AI ubiquitous, and to achieve this mission, we want to collaborate with the world’s leading cloud provider to distribute our top-tier models. We have a long and deep relationship with AWS and through strengthening this relationship today, we will be able to provide tailor-made AI to builders around the world.”

– Arthur Mensch, CEO at Mistral AI.

Customers appreciate choice
Since we first announced Amazon Bedrock, we have been innovating at a rapid clip—adding more powerful features like agents and guardrails. And we’ve said all along that more exciting innovations, including new models will keep coming. With more model choice, customers tell us they can achieve remarkable results:

“The ease of accessing different models from one API is one of the strengths of Bedrock. The model choices available have been exciting. As new models become available, our AI team is able to quickly and easily evaluate models to know if they fit our needs. The security and privacy that Bedrock provides makes it a great choice to use for our AI needs.”

– Jamie Caramanica, SVP, Engineering at CS Disco.

“Our top priority today is to help organizations use generative AI to support employees and enhance bots through a range of applications, such as stronger topic, sentiment, and tone detection from customer conversations, language translation, content creation and variation, knowledge optimization, answer highlighting, and auto summarization. To make it easier for them to tap into the potential of generative AI, we’re enabling our users with access to a variety of large language models, such as Genesys-developed models and multiple third-party foundational models through Amazon Bedrock, including Anthropic’s Claude, AI21 Labs’s Jurrassic-2, and Amazon Titan. Together with AWS, we’re offering customers exponential power to create differentiated experiences built around the needs of their business, while helping them prepare for the future.”

– Glenn Nethercutt, CTO at Genesys.

As the generative AI revolution continues to unfold, AWS is poised to shape its future, empowering customers across industries to drive innovation, streamline processes, and redefine how we interact with machines. Together with outstanding partners like Mistral AI, and with Amazon Bedrock as the foundation, our customers can build more innovative generative AI applications.

Democratizing access to LLMs and FMs
Amazon Bedrock is democratizing access to cutting-edge LLMs and FMs and AWS is the only cloud provider to offer the most popular and advanced FMs to customers. The collaboration with Mistral AI represents a significant milestone in this journey, further expanding Amazon Bedrock’s diverse model offerings and reinforcing our commitment to empowering customers with unparalleled choice through Amazon Bedrock. By recognizing that no single model can optimally serve every use case, AWS has paved the way for customers to unlock the full potential of generative AI. Through Amazon Bedrock, organizations can experiment with and take advantage of the unique strengths of multiple top-performing models, tailoring their solutions to specific needs, industry domains, and workloads. This unprecedented choice, combined with the robust security, privacy, and scalability of AWS, enables customers to harness the power of generative AI responsibly and with confidence, no matter their industry or regulatory constraints.
"""

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

# modelId = "mistral.mistral-large-instruct-v0:2"
modelId = "mistral.mistral-large-2402-v1:0"

accept = "application/json"
contentType = "application/json"

response = bedrock.invoke_model(
    body=body,
    modelId=modelId,
    accept=accept,
    contentType=contentType
)

print(json.loads(response.get('body').read()))

Anda akan mendapat JSON format seperti berikut:

{
  "Summary 1": "The generative AI revolution is transforming businesses with the help of Amazon Bedrock, which offers access to multiple state-of-the-art large language models and foundation models. Mistral AI's latest model, Mistral Large, is now available on Amazon Bedrock, providing exceptional language understanding and generation capabilities.",
  "Confidence 1": 0.95,
  "Summary 2": "Amazon Bedrock is a unified service that provides customers with access to top models from various AI companies, including Amazon, Anthropic, AI21 Labs, Cohere, Meta, Mistral AI, and Stability AI. The recent addition of Mistral Large to the platform enhances the range of top-performing LLMs available to customers.",
  "Confidence 2": 0.92,
  "Summary 3": "Mistral Large, the latest model from Mistral AI, offers exceptional language understanding and generation capabilities, making it ideal for complex tasks that require reasoning or specialized knowledge. Its multilingual performance and coding proficiency make it a valuable addition to Amazon Bedrock's diverse model offerings.",
  "Confidence 3": 0.90
}

Untuk mempelajari lebih lanjut tentang kemampuan prompt di model-model Mistral AI, kunjungi dokumentasi Mistral AI.

Sekarang Tersedia

Mistral Large, bersama dengan model-model AI Mistral lainnya (Mistral 7B dan Mixtral 8x7B), tersedia hari ini di Amazon Bedrock di US East (N. Virginia), US West (Oregon), dan Eropa (Paris); periksa list Region lengkap untuk pembaruan di masa mendatang.

Berbagi dan belajar dengan komunitas generative AI kami di community.aws. Coba Mistral Large di konsol Amazon Bedrock hari ini dan kirimkan feedback ke AWS re:Post untuk Amazon Bedrock atau melalui kontak dukungan AWS Anda.

Baca tentang kolaborasi kami dengan Mistral AI dan apa artinya bagi pelanggan kami.

Artikel ini diterjemahkan dari artikel asli dengan judul “Tackle complex reasoning tasks with Mistral Large, now available on Amazon Bedrock” yang ditulis oleh Veliswa Boya, AWS.

Anda mungkin tertarik dengan artikel tentang generative AI terkait yaitu “Kredit AWS Activate sekarang menerima third-party model di Amazon Bedrock”.

Rio Astamal

Rio Astamal

Rio Astamal is a Developer Advocate at AWS and a passionate web developer since 2003. In his spare time he loves writing small open source projects to solve problem in his daily activity.