Enterprises are looking for to shortly unlock the potential of generative AI by offering entry to basis fashions (FMs) to completely different traces of enterprise (LOBs). IT groups are liable for serving to the LOB innovate with pace and agility whereas offering centralized governance and observability. For instance, they could want to trace the utilization of FMs throughout groups, chargeback prices and supply visibility to the related price heart within the LOB. Moreover, they could want to manage entry to completely different fashions per workforce. For instance, if solely particular FMs could also be accepted to be used.
Amazon Bedrock is a completely managed service that provides a selection of high-performing basis fashions from main AI corporations like AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon through a single API, together with a broad set of capabilities to construct generative AI purposes with safety, privateness, and accountable AI. As a result of Amazon Bedrock is serverless, you don’t need to handle any infrastructure, and you may securely combine and deploy generative AI capabilities into your purposes utilizing the AWS companies you might be already accustomed to.
A software program as a service (SaaS) layer for basis fashions can present a easy and constant interface for end-users, whereas sustaining centralized governance of entry and consumption. API gateways can present free coupling between mannequin customers and the mannequin endpoint service, and adaptability to adapt to altering mannequin, architectures, and invocation strategies.
On this submit, we present you how one can construct an inside SaaS layer to entry basis fashions with Amazon Bedrock in a multi-tenant (workforce) structure. We particularly give attention to utilization and value monitoring per tenant and likewise controls equivalent to utilization throttling per tenant. We describe how the answer and Amazon Bedrock consumption plans map to the overall SaaS journey framework. The code for the answer and an AWS Cloud Improvement Equipment (AWS CDK) template is accessible within the GitHub repository.
Challenges
An AI platform administrator wants to offer standardized and quick access to FMs to a number of improvement groups.
The next are among the challenges to offer ruled entry to basis fashions:
Price and utilization monitoring – Observe and audit particular person tenant prices and utilization of basis fashions, and supply chargeback prices to particular price facilities
Price range and utilization controls – Handle API quota, finances, and utilization limits for the permitted use of basis fashions over an outlined frequency per tenant
Entry management and mannequin governance – Outline entry controls for particular permit listed fashions per tenant
Multi-tenant standardized API – Present constant entry to basis fashions with OpenAPI requirements
Centralized administration of API – Present a single layer to handle API keys for accessing fashions
Mannequin variations and updates – Deal with new and up to date mannequin model rollouts
Answer overview
On this resolution, we consult with a multi-tenant strategy. A tenant right here can vary from a person person, a particular undertaking, workforce, and even a whole division. As we talk about the strategy, we use the time period workforce, as a result of it’s the commonest. We use API keys to limit and monitor API entry for groups. Every workforce is assigned an API key for entry to the FMs. There might be completely different person authentication and authorization mechanisms deployed in a corporation. For simplicity, we don’t embody these on this resolution. You might also combine present id suppliers with this resolution.
The next diagram summarizes the answer structure and key parts. Groups (tenants) assigned to separate price facilities devour Amazon Bedrock FMs through an API service. To trace consumption and value per workforce, the answer logs knowledge for every particular person invocation, together with the mannequin invoked, variety of tokens for textual content technology fashions, and picture dimensions for multi-modal fashions. As well as, it aggregates the invocations per mannequin and prices by every workforce.
You possibly can deploy the answer in your personal account utilizing the AWS CDK. AWS CDK is an open supply software program improvement framework to mannequin and provision your cloud utility sources utilizing acquainted programming languages. The AWS CDK code is accessible within the GitHub repository.
Within the following sections, we talk about the important thing parts of the answer in additional element.
Capturing basis mannequin utilization per workforce
The workflow to seize FM utilization per workforce consists of the next steps (as numbered within the previous diagram):
A workforce’s utility sends a POST request to Amazon API Gateway with the mannequin to be invoked within the model_id question parameter and the person immediate within the request physique.
API Gateway routes the request to an AWS Lambda operate (bedrock_invoke_model) that’s liable for logging workforce utilization data in Amazon CloudWatch and invoking the Amazon Bedrock mannequin.
Amazon Bedrock supplies a VPC endpoint powered by AWS PrivateLink. On this resolution, the Lambda operate sends the request to Amazon Bedrock utilizing PrivateLink to ascertain a personal connection between the VPC in your account and the Amazon Bedrock service account. To be taught extra about PrivateLink, see Use AWS PrivateLink to arrange personal entry to Amazon Bedrock.
After the Amazon Bedrock invocation, Amazon CloudTrail generates a CloudTrail occasion.
If the Amazon Bedrock name is profitable, the Lambda operate logs the next data relying on the kind of invoked mannequin and returns the generated response to the applying:
team_id – The distinctive identifier for the workforce issuing the request.
requestId – The distinctive identifier of the request.
model_id – The ID of the mannequin to be invoked.
inputTokens – The variety of tokens despatched to the mannequin as a part of the immediate (for textual content technology and embeddings fashions).
outputTokens – The utmost variety of tokens to be generated by the mannequin (for textual content technology fashions).
peak – The peak of the requested picture (for multi-modal fashions and multi-modal embeddings fashions).
width – The width of the requested picture (for multi-modal fashions solely).
steps – The steps requested (for Stability AI fashions).
Monitoring prices per workforce
A special circulation aggregates the utilization data, then calculates and saves the on-demand prices per workforce each day. By having a separate circulation, we be sure that price monitoring doesn’t impression the latency and throughput of the mannequin invocation circulation. The workflow steps are as follows:
An Amazon EventBridge rule triggers a Lambda operate (bedrock_cost_tracking) every day.
The Lambda operate will get the utilization data from CloudWatch for the day gone by, calculates the related prices, and shops the info aggregated by team_id and model_id in Amazon Easy Storage Service (Amazon S3) in CSV format.
To question and visualize the info saved in Amazon S3, you may have completely different choices, together with S3 Choose, and Amazon Athena and Amazon QuickSight.
Controlling utilization per workforce
A utilization plan specifies who can entry a number of deployed APIs and optionally units the goal request charge to begin throttling requests. The plan makes use of API keys to establish API shoppers who can entry the related API for every key. You should utilize API Gateway utilization plans to throttle requests that exceed predefined thresholds. You may also use API keys and quota limits, which allow you to set the utmost variety of requests per API key every workforce is permitted to difficulty inside a specified time interval. That is along with Amazon Bedrock service quotas which can be assigned solely on the account stage.
Conditions
Earlier than you deploy the answer, ensure you have the next:
Deploy the AWS CDK stack
Comply with the directions within the README file of the GitHub repository to configure and deploy the AWS CDK stack.
The stack deploys the next sources:
Non-public networking atmosphere (VPC, personal subnets, safety group)
IAM function for controlling mannequin entry
Lambda layers for the mandatory Python modules
Lambda operate invoke_model
Lambda operate list_foundation_models
Lambda operate cost_tracking
Relaxation API (API Gateway)
API Gateway utilization plan
API key related to the utilization plan
Onboard a brand new workforce
For offering entry to new groups, you’ll be able to both share the identical API key throughout completely different groups and observe the mannequin consumptions by offering a distinct team_id for the API invocation, or create devoted API keys used for accessing Amazon Bedrock sources by following the directions offered within the README.
The stack deploys the next sources:
API Gateway utilization plan related to the beforehand created REST API
API key related to the utilization plan for the brand new workforce, with reserved throttling and burst configurations for the API
For extra details about API Gateway throttling and burst configurations, consult with Throttle API requests for higher throughput.
After you deploy the stack, you’ll be able to see that the brand new API key for team-2 is created as properly.
Configure mannequin entry management
The platform administrator can permit entry to particular basis fashions by enhancing the IAM coverage related to the Lambda operate invoke_model. The
IAM permissions are outlined within the file setup/stack_constructs/iam.py. See the next code:
Invoke the service
After you may have deployed the answer, you’ll be able to invoke the service instantly out of your code. The next
is an instance in Python for consuming the invoke_model API for textual content technology by means of a POST request:
Output: Amazon Bedrock is an inside know-how platform developed by Amazon to run and function lots of their companies and merchandise. Some key issues about Bedrock …
The next is one other instance in Python for consuming the invoke_model API for embeddings technology by means of a POST request:
model_id = “amazon.titan-embed-text-v1” #the mannequin id for the Amazon Titan Embeddings Textual content mannequin
immediate = “What’s Amazon Bedrock?”
response = requests.submit(
f”{api_url}/invoke_model?model_id={model_id}”,
json={“inputs”: immediate, “parameters”: model_kwargs},
headers={
“x-api-key”: api_key, #key for querying the API
“team_id”: team_id #distinctive tenant identifier,
“embeddings”: “true” #boolean worth for the embeddings mannequin
}
)
textual content = response.json()[0][“embedding”]
Output: 0.91796875, 0.45117188, 0.52734375, -0.18652344, 0.06982422, 0.65234375, -0.13085938, 0.056884766, 0.092285156, 0.06982422, 1.03125, 0.8515625, 0.16308594, 0.079589844, -0.033935547, 0.796875, -0.15429688, -0.29882812, -0.25585938, 0.45703125, 0.044921875, 0.34570312 …
Entry denied to basis fashions
The next is an instance in Python for consuming the invoke_model API for textual content technology by means of a POST request with an entry denied response:
<Response [500]> “Traceback (most up-to-date name final):n File ”/var/activity/index.py”, line 213, in lambda_handlern response = _invoke_text(bedrock_client, model_id, physique, model_kwargs)n File ”/var/activity/index.py”, line 146, in _invoke_textn increase en File ”/var/activity/index.py”, line 131, in _invoke_textn response = bedrock_client.invoke_model(n File ”/choose/python/botocore/shopper.py”, line 535, in _api_calln return self._make_api_call(operation_name, kwargs)n File ”/choose/python/botocore/shopper.py”, line 980, in _make_api_calln increase error_class(parsed_response, operation_name)nbotocore.errorfactory.AccessDeniedException: An error occurred (AccessDeniedException) when calling the InvokeModel operation: Your account isn’t approved to invoke this API operation.n”
Price estimation instance
When invoking Amazon Bedrock fashions with on-demand pricing, the overall price is calculated because the sum of the enter and output prices. Enter prices are based mostly on the variety of enter tokens despatched to the mannequin, and output prices are based mostly on the tokens generated. The costs are per 1,000 enter tokens and per 1,000 output tokens. For extra particulars and particular mannequin costs, consult with Amazon Bedrock Pricing.
Let’s have a look at an instance the place two groups, team1 and team2, entry Amazon Bedrock by means of the answer on this submit. The utilization and value knowledge saved in Amazon S3 in a single day is proven within the following desk.
The columns input_tokens and output_tokens retailer the overall enter and output tokens throughout mannequin invocations per mannequin and per workforce, respectively, for a given day.
The columns input_cost and output_cost retailer the respective prices per mannequin and per workforce. These are calculated utilizing the next formulation:
input_cost = input_token_count * model_pricing[“input_cost”] / 1000output_cost = output_token_count * model_pricing[“output_cost”] / 1000
team_id
model_id
input_tokens
output_tokens
invocations
input_cost
output_cost
Team1
amazon.titan-tg1-large
24000
2473
1000
0.0072
0.00099
Team1
anthropic.claude-v2
2448
4800
24
0.02698
0.15686
Team2
amazon.titan-tg1-large
35000
52500
350
0.0105
0.021
Team2
ai21.j2-grande-instruct
4590
9000
45
0.05738
0.1125
Team2
anthropic.claude-v2
1080
4400
20
0.0119
0.14379
Finish-to-end view of a practical multi-tenant serverless SaaS atmosphere
Let’s perceive what an end-to-end practical multi-tenant serverless SaaS atmosphere may appear to be. The next is a reference structure diagram.
This structure diagram is a zoomed-out model of the earlier structure diagram defined earlier within the submit, the place the earlier structure diagram explains the small print of one of many microservices talked about (foundational mannequin service). This diagram explains that, other than foundational mannequin service, it is advisable to produce other parts as properly in your multi-tenant SaaS platform to implement a practical and scalable platform.
Let’s undergo the small print of the structure.
Tenant purposes
The tenant purposes are the entrance finish purposes that work together with the atmosphere. Right here, we present a number of tenants accessing from completely different native or AWS environments. The entrance finish purposes might be prolonged to incorporate a registration web page for brand new tenants to register themselves and an admin console for directors of the SaaS service layer. If the tenant purposes require a customized logic to be carried out that wants interplay with the SaaS atmosphere, they’ll implement the specs of the applying adaptor microservice. Instance situations might be including customized authorization logic whereas respecting the authorization specs of the SaaS atmosphere.
Shared companies
The next are shared companies:
Tenant and person administration companies –These companies are liable for registering and managing the tenants. They supply the cross-cutting performance that’s separate from utility companies and shared throughout the entire tenants.
Basis mannequin service –The answer structure diagram defined originally of this submit represents this microservice, the place the interplay from API Gateway to Lambda features is occurring inside the scope of this microservice. All tenants use this microservice to invoke the foundations fashions from Anthropic, AI21, Cohere, Stability, Meta, and Amazon, in addition to fine-tuned fashions. It additionally captures the knowledge wanted for utilization monitoring in CloudWatch logs.
Price monitoring service –This service tracks the associated fee and utilization for every tenant. This microservice runs on a schedule to question the CloudWatch logs and output the aggregated utilization monitoring and inferred price to the info storage. The fee monitoring service might be prolonged to construct additional reviews and visualization.
Utility adaptor service
This service presents a set of specs and APIs {that a} tenant might implement so as to combine their customized logic to the SaaS atmosphere. Based mostly on how a lot customized integration is required, this part might be optionally available for tenants.
Multi-tenant knowledge retailer
The shared companies retailer their knowledge in an information retailer that may be a single shared Amazon DynamoDB desk with a tenant partitioning key that associates DynamoDB objects with particular person tenants. The fee monitoring shared service outputs the aggregated utilization and value monitoring knowledge to Amazon S3. Based mostly on the use case, there might be an application-specific knowledge retailer as properly.
A multi-tenant SaaS atmosphere can have much more parts. For extra data, consult with Constructing a Multi-Tenant SaaS Answer Utilizing AWS Serverless Companies.
Assist for a number of deployment fashions
SaaS frameworks sometimes define two deployment fashions: pool and silo. For the pool mannequin, all tenants entry FMs from a shared atmosphere with widespread storage and compute infrastructure. Within the silo mannequin, every tenant has its personal set of devoted sources. You possibly can examine isolation fashions within the SaaS Tenant Isolation Methods whitepaper.
The proposed resolution might be adopted for each SaaS deployment fashions. Within the pool strategy, a centralized AWS atmosphere hosts the API, storage, and compute sources. In silo mode, every workforce accesses APIs, storage, and compute sources in a devoted AWS atmosphere.
The answer additionally suits with the obtainable consumption plans offered by Amazon Bedrock. AWS supplies a selection of two consumptions plan for inference:
On-Demand – This mode lets you use basis fashions on a pay-as-you-go foundation with out having to make any time-based time period commitments
Provisioned Throughput – This mode lets you provision ample throughput to fulfill your utility’s efficiency necessities in trade for a time-based time period dedication
For extra details about these choices, consult with Amazon Bedrock Pricing.
The serverless SaaS reference resolution described on this submit can apply the Amazon Bedrock consumption plans to offer primary and premium tiering choices to end-users. Fundamental may embody On-Demand or Provisioned Throughput consumption of Amazon Bedrock and will embody particular utilization and finances limits. Tenant limits might be enabled by throttling requests based mostly on requests, token sizes, or finances allocation. Premium tier tenants may have their very own devoted sources with provisioned throughput consumption of Amazon Bedrock. These tenants would sometimes be related to manufacturing workloads that require excessive throughput and low latency entry to Amazon Bedrock FMs.
Conclusion
On this submit, we mentioned how one can construct an inside SaaS platform to entry basis fashions with Amazon Bedrock in a multi-tenant setup with a give attention to monitoring prices and utilization, and throttling limits for every tenant. Further matters to discover embody integrating present authentication and authorization options within the group, enhancing the API layer to incorporate net sockets for bi-directional shopper server interactions, including content material filtering and different governance guardrails, designing a number of deployment tiers, integrating different microservices within the SaaS structure, and plenty of extra.
The complete code for this resolution is accessible within the GitHub repository.
For extra details about SaaS-based frameworks, consult with SaaS Journey Framework: Constructing a New SaaS Answer on AWS.
Concerning the Authors
Hasan Poonawala is a Senior AI/ML Specialist Options Architect at AWS, working with Healthcare and Life Sciences prospects. Hasan helps design, deploy and scale Generative AI and Machine studying purposes on AWS. He has over 15 years of mixed work expertise in machine studying, software program improvement and knowledge science on the cloud. In his spare time, Hasan likes to discover nature and spend time with family and friends.
Anastasia Tzeveleka is a Senior AI/ML Specialist Options Architect at AWS. As a part of her work, she helps prospects throughout EMEA construct basis fashions and create scalable generative AI and machine studying options utilizing AWS companies.
Bruno Pistone is a Generative AI and ML Specialist Options Architect for AWS based mostly in Milan. He works with giant prospects serving to them to deeply perceive their technical wants and design AI and Machine Studying options that make the perfect use of the AWS Cloud and the Amazon Machine Studying stack. His experience embody: Machine Studying finish to finish, Machine Studying Industrialization, and Generative AI. He enjoys spending time along with his mates and exploring new locations, in addition to travelling to new locations.
Vikesh Pandey is a Generative AI/ML Options architect, specialising in monetary companies the place he helps monetary prospects construct and scale Generative AI/ML platforms and resolution which scales to a whole lot to even 1000’s of customers. In his spare time, Vikesh likes to put in writing on varied weblog boards and construct legos along with his child.