Posts in category: Amazon AWS

Vision loss comes in various forms. For some, it’s from birth, for others, it’s a slow descent over time which comes with many expiration dates: The day you can’t see pictures, recognize yourself, or loved ones faces or even read your mail. In our previous blogpost Enable the Visually Impaired to Hear Documents using Amazon Textract and Amazon Polly, we showed you our Text to Speech application called “Read for Me”. Accessibility has come a long way, but what about images?

At the 2022 AWS re:Invent conference in Las Vegas, we demonstrated “Describe for Me” at the AWS Builders’ Fair, a website which helps the visually impaired understand images through image caption, facial recognition, and text-to-speech, a technology we refer to as “Image to Speech.” Through the use of multiple AI/ML services, “Describe For Me” generates a caption of an input image and will read it back in a clear, natural-sounding voice in a variety of languages and dialects.

In this blog post we walk you through the Solution Architecture behind “Describe For Me”, and the design considerations of our solution.

Solution Overview

The following Reference Architecture shows the workflow of a user taking a picture with a phone and playing an MP3 of the captioning the image.

The workflow includes the below steps,

1. AWS Amplify distributes the DescribeForMe web app consisting of HTML, JavaScript, and CSS to end users’ mobile devices.
2. The Amazon Cognito Identity pool grants temporary access to the Amazon S3 bucket.
3. The user uploads an image file to the Amazon S3 bucket using AWS SDK through the web app.
4. The DescribeForMe web app invokes the backend AI services by sending the Amazon S3 object Key in the payload to Amazon API Gateway
5. Amazon API Gateway instantiates an AWS Step Functions workflow. The state Machine orchestrates the Artificial Intelligence /Machine Learning (AI/ML) services Amazon Rekognition, Amazon SageMaker, Amazon Textract, Amazon Translate, and Amazon Polly  using AWS lambda functions.
6. The AWS Step Functions workflow creates an audio file as output and stores it in Amazon S3 in MP3 format.
7. A pre-signed URL with the location of the audio file stored in Amazon S3 is sent back to the user’s browser through Amazon API Gateway. The user’s mobile device plays the audio file using the pre-signed URL.

Solution Walkthrough

In this section, we focus on the design considerations for why we chose

1. parallel processing within an AWS Step Functions workflow
2. unified sequence-to-sequence pre-trained machine learning model OFA (One For All) from Hugging Face to Amazon SageMaker for image caption
3. Amazon Rekognition for facial recognition

For a more detailed overview of why we chose a serverless architecture, synchronous workflow, express step functions workflow, headless architecture and the benefits gained, please read our previous blog post Enable the Visually Impaired to Hear Documents using Amazon Textract and Amazon Polly. 

Parallel Processing

Using parallel processing within the Step Functions workflow reduced compute time up to 48%. Once the user uploads the image to the S3 bucket, Amazon API Gateway instantiates an AWS Step Functions workflow. Then the below three Lambda functions process the image within the Step Functions workflow in parallel.

• The first Lambda function called describe_image analyzes the image using the OFA_IMAGE_CAPTION model hosted on a SageMaker real-time endpoint to provide image caption.
• The second Lambda function called describe_faces first checks if there are faces using Amazon Rekognition’s Detect Faces API, and if true, it calls the Compare Faces API. The reason for this is Compare Faces will throw an error if there are no faces found in the image. Also, calling Detect Faces first is faster than simply running Compare Faces and handling errors, so for images without faces in them, processing time will be faster.
• The third Lambda function called extract_text handles text-to-speech utilizing Amazon Textract, and Amazon Comprehend.

Executing the Lambda functions in succession is suitable, but the faster, more efficient way of doing this is through parallel processing. The following table shows the compute time saved for three sample images.

Image	People	Sequential Time	Parallel Time	Time Savings (%)	Caption
	0	1869ms	1702ms	8%	A tabby cat curled up in a fluffy white bed.
	1	4277ms	2197ms	48%	A woman in a green blouse and black cardigan smiles at the camera. I recognize one person: Kanbo.
	4	6603ms	3904ms	40%	People standing in front of the Amazon Spheres. I recognize 3 people: Kanbo, Jack, and Ayman.

Image Caption

Hugging Face is an open-source community and data science platform that allows users to share, build, train, and deploy machine learning models. After exploring models available in the Hugging Face model hub, we chose to use the OFA model because as described by the authors, it is “a task-agnostic and modality-agnostic framework that supports Task Comprehensiveness”.

OFA is a step towards “One For All”, as it is a unified multimodal pre-trained model that can transfer to a number of downstream tasks effectively. While the OFA model supports many tasks including visual grounding, language understanding, and image generation, we used the OFA model for image captioning in the Describe For Me project to perform the image to text portion of the application. Check out the official repository of OFA (ICML 2022), paper to learn about OFA’s Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework.

To integrate OFA in our application we cloned the repo from Hugging Face and containerized the model to deploy it to a SageMaker endpoint. The notebook in this repo is an excellent guide to deploy the OFA large model in a Jupyter notebook in SageMaker. After containerizing your inference script, the model is ready to be deployed behind a SageMaker endpoint as described in the SageMaker documentation. Once the model is deployed, create an HTTPS endpoint which can be integrated with the “describe_image” lambda function that analyzes the image to create the image caption. We deployed the OFA tiny model because it is a smaller model and can be deployed in a shorter period of time while achieving similar performance.

Examples of image to speech content generated by “Describe For Me“ are shown below:

The aurora borealis, or northern lights, fill the night sky above a silhouette of a house..

A dog sleeps on a red blanket on a hardwood floor, next to an open suitcase filled with toys..

A tabby cat curled up in a fluffy white bed.

Facial recognition

Amazon Rekognition Image provides the DetectFaces operation that looks for key facial features such as eyes, nose, and mouth to detect faces in an input image. In our solution we leverage this functionality to detect any people in the input image. If a person is detected, we then use the CompareFaces operation to compare the face in the input image with the faces that “Describe For Me“ has been trained with and describe the person by name. We chose to use Rekognition for facial detection because of the high accuracy and how simple it was to integrate into our application with the out of the box capabilities.

A group of people posing for a picture in a room. I recognize 4 people: Jack, Kanbo, Alak, and Trac. There was text found in the image as well. It reads: AWS re: Invent

Potential Use Cases

Alternate Text Generation for web images

All images on a web site are required to have an alternative text so that screen readers can speak them to the visually impaired. It’s also good for search engine optimization (SEO). Creating alt captions can be time consuming as a copywriter is tasked with providing them within a design document. The Describe For Me API could automatically generate alt-text for images. It could also be utilized as a browser plugin to automatically add image caption to images missing alt text on any website.

Audio Description for Video

Audio Description provides a narration track for video content to help the visually impaired follow along with movies. As image caption becomes more robust and accurate, a workflow involving the creation of an audio track based upon descriptions for key parts of a scene could be possible. Amazon Rekognition can already detect scene changes, logos, and credit sequences, and celebrity detection. A future version of describe would allow for automating this key feature for films and videos.

Conclusion

In this post, we discussed how to use AWS services, including AI and serverless services, to aid the visually impaired to see images. You can learn more about the Describe For Me project and use it by visiting describeforme.com. Learn more about the unique features of Amazon SageMaker, Amazon Rekognition and the AWS partnership with Hugging Face.

Third Party ML Model Disclaimer for Guidance

This guidance is for informational purposes only. You should still perform your own independent assessment, and take measures to ensure that you comply with your own specific quality control practices and standards, and the local rules, laws, regulations, licenses and terms of use that apply to you, your content, and the third-party Machine Learning model referenced in this guidance. AWS has no control or authority over the third-party Machine Learning model referenced in this guidance, and does not make any representations or warranties that the third-party Machine Learning model is secure, virus-free, operational, or compatible with your production environment and standards. AWS does not make any representations, warranties or guarantees that any information in this guidance will result in a particular outcome or result.

About the Authors

Jack Marchetti is a Senior Solutions architect at AWS focused on helping customers modernize and implement serverless, event-driven architectures. Jack is legally blind and resides in Chicago with his wife Erin and cat Minou. He also is a screenwriter, and director with a primary focus on Christmas movies and horror. View Jack’s filmography at his IMDb page.

Alak Eswaradass is a Senior Solutions Architect at AWS based in Chicago, Illinois. She is passionate about helping customers design cloud architectures utilizing AWS services to solve business challenges. Alak is enthusiastic about using SageMaker to solve a variety of ML use cases for AWS customers. When she’s not working, Alak enjoys spending time with her daughters and exploring the outdoors with her dogs.

Kandyce Bohannon is a Senior Solutions Architect based out of Minneapolis, MN. In this role, Kandyce works as a technical advisor to AWS customers as they modernize technology strategies especially related to data and DevOps to implement best practices in AWS. Additionally, Kandyce is passionate about mentoring future generations of technologists and showcasing women in technology through the AWS She Builds Tech Skills program.

Trac Do is a Solutions Architect at AWS. In his role, Trac works with enterprise customers to support their cloud migrations and application modernization initiatives. He is passionate about learning customers’ challenges and solving them with robust and scalable solutions using AWS services. Trac currently lives in Chicago with his wife and 3 boys. He is a big aviation enthusiast and in the process of completing his Private Pilot License.

Read More

Amazon Kendra is a highly accurate and simple-to-use intelligent search service powered by machine learning (ML). Amazon Kendra offers a suite of data source connectors to simplify the process of ingesting and indexing your content, wherever it resides.

Valuable data in organizations is stored in both structured and unstructured repositories. Amazon Kendra can pull together data across several structured and unstructured knowledge base repositories to index and search on.

One such knowledge base repository is Microsoft SharePoint, and we are excited to announce that we have updated the SharePoint connector for Amazon Kendra to add even more capabilities. In this new version (V2.0), we have added support for SharePoint Subscription Edition and multiple authentication and sync modes to index contents based on new, modified, or deleted contents.

You can now also choose OAuth 2.0 to authenticate with SharePoint Online. Multiple synchronization options are available to update your index when your data source content changes. You can filter the search results based on the user and group information to ensure your search results are only shown based on user access rights.

In this post, we demonstrate how to index content from SharePoint using the Amazon Kendra SharePoint connector V2.0.

Solution overview

You can use Amazon Kendra as a central location to index the content provided by various data sources for intelligent search. In the following sections, we go through the steps to create an index, add the SharePoint connector, and test the solution.

Prerequisites

To get started, you need the following:

• A SharePoint (Server or Online) user with owner rights.
• An AWS account with privileges to create AWS Identity and Access Management (IAM) roles and policies. For more information, see Overview of access management: Permissions and policies.
• Basic knowledge of AWS.

Create an Amazon Kendra Index

To create an Amazon Kendra index, complete the following steps:

1. On the Amazon Kendra console, choose Create an index.
2. For Index name, enter a name for the index (for example, my-sharepoint-index).
3. Enter an optional description.
4. Choose Create a new role.
5. For Role name, enter an IAM role name.
6. ­Configure optional encryption settings and tags.
7. Choose Next.
8. For Access control settings, choose Yes.
9. For Token configuration, set Token type to JSON and leave the default values for Username and Groups.
10. For User-group expansion, leave the defaults.
11. Choose Next.
12. For Specify provisioning, select Developer edition, which is suited for building a proof of concept and experimentation, and choose Create.

Add a SharePoint data source to your Amazon Kendra index

One of the advantages of implementing Amazon Kendra is that you can use a set of pre-built connectors for data sources such as Amazon Simple Storage Service (Amazon S3), Amazon Relational Database Service (Amazon RDS), SharePoint Online, and Salesforce.

To add a SharePoint data source to your index, complete the following steps:

1. On the Amazon Kendra console, navigate to the index that you created.
2. Choose Data sources in the navigation pane.
3. Under SharePoint Connector V2.0, choose Add connector.
4. For Data source name, enter a name (for example, my-sharepoint-data-source).
5. Enter an optional description.
6. Choose English (en) for Default language.
7. Enter optional tags.
8. Choose Next.

Depending on the hosting option your SharePoint application is using, pick the appropriate hosting method. The required attributes for the connector configuration appear based on the hosting method you choose.

9. If you select SharePoint Online, complete the following steps:
   • Enter the URL for your SharePoint Online repository.
   • Choose your authentication option (these authentication details will be used by the SharePoint connector to integrate with your SharePoint application).
   • Enter the tenant ID of your SharePoint Online application.
   • For AWS Secrets Manager secret, pick the secret that has SharePoint Online application credentials or create a new secret and add the connection details (for example, AmazonKendra-SharePoint-my-sharepoint-online-secret).

To learn more about AWS Secrets Manger, refer to Getting started with Secrets Manager.

The SharePoint connector uses the clientId, clientSecret, userName, and password information to authenticate with the SharePoint Online application. These details can be accessed on the App registrations page on the Azure portal, if the SharePoi­nt Online application is already registered.

10. If you select SharePoint Server, complete the following steps:
    • Choose your SharePoint version (for example, we use SharePoint 2019 for this post).
    • Enter the site URL for your SharePoint Server repository.
    • For SSL certificate location, enter the path to the S3 bucket file where the SharePoint Server SSL certificate is located.
    • Enter the web proxy host name and the port number details if the SharePoint server requires a proxy connection.

For this post, no web proxy is used because the SharePoint application used for this example is a public-facing application.

• • Select the authorization option for the Access Control List (ACL) configuration.

These authentication details will be used by the SharePoint connector to integrate with your SharePoint instance.

11. For AWS Secrets Manager secret, choose the secret that has SharePoint Server credentials or create a new secret and add the connection details (for example, AmazonKendra-my-sharepoint-server-secret).

The SharePoint connector uses the user name and password information to authenticate with the SharePoint Server application. If you use an email ID with domain form IDP as the ACL setting, the LDAP server endpoint, search base, LDAP user name, and LDAP password are also required.

To achieve a granular level of control over the searchable and displayable content, identity crawler functionality is introduced in the SharePoint connector V2.0.

12. Enable the identity crawler and select Crawl Local Group Mapping and Crawl AD Group Mapping.
13. For Virtual Private Cloud (VPC), choose the VPC through which the SharePoint application is reachable from your SharePoint connector.

For this post, we choose No VPC because the SharePoint application used for this example is a public-facing application deployed on Amazon Elastic Compute Cloud (Amazon EC2) instances.

14. Chose Create a new role (Recommended) and provide a role name, such as AmazonKendra-sharepoint-v2.
15. Choose Next.
16. Select entities that you would like to include for indexing. You can choose All or specific entities based on your use case. For this post, we choose All.

You can also include or exclude documents by using regular expressions. You can define patterns that Amazon Kendra either uses to exclude certain documents from indexing or include only documents with that pattern. For more information, refer to SharePoint Configuration.

17. Select your sync mode to update the index when your data source content changes.

You can sync and index all contents in all entities, regardless of the previous sync process by selecting Full sync, or only sync new, modified, or deleted content, or only sync new or modified content. For this post, we select Full sync.

18. Choose a frequency to run the sync schedule, such as Run on demand.
19. Choose Next.

In this next step, you can create field mappings to add an extra layer of metadata to your documents. This enables you to improve accuracy through manual tuning, filtering, and faceting.

20. Review the default field mappings information and choose Next.
21. As a last step, review the configuration details and choose Add data source to create the SharePoint connector data source for the Amazon Kendra index.

Test the solution

Now you’re ready to prepare and test the Amazon Kendra search features using the SharePoint connector.

For this post, AWS getting started documents are added to the SharePoint data source. The sample dataset used for this post can be downloaded from AWS_Whitepapers.zip. This dataset has PDF documents categorized into multiple directories based on the type of documents (for example, documents related to AWS database options, security, and ML).

Also, sample dataset directories in SharePoint are configured with user email IDs and group details so that only the users and groups with permissions can access specific directories or individual files.

To achieve granular-level control over the search results, the SharePoint connector crawls the local or Active Directory (AD) group mapping in the SharePoint data source in addition to the content when the identity crawler is enabled with the local and AD group mapping options selected. With this capability, Amazon Kendra indexed content is searchable and displayable based on the access control permissions of the users and groups.

To sync our index with SharePoint content, complete the following steps:

1. On the Amazon Kendra console, navigate to the index you created.
2. Choose Data sources in the navigation pane and select the SharePoint data source.
3. Choose Sync now to start the process to index the content from the SharePoint application and wait for the process to complete.

If you encounter any sync issues, refer to Troubleshooting data sources for more information.

When the sync process is successful, the value for Last sync status will be set to Successful – service is operating normally. The content from the SharePoint application is now indexed and ready for queries.

4. Choose Search indexed content (under Data management) in the navigation pane.
5. Enter a test query in the search field and press Enter.

A test query such as “What is the durability of S3?” provides the following Amazon Kendra suggested answers. Note that the results for this query are from all the indexed content. This is because there is no context of user name or group information for this query.

6. To test the access-controlled search, expand Test query with username or groups and choose Apply user name or groups to add a user name (email ID) or group information.

When an Experience Builder app is used, it includes the user context, and therefore you don’t need to add user or group IDs explicitly.

7. For this post, access to the Databases directory in the SharePoint site is provided to the database-specialists group only.
8. Enter a new test query and press Enter.

In this example, only the content in the Databases directory is searched and the results are displayed. This is because the database-specialists group only has access to the Databases directory.

Congratulations! You have successfully used Amazon Kendra to surface answers and insights based on the content indexed from your SharePoint application.

Amazon Kendra Experience Builder

You can build and deploy an Amazon Kendra search application without the need for any front-end code. Amazon Kendra Experience Builder helps you build and deploy a fully functional search application in a few clicks so that you can start searching right away.

Refer to Building a search experience with no code for more information.

Clean up

To avoid incurring future costs, clean up the resources you created as part of this solution. If you created a new Amazon Kendra index while testing this solution, delete it if you no longer need it. If you only added a new data source using the Amazon Kendra connector for SharePoint, delete that data source after your solution review is completed.

Refer to Deleting an index and data source for more information.

Conclusion

In this post, we showed how to ingest documents from your SharePoint application into your Amazon Kendra index. We also reviewed some of the new features that are introduced in the new version of the SharePoint connector.

To learn more about the Amazon Kendra connector for SharePoint, refer to Microsoft SharePoint connector V2.0.

Finally, don’t forget to check out the other blog posts about Amazon Kendra!

About the Author

Udaya Jaladi is a Solutions Architect at Amazon Web Services (AWS), specializing in assisting Independent Software Vendor (ISV) customers. With expertise in cloud strategies, AI/ML technologies, and operations, Udaya serves as a trusted advisor to executives and engineers, offering personalized guidance on maximizing the cloud’s potential and driving innovative product development. Leveraging his background as an Enterprise Architect (EA) across diverse business domains, Udaya excels in architecting scalable cloud solutions tailored to meet the specific needs of ISV customers.

Read More

AWS delivers services that meet customers’ artificial intelligence (AI) and machine learning (ML) needs with services ranging from custom hardware like AWS Trainium and AWS Inferentia to generative AI foundation models (FMs) on Amazon Bedrock. In February 2022, AWS and Hugging Face announced a collaboration to make generative AI more accessible and cost efficient.

Generative AI has grown at an accelerating rate from the largest pre-trained model in 2019 having 330 million parameters to more than 500 billion parameters today. The performance and quality of the models also improved drastically with the number of parameters. These models span tasks like text-to-text, text-to-image, text-to-embedding, and more. You can use large language models (LLMs), more specifically, for tasks including summarization, metadata extraction, and question answering.

Amazon SageMaker JumpStart is an ML hub that can helps you accelerate your ML journey. With JumpStart, you can access pre-trained models and foundation models from the Foundations Model Hub to perform tasks like article summarization and image generation. Pre-trained models are fully customizable for your use cases and can be easily deployed into production with the user interface or SDK. Most importantly, none of your data is used to train the underlying models. Because all data is encrypted and doesn’t leave the virtual private cloud (VPC), you can trust that your data will remain private and confidential.

This post focuses on building a serverless meeting summarization using Amazon Transcribe to transcribe meeting audio and the Flan-T5-XL model from Hugging Face (available on JumpStart) for summarization.

Solution overview

The Meeting Notes Generator Solution creates an automated serverless pipeline using AWS Lambda for transcribing and summarizing audio and video recordings of meetings. The solution can be deployed with other FMs available on JumpStart.

The solution includes the following components:

• A shell script for creating a custom Lambda layer
• A configurable AWS CloudFormation template for deploying the solution
• Lambda function code for starting Amazon Transcribe transcription jobs
• Lambda function code for invoking a SageMaker real-time endpoint hosting the Flan T5 XL model

The following diagram illustrates this architecture.

As shown in the architecture diagram, the meeting recordings, transcripts, and notes are stored in respective Amazon Simple Storage Service (Amazon S3) buckets. The solution takes an event-driven approach to transcribe and summarize upon S3 upload events. The events trigger Lambda functions to make API calls to Amazon Transcribe and invoke the real-time endpoint hosting the Flan T5 XL model.

The CloudFormation template and instructions for deploying the solution can be found in the GitHub repository.

Real-time inference with SageMaker

Real-time inference on SageMaker is designed for workloads with low latency requirements. SageMaker endpoints are fully managed and support multiple hosting options and auto scaling. Once created, the endpoint can be invoked with the InvokeEndpoint API. The provided CloudFormation template creates a real-time endpoint with the default instance count of 1, but it can be adjusted based on expected load on the endpoint and as the service quota for the instance type permits. You can request service quota increases on the Service Quotas page of the AWS Management Console.

The following snippet of the CloudFormation template defines the SageMaker model, endpoint configuration, and endpoint using the ModelData and ImageURI of the Flan T5 XL from JumpStart. You can explore more FMs on Getting started with Amazon SageMaker JumpStart. To deploy the solution with a different model, replace the ModelData and ImageURI parameters in the CloudFormation template with the desired model S3 artifact and container image URI, respectively. Check out the sample notebook on GitHub for sample code on how to retrieve the latest JumpStart model artifact on Amazon S3 and the corresponding public container image provided by SageMaker.

  # SageMaker Model
  SageMakerModel:
    Type: AWS::SageMaker::Model
    Properties:
      ModelName: !Sub ${AWS::StackName}-SageMakerModel
      Containers:
        - Image: !Ref ImageURI
          ModelDataUrl: !Ref ModelData
          Mode: SingleModel
          Environment: {
            "MODEL_CACHE_ROOT": "/opt/ml/model",
            "SAGEMAKER_ENV": "1",
            "SAGEMAKER_MODEL_SERVER_TIMEOUT": "3600",
            "SAGEMAKER_MODEL_SERVER_WORKERS": "1",
            "SAGEMAKER_PROGRAM": "inference.py",
            "SAGEMAKER_SUBMIT_DIRECTORY": "/opt/ml/model/code/",
            "TS_DEFAULT_WORKERS_PER_MODEL": 1
          }
      EnableNetworkIsolation: true
      ExecutionRoleArn: !GetAtt SageMakerExecutionRole.Arn

  # SageMaker Endpoint Config
  SageMakerEndpointConfig:
    Type: AWS::SageMaker::EndpointConfig
    Properties:
      EndpointConfigName: !Sub ${AWS::StackName}-SageMakerEndpointConfig
      ProductionVariants:
        - ModelName: !GetAtt SageMakerModel.ModelName
          VariantName: !Sub ${SageMakerModel.ModelName}-1
          InitialInstanceCount: !Ref InstanceCount
          InstanceType: !Ref InstanceType
          InitialVariantWeight: 1.0
          VolumeSizeInGB: 40

  # SageMaker Endpoint
  SageMakerEndpoint:
    Type: AWS::SageMaker::Endpoint
    Properties:
      EndpointName: !Sub ${AWS::StackName}-SageMakerEndpoint
      EndpointConfigName: !GetAtt SageMakerEndpointConfig.EndpointConfigName

Deploy the solution

For detailed steps on deploying the solution, follow the Deployment with CloudFormation section of the GitHub repository.

If you want to use a different instance type or more instances for the endpoint, submit a quota increase request for the desired instance type on the AWS Service Quotas Dashboard.

To use a different FM for the endpoint, replace the ImageURI and ModelData parameters in the CloudFormation template for the corresponding FM.

Test the solution

After you deploy the solution using the Lambda layer creation script and the CloudFormation template, you can test the architecture by uploading an audio or video meeting recording in any of the media formats supported by Amazon Transcribe. Complete the following steps:

1. On the Amazon S3 console, choose Buckets in the navigation pane.
2. From the list of S3 buckets, choose the S3 bucket created by the CloudFormation template named meeting-note-generator-demo-bucket-<aws-account-id>.
3. Choose Create folder.
4. For Folder name, enter the S3 prefix specified in the S3RecordingsPrefix parameter of the CloudFormation template (recordings by default).
5. Choose Create folder.
6. In the newly created folder, choose Upload.
7. Choose Add files and choose the meeting recording file to upload.
8. Choose Upload.

Now we can check for a successful transcription.

1. On the Amazon Transcribe console, choose Transcription jobs in the navigation pane.
2. Check that a transcription job with a corresponding name to the uploaded meeting recording has the status In progress or Complete.
3. When the status is Complete, return to the Amazon S3 console and open the demo bucket.
4. In the S3 bucket, open the transcripts/ folder.
5. Download the generated text file to view the transcription.

We can also check the generated summary.

1. In the S3 bucket, open the notes/ folder.
2. Download the generated text file to view the generated summary.

Prompt engineering

Even though LLMs have improved in the last few years, the models can only take in finite inputs; therefore, inserting an entire transcript of a meeting may exceed the limit of the model and cause an error with the invocation. To design around this challenge, we can break down the context into manageable chunks by limiting the number of tokens in each invocation context. In this sample solution, the transcript is broken down into smaller chunks with a maximum limit on the number of tokens per chunk. Then each transcript chunk is summarized using the Flan T5 XL model. Finally, the chunk summaries are combined to form the context for the final combined summary, as shown in the following diagram.

The following code from the GenerateMeetingNotes Lambda function uses the Natural Language Toolkit (NLTK) library to tokenize the transcript, then it chunks the transcript into sections, each containing up to a certain number of tokens:

# Chunk transcript into chunks
transcript = contents['results']['transcripts'][0]['transcript']
transcript_tokens = word_tokenize(transcript)

num_chunks = int(math.ceil(len(transcript_tokens) / CHUNK_LENGTH))
transcript_chunks = []
for i in range(num_chunks):
    if i == num_chunks - 1:
        chunk = TreebankWordDetokenizer().detokenize(transcript_tokens[CHUNK_LENGTH * i:])
    else:
        chunk = TreebankWordDetokenizer().detokenize(transcript_tokens[CHUNK_LENGTH * i:CHUNK_LENGTH * (i + 1)])
    transcript_chunks.append(chunk)

# Summarize each chunk
chunk_summaries = []
for i in range(len(transcript_chunks)):
    text_input = '{}n{}'.format(transcript_chunks[i], instruction)
    payload = {
        "text_inputs": text_input,
        "max_length": 100,
        "num_return_sequences": 1,
        "top_k": 50,
        "top_p": 0.95,
        "do_sample": True
    }
    query_response = query_endpoint_with_json_payload(json.dumps(payload).encode('utf-8'))
    generated_texts = parse_response_multiple_texts(query_response)
    chunk_summaries.append(generated_texts[0])
    print(generated_texts[0])

Finally, the following code snippet combines the chunk summaries as the context to generate a final summary:

# Create a combined summary
text_input = '{}n{}'.format(' '.join(chunk_summaries), instruction)
payload = {
    "text_inputs": text_input,
    "max_length": 100,
    "num_return_sequences": 1,
    "top_k": 50,
    "top_p": 0.95,
    "do_sample": True
}
query_response = query_endpoint_with_json_payload(json.dumps(payload).encode('utf-8'))
generated_texts = parse_response_multiple_texts(query_response)

results = {
    "summary": generated_texts,
    "chunk_summaries": chunk_summaries
}

The full GenerateMeetingNotes Lambda function can be found in the GitHub repository.

Clean up

To clean up the solution, complete the following steps:

1. Delete all objects in the demo S3 bucket and the logs S3 bucket.
2. Delete the CloudFormation stack.
3. Delete the Lambda layer.

Conclusion

This post demonstrated how to use FMs on JumpStart to quickly build a serverless meeting notes generator architecture with AWS CloudFormation. Combined with AWS AI services like Amazon Transcribe and serverless technologies like Lambda, you can use FMs on JumpStart and Amazon Bedrock to build applications for various generative AI use cases.

For additional posts on ML at AWS, visit the AWS ML Blog.

About the author

Eric Kim is a Solutions Architect (SA) at Amazon Web Services. He works with game developers and publishers to build scalable games and supporting services on AWS. He primarily focuses on applications of artificial intelligence and machine learning.

Read More

This post is co-written with Thatcher Thornberry from bpx energy. 

Facies classification is the process of segmenting lithologic formations from geologic data at the wellbore location. During drilling, wireline logs are obtained, which have depth-dependent geologic information. Geologists are deployed to analyze this log data and determine depth ranges for potential facies of interest from the different types of log data. Accurately classifying these regions is critical for the drilling processes that follow.

Facies classification using AI and machine learning (ML) has become an increasingly popular area of investigation for many oil majors. Many data scientists and business analysts at large oil companies don’t have the necessary skillset to run advanced ML experiments on important tasks such as facies classification. To address this, we show you how to easily prepare and train a best-in-class ML classification model on this problem.

In this post, aimed primarily at those who are already using Snowflake, we explain how you can import both training and validation data for a facies classification task from Snowflake into Amazon SageMaker Canvas and subsequently train the model using a 3+ category prediction model.

Solution overview

Our solution consists of the following steps:

1. Upload facies CSV data from your local machine to Snowflake. For this post, we use data from the following open-source GitHub repo.
2. Configure AWS Identity and Access Management (IAM) roles for Snowflake and create a Snowflake integration.
3. Create a secret for Snowflake credentials (optional, but advised).
4. Import Snowflake directly into Canvas.
5. Build a facies classification model.
6. Analyze the model.
7. Run batch and single predictions using the multi-class model.
8. Share the trained model to Amazon SageMaker Studio.

Prerequisites

Prerequisites for this post include the following:

• An AWS account.
• Canvas set up, with an Amazon SageMaker user profile associated with it.
• A Snowflake account. For steps to create a Snowflake account, refer to How to: Create a Snowflake Free Trial Account
• The Snowflake CLI. For steps to connect to Snowflake by CLI, refer to SnowSQL, the command line interface for connecting to Snowflake. For steps to connect to to Snowflake by CLI, refer to Snowflake SnowSQL: Command Line Tool to access Snowflake.
• An existing database within Snowflake.

Upload facies CSV data to Snowflake

In this section, we take two open-source datasets and upload them directly from our local machine to a Snowflake database. From there, we set up an integration layer between Snowflake and Canvas.

1. Download the training_data.csv and validation_data_nofacies.csv files to your local machine. Make note of where you saved them.
2. Ensuring that you have the correct Snowflake credentials and have installed the Snowflake CLI desktop app, you can federate in. For more information, refer to Log into SnowSQL.
3. Select the appropriate Snowflake warehouse to work within, which in our case is COMPUTE_WH:

USE WAREHOUSE COMPUTE_WH;

4. Choose a database to use for the remainder of the walkthrough:

use demo_db;

5. Create a named file format that will describe a set of staged data to access or load into Snowflake tables.

This can be run either in the Snowflake CLI or in a Snowflake worksheet on the web application. For this post, we run a SnowSQL query in the web application. See Getting Started With Worksheets for instructions to create a worksheet on the Snowflake web application.

6. Create a table in Snowflake using the CREATE statement.

The following statement creates a new table in the current or specified schema (or replaces an existing table).

It’s important that the data types and the order in which they appear are correct, and align with what is found in the CSV files that we previously downloaded. If they’re inconsistent, we’ll run into issues later when we try to copy the data across.

7. Do the same for the validation database.

Note that the schema is a little different to the training data. Again, ensure that the data types and column or feature orders are correct.

8. Load the CSV data file from your local system into the Snowflake staging environment:
   • The following is the syntax of the statement for Windows OS:

     put file://D:path-to-file.csv @DB_Name.PUBLIC.%table_name;

   • The following is the syntax of the statement for Mac OS:

     put file:///path-to-file.csv @DB_NAME.PUBLIC.%table_name;

The following screenshot shows an example command and output from within the SnowSQL CLI.

9. Copy the data into the target Snowflake table.

Here, we load the training CSV data to the target table, which we created earlier. Note that you have to do this for both the training and validation CSV files, copying them into the training and validation tables, respectively.

10. Verify that the data has been loaded into the target table by running a SELECT query (you can do this for both the training and validation data):

select * from TRAINING_DATA

Configure Snowflake IAM roles and create the Snowflake integration

As a prerequisite for this section, please follow the official Snowflake documentation on how to configure a Snowflake Storage Integration to Access Amazon S3.

Retrieve the IAM user for your Snowflake account

Once you have successfully configured your Snowflake storage integration, run the following DESCRIBE INTEGRATION command to retrieve the ARN for the IAM user that was created automatically for your Snowflake account:

DESC INTEGRATION SAGEMAKER_CANVAS_INTEGRATION;

Record the following values from the output:

• STORAGE_AWS_IAM_USER_ARN – The IAM user created for your Snowflake account
• STORAGE_AWS_EXTERNAL_ID – The external ID needed to establish a trust relationship

Update the IAM role trust policy

Now we update the trust policy:

1. On the IAM console, choose Roles in the navigation pane.
2. Choose the role you created.
3. On the Trust relationship tab, choose Edit trust relationship.
4. Modify the policy document as shown in the following code with the DESC STORAGE INTEGRATION output values you recorded in the previous step.

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "",
            "Effect": "Allow",
            "Principal": {
                "AWS": "<snowflake_user_arn>"
            },
            "Action": "sts:AssumeRole",
            "Condition": {
                "StringEquals": {
                    "sts:ExternalId": "<snowflake_external_id>"
                }
            }
        }
    ]
}

5. Choose Update trust policy.

Create an external stage in Snowflake

We use an external stage within Snowflake for loading data from an S3 bucket in your own account into Snowflake. In this step, we create an external (Amazon S3) stage that references the storage integration you created. For more information, see Creating an S3 Stage.

This requires a role that has the CREATE_STAGE privilege for the schema as well as the USAGE privilege on the storage integration. You can grant these privileges to the role as shown in the code in the next step.

Create the stage using the CREATE_STAGE command with placeholders for the external stage and S3 bucket and prefix. The stage also references a named file format object called my_csv_format:

grant create stage on schema public to role <iam_role>;
grant usage on integration SAGEMAKER_CANVAS_INTEGRATION to role <iam_role_arn>;
create stage <external_stage>
storage_integration = SAGEMAKER_CANVAS_INTEGRATION
url = '<s3_bucket>/<prefix>'
file_format = my_csv_format;

Create a secret for Snowflake credentials

Canvas allows you to use the ARN of an AWS Secrets Manager secret or a Snowflake account name, user name, and password to access Snowflake. If you intend to use the Snowflake account name, user name, and password option, skip to the next section, which covers adding the data source.

To create a Secrets Manager secret manually, complete the following steps:

1. On the Secrets Manager console, choose Store a new secret.
2. For Select secret type¸ select Other types of secrets.
3. Specify the details of your secret as key-value pairs.

The names of the key are case-sensitive and must be lowercase.

If you prefer, you can use the plaintext option and enter the secret values as JSON:

{
"username": "<snowflake username>",
"password": "<snowflake password>",
"accountid": "<snowflake account id>"
}

4. Choose Next.
5. For Secret name, add the prefix AmazonSageMaker (for example, our secret is AmazonSageMaker-CanvasSnowflakeCreds).
6. In the Tags section, add a tag with the key SageMaker and value true.

7. Choose Next.
8. The rest of the fields are optional; choose Next until you have the option to choose Store to store the secret.
9. After you store the secret, you’re returned to the Secrets Manager console.
10. Choose the secret you just created, then retrieve the secret ARN.
11. Store this in your preferred text editor for use later when you create the Canvas data source.

Import Snowflake directly into Canvas

To import your facies dataset directly into Canvas, complete the following steps:

1. On the SageMaker console, choose Amazon SageMaker Canvas in the navigation pane.
2. Choose your user profile and choose Open Canvas.
3. On the Canvas landing page, choose Datasets in the navigation pane.
4. Choose Import.

5. Click on Snowflake in the below image and then immediately “Add Connection”.
   
6. Enter the ARN of the Snowflake secret that we previously created, the storage integration name (SAGEMAKER_CANVAS_INTEGRATION), and a unique connection name of your choosing.
7. Choose Add connection.

If all the entries are valid, you should see all the databases associated with the connection in the navigation pane (see the following example for NICK_FACIES).

8. Choose the TRAINING_DATA table, then choose Preview dataset.

If you’re happy with the data, you can edit the custom SQL in the data visualizer.

9. Choose Edit in SQL.
10. Run the following SQL command before importing into Canvas. (This assumes that the database is called NICK_FACIES. Replace this value with your database name.)

SELECT "FACIES", "FORMATION", "WELL_NAME", "DEPTH", "GR", "ILD_LOG10", "DELTAPHI", "PHIND", "PE", "NM_M", "RELPOS" FROM "NICK_FACIES"."PUBLIC"."TRAINING_DATA";

Something similar to the following screenshot should appear in the Import preview section.

11. If you’re happy with the preview, choose Import data.

12. Choose an appropriate data name, ensuring that it’s unique and fewer than 32 characters long.
13. Use the following command to import the validation dataset, using the same method as earlier:

SELECT "FORMATION", "WELL_NAME", "DEPTH", "GR", "ILD_LOG10", "DELTAPHI", "PHIND", "PE", "NM_M", "RELPOS" FROM "NICK_FACIES"."PUBLIC"."VALIDATION_DATA";

Build a facies classification model

To build your facies classification model, complete the following steps:

1. Choose Models in the navigation pane, then choose New Model.
2. Give your model a suitable name.
3. On the Select tab, choose the recently imported training dataset, then choose Select dataset.
4. On the Build tab, drop the WELL_NAME column.

We do this because the well names themselves aren’t useful information for the ML model. They are merely arbitrary names that we find useful to distinguish between the wells themselves. The name we give a particular well is irrelevant to the ML model.

5. Choose FACIES as the target column.
6. Leave Model type as 3+ category prediction.
7. Validate the data.
8. Choose Standard build.

Your page should look similar to the following screenshot just before building your model.

After you choose Standard build, the model enters the analyze stage. You’re provided an expected build time. You can now close this window, log out of Canvas (in order to avoid charges), and return to Canvas at a later time.

Analyze the facies classification model

To analyze the model, complete the following steps:

1. Federate back into Canvas.
2. Locate your previously created model, choose View, then choose Analyze.
3. On the Overview tab, you can see the impact that individual features are having on the model output.
4. In the right pane, you can visualize the impact that a given feature (X axis) is having on the prediction of each facies class (Y axis).

These visualizations will change accordingly depending on the feature you select. We encourage you to explore this page by cycling through all 9 classes and 10 features.

5. On the Scoring tab, we can see the predicted vs. actual facies classification.
6. Choose Advanced metrics to view F1 scores, average accuracy, precision, recall, and AUC.
7. Again, we encourage viewing all the different classes.
8. Choose Download to download an image to your local machine.

In the following image, we can see a number of different advanced metrics, such as the F1 score. In statistical analysis, the F1 score conveys the balance between the precision and the recall of a classification model, and is computed using the following equation: 2*((Precision * Recall)/ (Precision + Recall)).

Run batch and single prediction using the multi-class facies classification model

To run a prediction, complete the following steps:

1. Choose Single prediction to modify the feature values as needed, and get a facies classification returned on the right of the page.

You can then copy the prediction chart image to your clipboard, and also download the predictions into a CSV file.

2. Choose Batch prediction and then choose Select dataset to choose the validation dataset you previously imported.
3. Choose Generate predictions.

You’re redirected to the Predict page, where the Status will read Generating predictions for a few seconds.

After the predictions are returned, you can preview, download, or delete the predictions by choosing the options menu (three vertical dots) next to the predictions.

The following is an example of a predictions preview.

Share a trained model in Studio

You can now share the latest version of the model with another Studio user. This allows data scientists to review the model in detail, test it, make any changes that may improve accuracy, and share the updated model back with you.

The ability to share your work with a more technical user within Studio is a key feature of Canvas, given the key distinction between ML personas’ workflows. Note the strong focus here on collaboration between cross-functional teams with differing technical abilities.

1. Choose Share to share the model.

2. Choose which model version to share.
3. Enter the Studio user to share the model with.
4. Add an optional note.
5. Choose Share.

Conclusion

In this post, we showed how with just a few clicks in Amazon SageMaker Canvas you can prepare and import your data from Snowflake, join your datasets, analyze estimated accuracy, verify which columns are impactful, train the best performing model, and generate new individual or batch predictions. We’re excited to hear your feedback and help you solve even more business problems with ML. To build your own models, see Getting started with using Amazon SageMaker Canvas.

About the Authors

Nick McCarthy is a Machine Learning Engineer in the AWS Professional Services team. He has worked with AWS clients across various industries including healthcare, finance, sports, telecoms and energy to accelerate their business outcomes through the use of AI/ML. Working with the bpx data science team, Nick recently finished building bpx’s Machine Learning platform on Amazon SageMaker.

Thatcher Thornberry is a Machine Learning Engineer at bpx Energy. He supports bpx’s data scientists by developing and maintaining the company’s core Data Science platform in Amazon SageMaker. In his free time he loves to hack on personal coding projects and spend time outdoors with his wife.

Read More

Today we are excited to announce that Together Computer’s GPT-NeoXT-Chat-Base-20B language foundation model is available for customers using Amazon SageMaker JumpStart. GPT-NeoXT-Chat-Base-20B is an open-source model to build conversational bots. You can easily try out this model and use it with JumpStart. JumpStart is the machine learning (ML) hub of Amazon SageMaker that provides access to foundation models in addition to built-in algorithms and end-to-end solution templates to help you quickly get started with ML.

In this post, we walk through how to deploy the GPT-NeoXT-Chat-Base-20B model and invoke the model within an OpenChatKit interactive shell. This demonstration provides an open-source foundation model chatbot for use within your application.

JumpStart models use Deep Java Serving that uses the Deep Java Library (DJL) with deep speed libraries to optimize models and minimize latency for inference. The underlying implementation in JumpStart follows an implementation that is similar to the following notebook. As a JumpStart model hub customer, you get improved performance without having to maintain the model script outside of the SageMaker SDK. JumpStart models also achieve improved security posture with endpoints that enable network isolation.

Foundation models in SageMaker

JumpStart provides access to a range of models from popular model hubs, including Hugging Face, PyTorch Hub, and TensorFlow Hub, which you can use within your ML development workflow in SageMaker. Recent advances in ML have given rise to a new class of models known as foundation models, which are typically trained on billions of parameters and are adaptable to a wide category of use cases, such as text summarization, generating digital art, and language translation. Because these models are expensive to train, customers want to use existing pre-trained foundation models and fine-tune them as needed, rather than train these models themselves. SageMaker provides a curated list of models that you can choose from on the SageMaker console.

You can now find foundation models from different model providers within JumpStart, enabling you to get started with foundation models quickly. You can find foundation models based on different tasks or model providers, and easily review model characteristics and usage terms. You can also try out these models using a test UI widget. When you want to use a foundation model at scale, you can do so easily without leaving SageMaker by using pre-built notebooks from model providers. Because the models are hosted and deployed on AWS, you can rest assured that your data, whether used for evaluating or using the model at scale, is never shared with third parties.

GPT-NeoXT-Chat-Base-20B foundation model

Together Computer developed GPT-NeoXT-Chat-Base-20B, a 20-billion-parameter language model, fine-tuned from ElutherAI’s GPT-NeoX model with over 40 million instructions, focusing on dialog-style interactions. Additionally, the model is tuned on several tasks, such as question answering, classification, extraction, and summarization. The model is based on the OIG-43M dataset that was created in collaboration with LAION and Ontocord.

In addition to the aforementioned fine-tuning, GPT-NeoXT-Chat-Base-20B-v0.16 has also undergone further fine-tuning via a small amount of feedback data. This allows the model to better adapt to human preferences in the conversations. GPT-NeoXT-Chat-Base-20B is designed for use in chatbot applications and may not perform well for other use cases outside of its intended scope. Together, Ontocord and LAION collaborated to release OpenChatKit, an open-source alternative to ChatGPT with a comparable set of capabilities. OpenChatKit was launched under an Apache-2.0 license, granting complete access to the source code, model weights, and training datasets. There are several tasks that OpenChatKit excels at out of the box. This includes summarization tasks, extraction tasks that allow extracting structured information from unstructured documents, and classification tasks to classify a sentence or paragraph into different categories.

Let’s explore how we can use the GPT-NeoXT-Chat-Base-20B model in JumpStart.

Solution overview

You can find the code showing the deployment of GPT-NeoXT-Chat-Base-20B on SageMaker and an example of how to use the deployed model in a conversational manner using the command shell in the following GitHub notebook.

In the following sections, we expand each step in detail to deploy the model and then use it to solve different tasks:

1. Set up prerequisites.
2. Select a pre-trained model.
3. Retrieve artifacts and deploy an endpoint.
4. Query the endpoint and parse a response.
5. Use an OpenChatKit shell to interact with your deployed endpoint.

Set up prerequisites

This notebook was tested on an ml.t3.medium instance in Amazon SageMaker Studio with the Python 3 (Data Science) kernel and in a SageMaker notebook instance with the conda_python3 kernel.

Before you run the notebook, use the following command to complete some initial steps required for setup:

%pip install --upgrade sagemaker –quiet

Select a pre-trained model

We set up a SageMaker session like usual using Boto3 and then select the model ID that we want to deploy:

model_id, model_version = "huggingface-textgeneration2-gpt-neoxt-chat-base-20b-fp16", "*"

Retrieve artifacts and deploy an endpoint

With SageMaker, we can perform inference on the pre-trained model, even without fine-tuning it first on a new dataset. We start by retrieving the instance_type, image_uri, and model_uri for the pre-trained model. To host the pre-trained model, we create an instance of sagemaker.model.Model and deploy it. The following code uses ml.g5.24xlarge for the inference endpoint. The deploy method may take a few minutes.

endpoint_name = name_from_base(f"jumpstart-example-{model_id}")

# Retrieve the inference instance type for the specified model.
instance_type = instance_types.retrieve_default(
    model_id=model_id, model_version=model_version, scope="inference"
)

# Retrieve the inference docker container uri.
image_uri = image_uris.retrieve(
    region=None,
    framework=None,
    image_scope="inference",
    model_id=model_id,
    model_version=model_version,
    instance_type=instance_type,
)

# Retrieve the model uri.
model_uri = model_uris.retrieve(
    model_id=model_id, model_version=model_version, model_scope="inference"
)

# Create the SageMaker model instance. The inference script is prepacked with the model artifact.
model = Model(
    image_uri=image_uri,
    model_data=model_uri,
    role=aws_role,
    predictor_cls=Predictor,
    name=endpoint_name,
)

# Set the serializer/deserializer used to run inference through the sagemaker API.
serializer = JSONSerializer()
deserializer = JSONDeserializer()

# Deploy the Model.
predictor = model.deploy(
    initial_instance_count=1,
    instance_type=instance_type,
    predictor_cls=Predictor,
    endpoint_name=endpoint_name,
    serializer=serializer,
    deserializer=deserializer
)

Query the endpoint and parse the response

Next, we show you an example of how to invoke an endpoint with a subset of the hyperparameters:

payload = {
    "text_inputs": "<human>: Tell me the steps to make a pizzan<bot>:",
    "max_length": 500,
    "max_time": 50,
    "top_k": 50,
    "top_p": 0.95,
    "do_sample": True,
    "stopping_criteria": ["<human>"],
}
response = predictor.predict(payload)
print(response[0][0]["generated_text"])

The following is the response that we get:

<human>: Tell me the steps to make a pizza
<bot>: 1. Choose your desired crust, such as thin-crust or deep-dish. 
2. Preheat the oven to the desired temperature. 
3. Spread sauce, such as tomato or garlic, over the crust. 
4. Add your desired topping, such as pepperoni, mushrooms, or olives. 
5. Add your favorite cheese, such as mozzarella, Parmesan, or Asiago. 
6. Bake the pizza according to the recipe instructions. 
7. Allow the pizza to cool slightly before slicing and serving.
<human>:

Here, we have provided the payload argument "stopping_criteria": ["<human>"], which has resulted in the model response ending with the generation of the word sequence <human>. The JumpStart model script will accept any list of strings as desired stop words, convert this list to a valid stopping_criteria keyword argument to the transformers generate API, and stop text generation when the output sequence contains any specified stop words. This is useful for two reasons: first, inference time is reduced because the endpoint doesn’t continue to generate undesired text beyond the stop words, and second, this prevents the OpenChatKit model from hallucinating additional human and bot responses until other stop criteria are met.

Use an OpenChatKit shell to interact with your deployed endpoint

OpenChatKit provides a command line shell to interact with the chatbot. In this step, you create a version of this shell that can interact with your deployed endpoint. We provide a bare-bones simplification of the inference scripts in this OpenChatKit repository that can interact with our deployed SageMaker endpoint.

There are two main components to this:

• A shell interpreter (JumpStartOpenChatKitShell) that allows for iterative inference invocations of the model endpoint
• A conversation object (Conversation) that stores previous human/chatbot interactions locally within the interactive shell and appropriately formats past conversations for future inference context

The Conversation object is imported as is from the OpenChatKit repository. The following code creates a custom shell interpreter that can interact with your endpoint. This is a simplified version of the OpenChatKit implementation. We encourage you to explore the OpenChatKit repository to see how you can use more in-depth features, such as token streaming, moderation models, and retrieval augmented generation, within this context. The context of this notebook focuses on demonstrating a minimal viable chatbot with a JumpStart endpoint; you can add complexity as needed from here.

A short demo to showcase the JumpStartOpenChatKitShell is shown in the following video.

The following snippet shows how the code works:

class JumpStartOpenChatKitShell(cmd.Cmd):
    intro = (
        "Welcome to the OpenChatKit chatbot shell, modified to use a SageMaker JumpStart endpoint! Type /help or /? to "
        "list commands. For example, type /quit to exit shell.n"
    )
    prompt = ">>> "
    human_id = "<human>"
    bot_id = "<bot>"
    
    def __init__(self, predictor: Predictor, cmd_queue: Optional[List[str]] = None, **kwargs):
        super().__init__()
        self.predictor = predictor
        self.payload_kwargs = kwargs
        self.payload_kwargs["stopping_criteria"] = [self.human_id]
        if cmd_queue is not None:
            self.cmdqueue = cmd_queue

    def preloop(self):
        self.conversation = Conversation(self.human_id, self.bot_id)

    def precmd(self, line):
        command = line[1:] if line.startswith('/') else 'say ' + line
        return command

    def do_say(self, arg):
        self.conversation.push_human_turn(arg)
        prompt = self.conversation.get_raw_prompt()
        payload = {"text_inputs": prompt, **self.payload_kwargs}
        response = self.predictor.predict(payload)
        output = response[0][0]["generated_text"][len(prompt):]
        self.conversation.push_model_response(output)
        print(self.conversation.get_last_turn())

    def do_reset(self, arg):
        self.conversation = Conversation(self.human_id, self.bot_id)

    def do_hyperparameters(self, arg):
        print(f"Hyperparameters: {self.payload_kwargs}n")

    def do_quit(self, arg):
        return True

You can now launch this shell as a command loop. This will repeatedly issue a prompt, accept input, parse the input command, and dispatch actions. Because the resulting shell may be utilized in an infinite loop, this notebook provides a default command queue (cmdqueue) as a queued list of input lines. Because the last input is the command /quit, the shell will exit upon exhaustion of the queue. To dynamically interact with this chatbot, remove the cmdqueue.

cmd_queue = [
    "Hello!",
]
JumpStartOpenChatKitShell(
    endpoint_name=endpoint_name,
    cmd_queue=cmd_queue,
    max_new_tokens=128,
    do_sample=True,
    temperature=0.6,
    top_k=40,
).cmdloop()

Example 1: Conversation context is retained

The following prompt shows that the chatbot is able to retain the context of the conversation to answer follow-up questions:

Welcome to the OpenChatKit chatbot shell, modified to use a SageMaker JumpStart endpoint! Type /help or /? to list commands. For example, type /quit to exit shell.

<<<  Hello! How may I help you today? 

>>>  What is the capital of US?

<<<  The capital of US is Washington, D.C.

>>>  How far it is from PA ?

<<<  It is approximately 1100 miles.

Example 2: Classification of sentiments

In the following example, the chatbot performed a classification task by identifying the sentiments of the sentence. As you can see, the chatbot was able to classify positive and negative sentiments successfully.

Welcome to the OpenChatKit chatbot shell, modified to use a SageMaker JumpStart endpoint! Type /help or /? to list commands. For example, type /quit to exit shell.

<<<  Hello! How may I help you today?

>>>  What is the sentiment of this sentence "The weather is good and I am going to play outside, it is sunny and warm"

<<<  POSITIVE

>>>  What is the sentiment of this sentence " The news this morning was tragic and it created lot of fear and concerns in city"

<<<  NEGATIVE

Example 3: Summarization tasks

Next, we tried summarization tasks with the chatbot shell. The following example shows how the long text about Amazon Comprehend was summarized to one sentence and the chatbot was able to answer follow-up questions on the text:

Welcome to the OpenChatKit chatbot shell, modified to use a SageMaker JumpStart endpoint! Type /help or /? to list commands. For example, type /quit to exit shell.

<<<  Hello! How may I help you today?

>>>  Write a short summary for this text: Amazon Comprehend uses natural language processing (NLP) to extract insights about the content of documents. It develops insights by recognizing the entities, key phrases, language, sentiments, and other common elements in a document. Use Amazon Comprehend to create new products based on understanding the structure of documents. For example, using Amazon Comprehend you can search social networking feeds for mentions of products or scan an entire document repository for key phrases. nYou can access Amazon Comprehend document analysis capabilities using the Amazon Comprehend console or using the Amazon Comprehend APIs. You can run real-time analysis for small workloads or you can start asynchronous analysis jobs for large document sets. You can use the pre-trained models that Amazon Comprehend provides, or you can train your own custom models for classification and entity recognition. nAll of the Amazon Comprehend features accept UTF-8 text documents as the input. In addition, custom classification and custom entity recognition accept image files, PDF files, and Word files as input. nAmazon Comprehend can examine and analyze documents in a variety of languages, depending on the specific feature. For more information, see Languages supported in Amazon Comprehend. Amazon Comprehend's Dominant language capability can examine documents and determine the dominant language for a far wider selection of languages.

<<<  Amazon Comprehend is a natural language processing (NLP) service that uses deep learning and other advanced AI techniques to extract insights from unstructured text.

>>>  What kind of files does custom entity recognition accept as inputs?

<<<  Image files, PDF files, and Word files

Example 4: Extract structured information from unstructured text

In the following example, we used the chatbot to create a markdown table with headers, rows, and columns to create a project plan using the information that is provided in free-form language:

Welcome to the OpenChatKit chatbot shell, modified to use a SageMaker JumpStart endpoint! Type /help or /? to list commands. For example, type /quit to exit shell.

<<<  Hello! How may I help you today?

>>>  Generate a table summarizing the options outlined in this email.   Team, we need to plan a project.   The first task is for creating a web app and will take 3 developers, 2 testers with duration of 3 weeks. This is priority 1 The second task is for refactoring a web app and will take 2 developers, 5 testers with duration of 4 weeks. This is priority 2  A markdown table with 2 rows and six columns: (1) Task ID , (2) Task Description, (3) Developers, (4) Testers, (5) Duration, (6) Priority

<<<  | Task ID | Task Description | Developers | Testers | Duration | Priority |
| --------- | --------- | --------- | --------- | --------- | --------- |
| 1 | Create a web app | 3 | 2 | 3 weeks | 1 |
| 2 | Refactor a web app | 2 | 5 | 4 weeks | 2 |

Example 5: Commands as input to chatbot

We can also provide input as commands like /hyperparameters to see hyperparameters values and /quit to quit the command shell:

>>>  /hyperparameters

<<<  Hyperparameters: {'max_new_tokens': 128, 'do_sample': True, 'temperature': 0.6, 'top_k': 40, 'stopping_criteria': ['<human>']}

>>>  /quit

These examples showcased just some of the tasks that OpenChatKit excels at. We encourage you to try various prompts and see what works best for your use case.

Clean up

After you have tested the endpoint, make sure you delete the SageMaker inference endpoint and the model to avoid incurring charges.

Conclusion

In this post, we showed you how to test and use the GPT-NeoXT-Chat-Base-20B model using SageMaker and build interesting chatbot applications. Try out the foundation model in SageMaker today and let us know your feedback!

This guidance is for informational purposes only. You should still perform your own independent assessment, and take measures to ensure that you comply with your own specific quality control practices and standards, and the local rules, laws, regulations, licenses and terms of use that apply to you, your content, and the third-party model referenced in this guidance. AWS has no control or authority over the third-party model referenced in this guidance, and does not make any representations or warranties that the third-party model is secure, virus-free, operational, or compatible with your production environment and standards. AWS does not make any representations, warranties or guarantees that any information in this guidance will result in a particular outcome or result.

About the authors

Rachna Chadha is a Principal Solutions Architect AI/ML in Strategic Accounts at AWS. Rachna is an optimist who believes that the ethical and responsible use of AI can improve society in the future and bring economic and social prosperity. In her spare time, Rachna likes spending time with her family, hiking, and listening to music.

Dr. Kyle Ulrich is an Applied Scientist with the Amazon SageMaker built-in algorithms team. His research interests include scalable machine learning algorithms, computer vision, time series, Bayesian non-parametrics, and Gaussian processes. His PhD is from Duke University and he has published papers in NeurIPS, Cell, and Neuron.

Dr. Ashish Khetan is a Senior Applied Scientist with Amazon SageMaker built-in algorithms and helps develop machine learning algorithms. He got his PhD from University of Illinois Urbana-Champaign. He is an active researcher in machine learning and statistical inference, and has published many papers in NeurIPS, ICML, ICLR, JMLR, ACL, and EMNLP conferences.

Read More

This is a guest post co-authored by Nafi Ahmet Turgut, Mutlu Polatcan, Pınar Baki, Mehmet İkbal Özmen, Hasan Burak Yel, and Hamza Akyıldız from Getir.

Getir is the pioneer of ultrafast grocery delivery. The tech company has revolutionized last-mile delivery with its “groceries in minutes” delivery proposition. Getir was founded in 2015 and operates in Turkey, the UK, the Netherlands, Germany, France, Spain, Italy, Portugal, and the United States. Today, Getir is a conglomerate incorporating nine verticals under the same brand.

Predicting future demand is one of the most important insights for Getir and one of the biggest challenges we face. Getir relies heavily on accurate demand forecasts at a SKU level when making business decisions in a wide range of areas, including marketing, production, inventory, and finance. Accurate forecasts are necessary for supporting inventory holding and replenishment decisions. Having a clear and reliable picture of predicted demand for the next day or week allows us to adjust our strategy and increase our ability to meet sales and revenue goals.

Getir used Amazon Forecast, a fully managed service that uses machine learning (ML) algorithms to deliver highly accurate time series forecasts, to increase revenue by four percent and reduce waste cost by 50 percent. In this post, we describe how we used Forecast to achieve these benefits. We outline how we built an automated demand forecasting pipeline using Forecast and orchestrated by AWS Step Functions to predict daily demand for SKUs. This solution led to highly accurate forecasting for over 10,000 SKUs across all countries where we operate, and contributed significantly to our ability to develop high scalable internal supply chain processes.

Forecast automates much of the time-series forecasting process, enabling you to focus on preparing your datasets and interpreting your predictions.

Step Functions is a fully managed service that makes it easier to coordinate the components of distributed applications and microservices using visual workflows. Building applications from individual components that each perform a discrete function helps you scale more easily and change applications more quickly. Step Functions automatically triggers and tracks each step and retries when there are errors, so your application executes in order and as expected.

Solution overview

Six people from Getir’s data science team and infrastructure team worked together on this project. The project was completed in 3 months and deployed to production after 2 months of testing.

The following diagram shows the solution’s architecture.

The model pipeline is executed separately for each country. The architecture includes four Airflow cron jobs running on a defined schedule. The pipeline starts with feature creation which first creates the features and loads them to Amazon Redshift. Next, a feature processing job prepares daily features stored in Amazon Redshift and unloads the time series data to Amazon Simple Storage Service (Amazon S3). A second Airflow job is responsible for triggering the Forecast pipeline via Amazon EventBridge. The pipeline consists of Amazon Lambda functions, which create predictors and forecasts based on parameters stored in Amazon S3. Forecast reads data from Amazon S3, trains the model with hyperparameter optimization (HPO) to optimize model performance, and produces future predictions for product sales. Then the Step Functions “WaitInProgress” pipeline is triggered for each country, which enables parallel execution of a pipeline for each country.

Algorithm Selection

Amazon Forecast has six built-in algorithms (ARIMA, ETS, NPTS, Prophet, DeepAR+, CNN-QR), which are clustered into two groups: statististical and deep/neural network. Among those algorithms, deep/neural networks are more suitable for e-commerce forecasting problems as they accept item metadata features, forward-looking features for campaign and marketing activities, and – most importantly – related time series features. Deep/neural network algorithms also perform very well on sparse data set and in cold-start (new item introduction) scenarios.

Overall, in our experimentations, we observed that deep/neural network models performed significantly better than the statistical models. We therefore focused our deep-dive testing on DeepAR+ and CNN-QR

One of the most important benefits of Amazon Forecast is scalability and accurate results for many product and country combinations. In our testing both DeepAR+ and CNN-QR algorithms brought success in capturing trends and seasonality, allowing us to obtain efficient results in products whose demand changes very frequently.

Deep AutoRegressive Plus (DeepAR+) is a supervised univariate forecasting algorithm based on recurrent neural networks (RNNs) created by Amazon Research. Its main advantages are that it is easily scalable, able to incorporate relevant co-variates into the data (such as related data and metadata), and able to forecast cold-start items. Instead of fitting separate models for each time series, it creates a global model from related time series to handle widely-varying scales through rescaling and velocity-based sampling. The RNN architecture incorporates binomial likelihood to produce probabilistic forecasting and is advocated to outperform traditional single-item forecasting methods (like Prophet) by the authors of DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks.

We ultimately selected the Amazon CNN-QR (Convolutional Neural Network – Quantile Regression) algorithm for our forecasting due to its high performance in the backtest process. CNN-QR is a proprietary ML algorithm developed by Amazon for forecasting scalar (one-dimensional) time series using causal Convolutional Neural Networks (CNNs).

As previously mentioned, CNN-QR can employ related time series and metadata about the items being forecasted. Metadata must include an entry for all unique items in the target time series, which in our case are the products whose demand we are forecasting. To improve accuracy, we used category and subcategory metadata, which helped the model understand the relationship between certain products, including complementary and substitutes. For example, for beverages, we provide an additional flag for snacks since the two categories are complementary to each other.

One significant advantage of CNN-QR is its ability to forecast without future related time series, which is important when you can’t provide related features for the forecast window. This capability, along with its forecast accuracy, meant that CNN-QR produced the best results with our data and use case.

Forecast Output

Forecasts created through the system are written to separate S3 buckets after they are received on a country basis. Then, forecasts are written to Amazon Redshift based on SKU and country with daily jobs. We then carry out daily product stock planning based on our forecasts.

On an ongoing basis, we calculate mean absolute percentage error (MAPE) ratios with product-based data, and optimize model and feature ingestion processes.

Conclusion

In this post, we walked through an automated demand forecasting pipeline we built using Amazon Forecast and AWS Step Functions.

With Amazon Forecast we improved our country-specific MAPE by 10 percent. This has driven a four percent revenue increase, and decreased our waste costs by 50 percent. In addition, we achieved an 80 percent improvement in our training times in daily forecasts in terms of scalability. We are able to forecast over 10,000 SKUs daily in all the countries we serve.

For more information about how to get started building your own pipelines with Forecast, see Amazon Forecast resources. You can also visit AWS Step Functions to get more information about how to build automated processes and orchestrate and create ML pipelines. Happy forecasting, and start improving your business today!

About the Authors

Nafi Ahmet Turgut finished his Master’s Degree in Electrical & Electronics Engineering and worked as graduate research scientist. His focus was building machine learning algorithms to simulate nervous network anomalies. He joined Getir in 2019 and currently works as a Senior Data Science & Analytics Manager. His team is responsible for designing, implementing, and maintaining end-to-end machine learning algorithms and data-driven solutions for Getir.

Mutlu Polatcan is a Staff Data Engineer at Getir, specializing in designing and building cloud-native data platforms. He loves combining open-source projects with cloud services.

Pınar Baki received her Master’s Degree from the Computer Engineering Department at Boğaziçi University. She worked as a data scientist at Arcelik, focusing on spare-part recommendation models and age, gender, emotion analysis from speech data. She then joined Getir in 2022 as a Senior Data Scientist working on forecasting and search engine projects.

Mehmet İkbal Özmen received his Master’s Degree in Economics and worked as Graduate Research Assistant. His research area was mainly economic time series models, Markov simulations, and recession forecasting. He then joined Getir in 2019 and currently works as Data Science & Analytics Manager. His team is responsible for optimization and forecast algorithms to solve the complex problems experienced by the operation and supply chain businesses.

Hasan Burak Yel received his Bachelor’s Degree in Electrical & Electronics Engineering at Boğaziçi University. He worked at Turkcell, mainly focused on time series forecasting, data visualization, and network automation. He joined Getir in 2021 and currently works as a Lead Data Scientist with the responsibility of Search & Recommendation Engine and Customer Behavior Models.

Hamza Akyıldız received his Bachelor’s Degree of Mathematics and Computer Engineering at Boğaziçi University. He focuses on optimizing machine learning algorithms with their mathematical background. He joined Getir in 2021, and has been working as a Data Scientist. He has worked on Personalization and Supply Chain related projects.

Esra Kayabalı is a Senior Solutions Architect at AWS, specializing in the analytics domain including data warehousing, data lakes, big data analytics, batch and real-time data streaming and data integration. She has 12 years of software development and architecture experience. She is passionate about learning and teaching cloud technologies.

Read More

Amazon Textract is a machine learning (ML) service that automatically extracts text, handwriting, and data from any document or image. To make it simpler to evaluate the capabilities of Amazon Textract, we have launched a new Bulk Document Uploader feature on the Amazon Textract console that enables you to quickly process your own set of documents without writing any code.

In this post, we walk through when and how to use the Amazon Textract Bulk Document Uploader to evaluate how Amazon Textract performs on your documents.

Overview of solution

The Bulk Document Uploader should be used for quick evaluation of Amazon Textract for predetermined use cases. By uploading multiple documents simultaneously through an intuitive UI, you can easily gauge how well Amazon Textract performs on your documents.

You can upload and process up to 150 documents at once. Unlike the existing Amazon Textract console demos, which impose artificial limits on the number of documents, document size, and maximum allowed number of pages, the Bulk Document Uploader supports processing up to 150 documents per request and has the same document size and page limits as the Amazon Textract APIs. This makes it more efficient for you to evaluate a larger set of documents.

The Bulk Document Uploader outputs a standard Amazon Textract JSON response and CSV file. The results are provided in JSON format for easy programmatic analysis. Additionally, a human-readable CSV file with confidence scores is provided for simple comparison and evaluation of the extracted information.

When using this feature, keep in mind the following:

• The Bulk Document Uploader processes documents via asynchronous operations. You can track the status of the processing on the Amazon Textract console. Only DetectDocumentText (OCR), AnalyzeDocument (Tables, Queries, Forms, and Signatures), and AnalyzeExpense APIs are currently supported.
• The Bulk Document Uploader provides JSON results of the API operations and formatted CSV reports. You may need to rely on external tools for visualization of the data, such as displaying bounding box highlights on the document using the JSON results.
• Using this feature to process documents incurs the same charges as regular Amazon Textract usage (depending on which feature is used), and is subject to the TPS (transactions per second) limits for APIs that are set for the account and Region. For more information on pricing, refer to Amazon Textract pricing. To learn more about Amazon Textract limits, refer to Quotas in Amazon Textract.
• Accepted file formats for bulk uploader are JPEG, PNG, TIF, and PDF. JPEG 2000-encoded images within PDFs are also supported. JPEG and PNG files have a 10 MB size limit, whereas PDF and TIF files have a 500 MB size limit. Multi-page PDF and TIF files have a 3,000 page limit.

Use the Bulk Document Uploader

The Bulk Document Uploader is intended to help you quickly evaluate how Amazon Textract performs on a set of your own documents, without needing to write any code. You can use the Bulk Document Uploader to process as many as 150 documents instead of uploading and processing documents individually. You can bulk upload documents directly from your computer or import documents from an existing Amazon Simple Storage Service (Amazon S3) bucket.

The Bulk Document Uploader provides results that you can download later for offline review. Each downloadable ZIP file contains the Amazon Textract API response in JSON file format and a human-readable CSV file of the output containing the extracted data and confidence scores. The output results are available for download for 7 days after processing. After 14 days, documents are cleared from the Submitted documents section. To use the Bulk Document Uploader, complete the following steps:

1. On the Amazon Textract console, under Demos in the navigation pane, choose Bulk Document Uploader.
2. Choose Upload documents.
   
3. Specify the source of your documents.

You have two options to upload documents:

• Import documents from S3 bucket – If you’re using an S3 bucket for your documents, provide the bucket URL and (optionally) the prefix where your documents reside, in s3://your-bucket/prefix/ format. Alternatively, choose Browse S3 to browse and select the desired location of your documents. If the Amazon S3 location you specified contains more than 150 documents, then only the first 150 documents will be sent to Amazon Textract for processing.
  
• Upload documents from your computer – If you’re uploading documents from your computer, you can upload up to 50 documents at a time by choosing Upload Documents. To upload additional documents (up to the maximum of 150), choose Add documents after your initial documents are uploaded.
  

In this case, your documents are first uploaded to an S3 bucket in your account that is created on your behalf, therefore it’s important to ensure that you have permissions to access and upload documents to Amazon S3. This is a one-time action, and the same bucket will be used for all subsequent uploads from your computer. If you want to upload and process the same set of documents, you can use the path to this S3 bucket using the Import documents from S3 bucket option. The S3 bucket created on your behalf will be visible after the bucket gets created.

4. Next, specify the Amazon Textract feature you want to use to process your documents.

You may select only one feature at a time to process your documents. If you need to evaluate additional features, you must create a separate request by selecting the desired feature and uploading the documents again. If the AnalyzeDocument – Queries feature is selected, you need to provide the queries you want to test against your documents. You can specify up to 30 queries at a time. If the uploaded documents contain multi-page (PDF or TIF) files, queries are only applied to the first page of each document. Refer to Best Practices for Queries to learn about how to construct queries.

5. Choose Start processing to submit the documents to Amazon Textract for processing.

You can track the document status and download the output results of processed documents in the Submitted documents section. This section updates periodically, and you can manually refresh it to see if the processing is complete. Each document is processed individually, so you can either select the document with Ready to download status or wait for all documents to complete processing to download the results. The output of the processed documents will remain available for up to 7 days for download, after which they will expire. Expired documents will be cleared from the Submitted documents section after 7 additional days (14 days from the processed date). We suggest downloading and preserving the outputs within the 7-day period.

Conclusion

In this post, we announced the new Amazon Textract Bulk Document Uploader feature, which allows you to quickly process a large number of documents for evaluation purposes. You can use this feature to evaluate Amazon Textract for a predetermined use case with your documents. To learn more about how you can use Amazon Textract in your intelligent document processing workload, visit Amazon Textract features and Getting started with Amazon Textract.

About the Authors

Shashwat Sapre is a Senior Technical Product Manager with the Amazon Textract team. He is focused on building machine learning-based services for AWS customers. In his spare time, he likes reading about new technologies, traveling and exploring different cuisines.

Anjan Biswas is a Senior AI Services Solutions Architect with a focus on AI/ML and Data Analytics. Anjan is part of the world-wide AI services team and works with customers to help them understand and develop solutions to business problems with AI and ML. Anjan has over 14 years of experience working with global supply chain, manufacturing, and retail organizations, and is actively helping customers get started and scale on AWS AI services.

Read More