Skip to content

README-AKS.md

Latest commit

 

History

History
389 lines (260 loc) · 26.4 KB

README-AKS.md

File metadata and controls

389 lines (260 loc) · 26.4 KB

Microservice based architecture deployed on Azure Kubernetes Services

Microservice RAG Architecture

TL;DR

Open the project:

Open in GitHub Codespaces Open in VS Code Dev Containers

Open the terminal and run:

cd deploy/aks
azd auth login
azd up

For detailed instructions, see Getting Started below.

Table of contents

Getting Started

Run in GitHub Codespaces or VS Code Dev Containers

You can run this repo virtually by using GitHub Codespaces or VS Code Dev Containers. Click on one of the buttons below to open this repo in one of those options.

Open in GitHub Codespaces Open in VS Code Dev Containers

All prerequisites are already installed in the container. You can skip to the Starting from scratch section.

Prerequisites

[!WARNING] Your Azure Account must have Microsoft.Authorization/roleAssignments/write permissions, such as User Access Administrator or Owner.

Starting from scratch

You can clone this repo and change directory to the root of the repo. Or you can run azd init -t Azure-Samples/azure-search-openai-demo-java.

Once you have the project available locally, run the following commands if you don't have any pre-existing Azure services and want to start from a fresh deployment.

Important

All the commands below must be run from the deploy/aks folder

  1. Run

    azd auth login

  2. Run

    azd up
    • This will provision Azure resources and deploy this sample to those resources, including building the search index based on the files found in the ./data folder.
    • For the target location check up-to-date list of regions and models availables here

  3. After the application has been successfully deployed you will see a backend app load balancer IP printed to the console. Click that URL to interact with the application in your browser.

It will look like the following:

'Output from running azd up'

  1. When you enable login and ACL, the https url will be printed in the console output, and you can use that to access the application. For more information on enabling login and ACL, see here.

'Output from running azd up with login and ACL enabled'

NOTE: It may take a minute for the application to be fully deployed.

Deploying with existing Azure resources

If you already have existing Azure resources, you can re-use those by setting azd environment values.

Existing resource group

  1. Run azd env set AZURE_RESOURCE_GROUP {Name of existing resource group}
  2. Run azd env set AZURE_LOCATION {Location of existing resource group (i.e eastus2)}

Existing OpenAI resource

  1. Run azd env set AZURE_OPENAI_SERVICE {Name of existing OpenAI service}
  2. Run azd env set AZURE_OPENAI_RESOURCE_GROUP {Name of existing resource group that OpenAI service is provisioned to}
  3. Run azd env set AZURE_OPENAI_SERVICE_LOCATION {Location of existing resource (i.e eastus2)}. Only needed if your OpenAI resource is in a different location than the one you'll pick for the azd up step.
  4. Run azd env set AZURE_OPENAI_CHATGPT_DEPLOYMENT {Name of existing ChatGPT deployment}. Only needed if your ChatGPT deployment is not the default 'chat'.
  5. Run azd env set AZURE_OPENAI_EMB_DEPLOYMENT {Name of existing GPT embedding deployment}. Only needed if your embeddings deployment is not the default 'embedding'.

Existing Azure AI Search resource

  1. Run azd env set AZURE_SEARCH_SERVICE {Name of existing Azure AI Search service}
  2. Run azd env set AZURE_SEARCH_SERVICE_RESOURCE_GROUP {Name of existing resource group with ACS service}
  3. If that resource group is in a different location than the one you'll pick for the azd up step, then run azd env set AZURE_SEARCH_SERVICE_LOCATION {Location of existing service}
  4. If the search service's SKU is not standard, then run azd env set AZURE_SEARCH_SERVICE_SKU {Name of SKU}. The free tier won't work as it doesn't support managed identity. (See other possible values)

Other existing Azure resources

You can also use existing Form Recognizer and Storage Accounts. See ./infra/main.parameters.json for list of environment variables to pass to azd env set to configure those existing resources.

Provision remaining resources

Now you can run azd up, following the steps in Deploying from scratch above. That will both provision resources and deploy the code.

Redeploying

If you've only changed the backend/frontend code in the app folder, then you don't need to re-provision the Azure resources. You can just run:

azd deploy

If you've changed the infrastructure files (infra folder or azure.yaml), then you'll need to re-provision the Azure resources. You can do that by running:

azd up

Examples of an azd deployment changing the default chatgpt deployment model

azd auth login
azd env set AZURE_OPENAI_CHATGPT_MODEL "gpt-4" # Change the chatgpt model to gpt-4
azd up

NOTE: This sample has been tested with gpt-4o-mini.Using other models or different versions might result in unexpected behavior.

Examples of an azd deployment reusing an existing Azure OpenAI and Azure AI Search resources

azd auth login
azd init -t Azure-Samples/azure-search-openai-demo-java.

azd env set AZURE_RESOURCE_GROUP "openai-test-resource-group" # Target resource group for the new resources
azd env set AZURE_LOCATION "eastus" # Target region for the new resources

azd env set AZURE_OPENAI_SERVICE "my-openai-test-service" # Name of the OpenAI service
azd env set AZURE_OPENAI_RESOURCE_GROUP "my-openai-test-resource-group" # Resource group where the OpenAI service is deployed
azd env set AZURE_OPENAI_SERVICE_LOCATION "eastus2" # Region of the OpenAI service
azd env set AZURE_OPENAI_CHATGPT_DEPLOYMENT "gpt-35-turbo" # The "Deployment name" of the deployed model, deployed in the Azure OpenAI studio
azd env set AZURE_OPENAI_EMB_DEPLOYMENT "text-embedding-ada-002"  # The "Deployment name" of the deployed model, deployed in the Azure OpenAI studio

azd env set AZURE_SEARCH_SERVICE "my-acs-test-service" # Name of the ACS service
azd env set AZURE_SEARCH_SERVICE_RESOURCE_GROUP "my-acs-test-resource-group" # Resource group where the ACS service is deployed
azd env set AZURE_SEARCH_SERVICE_LOCATION "eastus2" # Region of the ACS service

azd up

UI Navigation

Once in the web app:

  • Try different topics in chat or Q&A context. For chat, try follow-up questions, clarifications, ask to simplify or elaborate on answer, etc.
  • Explore citations and sources
  • Click on "settings" to try different options, tweak prompts, etc.

Guidance

Enabling Application Insights

Applications Insights is disabled by default. It allows to investigate each request tracing along with the logging of errors.

If you want to disable it set the AZURE_USE_APPLICATION_INSIGHTS variable to false before running azd up

  1. Run azd env set AZURE_USE_APPLICATION_INSIGHTS true
  2. Run azd up

To see the performance data, go to the Application Insights resource in your resource group, click on the "Investigate -> Performance" blade and navigate to any HTTP request to see the timing data. To inspect the performance of chat requests, use the "Drill into Samples" button to see end-to-end traces of all the API calls made for any chat request. Under "Trace & Events" panel you can review custom Java informational logs to better understand content of OpenAI requests and responses.

Tracing screenshot

To see any exceptions and server errors, navigate to the "Investigate -> Failures" blade and use the filtering tools to locate a specific exception. You can see Java stack traces on the right-hand side.

Enabling login and search filtering

See here for detailed guidance.

Enabling client-side chat history

This feature allows users to view the chat history of their conversation, stored in the browser using IndexedDB. That means the chat history will be available only on the device where the chat was initiated. To enable browser-stored chat history, run:

azd env set USE_CHAT_HISTORY_BROWSER true

This is useful especially for unauthenticated users. For authenticated ones see below.

Enabling persistent chat history with Azure Cosmos DB

This feature allows authenticated users to view the chat history of their conversations, stored in the server-side storage using Azure Cosmos DB.This option requires that authentication be enabled. The chat history will be persistent and accessible from any device where the user logs in with the same account. To enable server-stored chat history, run:

azd env set USE_CHAT_HISTORY_COSMOS true

When both the browser-stored and Cosmos DB options are enabled, Cosmos DB will take precedence over browser-stored chat history.

App Continuous Integration

☀️ ☁️ 👷‍♂️ WIP

Productionizing

This sample is designed to be a starting point for your own production application, but you should do a thorough review of the security and performance before deploying to production. Here are some things to consider:

  • OpenAI Capacity: The default TPM (tokens per minute) is set to 60K for gpt and 80k for embeddings. That is equivalent to approximately 60 conversations per minute (assuming 1K per user message/response). You can increase the capacity by changing the chatGptDeploymentCapacity and embeddingDeploymentCapacity parameters in infra/main.bicep to your account's maximum capacity. You can also view the Quotas tab in Azure OpenAI studio to understand how much capacity you have.
  • Azure Storage: The default storage account uses the Standard_LRS SKU. To improve your resiliency, we recommend using Standard_ZRS for production deployments, which you can specify using the sku property under the storage module in infra/main.bicep.
  • Azure AI Search: The default search service uses the Standard SKU with the free semantic search option, which gives you 1000 free queries a month. Assuming your app will experience more than 1000 questions, you should either change semanticSearch to "standard" or disable semantic search entirely in the /app/backend/approaches files. If you see errors about search service capacity being exceeded, you may find it helpful to increase the number of replicas by changing replicaCount in infra/core/search/search-services.bicep or manually scaling it from the Azure Portal.
  • Service Bus: Standard SKU is used. Consider to use Premium SKU to enable redundancy and predictable performance with high throughput.
  • Event Grid: Event Grid basic is used. Consider to use Event Grid Standard tier if the ingestion requests rates are high (> 5MB/s). Only BlobId are sent in the event grid events. The blob content is not sent. Authentication: By default, the deployed app is publicly accessible. We recommend restricting access to authenticated users.
  • Networking: We recommend deploying inside a Virtual Network. If the app is only for internal enterprise use, use a private DNS zone. Also consider using Azure API Management (APIM) for firewalls and other forms of protection. For more details, read Azure OpenAI Landing Zone reference architecture.
  • Loadtesting: We recommend running a loadtest for your expected number of users. You can use Azure Load Test with Apache Jmeter

Cost estimation

Pricing varies per region and usage, so it isn't possible to predict exact costs for your usage. However, you can try the Azure pricing calculator for the resources below.

  • Azure Kubernetes Service. Pricing
  • Azure OpenAI: Standard tier, ChatGPT and Ada models. Pricing per 1K tokens used, and at least 1K tokens are used per question. Pricing
  • Form Recognizer: SO (Standard) tier using pre-built layout. Pricing per document page, sample documents have 261 pages total. Pricing
  • Azure AI Search: Standard tier, 1 replica, free level of semantic search. Pricing per hour.Pricing
  • Azure Blob Storage: Standard tier with ZRS (Zone-redundant storage). Pricing per storage and read operations. Pricing
  • Azure Monitor: Pay-as-you-go tier. Costs based on data ingested. Pricing
  • Azure Event Grid: Basic tier. Pricing per operation. Pricing
  • Azure Service Bus: Standard tier. Pricing per hour and operations. Pricing

To reduce costs, you can switch to free SKUs Form Recognizer by changing the parameters file under the infra folder. There are some limits to consider; for example, the free Form Recognizer resource only analyzes the first 2 pages of each document. You can also reduce costs associated with the Form Recognizer by reducing the number of documents in the data folder, or changing the code to use the Itext document based parser, or by removing the postprovision hook in azure.yaml that runs the indexer java cli.

⚠️ To avoid unnecessary costs, remember to take down your app if it's no longer in use, either by deleting the resource group in the Portal or running azd down --purge.

Note

Note: The PDF documents used in this demo contain information generated using a language model (Azure OpenAI Service). The information contained in these documents is only for demonstration purposes and does not reflect the opinions or beliefs of Microsoft. Microsoft makes no representations or warranties of any kind, express or implied, about the completeness, accuracy, reliability, suitability or availability with respect to the information contained in this document. All rights reserved to Microsoft.

FAQ

Why do we need to break up the PDFs into chunks when Azure AI Search supports searching large documents?

Chunking allows us to limit the amount of information we send to OpenAI due to token limits. By breaking up the content, it allows us to easily find potential chunks of text that we can inject into OpenAI. The method of chunking we use leverages a sliding window of text such that sentences that end one chunk will start the next. This allows us to reduce the chance of losing the context of the text.

Details How can we upload additional PDFs without redeploying everything?

To upload more PDFs, put them in the data/ folder and run ./scripts/prepdocs.sh or ./scripts/prepdocs.ps1. To avoid reuploading existing docs, move them out of the data folder. You could also implement checks to see whats been uploaded before; our code doesn't yet have such checks.

Details How do you use GPT-4 with this sample?

In infra/main.bicep, change chatGptModelName to 'gpt-4' instead of 'gpt-35-turbo'. You may also need to adjust the capacity above that line depending on how much TPM your account is allowed.

Details What is the difference between the Chat and Ask tabs?

The chat tab uses the approach programmed in PlainJavaChatApproach.

  • It uses the ChatGPT API to turn the user question into a good search query.
  • It queries Azure AI Search for search results for that query (optionally using the vector embeddings for that query).
  • It then combines the search results and original user question, and asks ChatGPT API to answer the question based on the sources. It includes the last 4K of message history as well (or however many tokens are allowed by the deployed model).

The ask tab uses the approach programmed in PlainJavaChatApproach.

  • It queries Azure AI Search for search results for the user question (optionally using the vector embeddings for that question).
  • It then combines the search results and user question, and asks ChatGPT API to answer the question based on the sources.

There are also three other /ask approaches which are implemented using Java Semantic Kernel sdk. Development it's still experimental and it will be consolidated as soon as semantic kernel beta version will be released. Below a brief description of the SK integration status:

Details What does the `azd up` command do?

The azd up command comes from the Azure Developer CLI, and takes care of both provisioning the Azure resources and deploying code to the selected Azure hosts.

The azd up command uses the azure.yaml file combined with the infrastructure-as-code .bicep files in the infra/ folder. The azure.yaml file for this project declares several "hooks" for the prepackage step and postprovision steps. The up command first runs the prepackage hook which installs Node dependencies and builds the React.JS-based JavaScript files. It then packages all the code (both frontend and backend) into a zip file which it will deploy later.

Next, it provisions the resources based on main.bicep and main.parameters.json. At that point, since there is no default value for the OpenAI resource location, it asks you to pick a location from a short list of available regions. Then it will send requests to Azure to provision all the required resources. With everything provisioned, it runs the postprovision hook to process the local data and add it to an Azure AI Search index.

Finally, it looks at azure.yaml to determine the Azure host (appservice, in this case) and uploads the zip to Azure App Service. The azd up command is now complete, but it may take another 5-10 minutes for the App Service app to be fully available and working, especially for the initial deploy.

Related commands are azd provision for just provisioning (if infra files change) and azd deploy for just deploying updated app code.

Details How can we view logs from AKS?

You can view logs of each deployment in the Portal using either the Log stream or by using kubectl commands and connecting to the cluster.

Troubleshooting

Here are the most common failure scenarios and solutions:

  1. The subscription (AZURE_SUBSCRIPTION_ID) doesn't have access to the Azure OpenAI Service. Please ensure AZURE_SUBSCRIPTION_ID matches the ID specified in the OpenAI access request process.

  2. You're attempting to create resources in regions not enabled for Azure OpenAI (e.g. East US 2 instead of East US), or where the model you're trying to use isn't enabled. See this matrix of model availability.

  3. You've exceeded a quota, most often number of resources per region. See this article on quotas and limits.

  4. You're getting "same resource name not allowed" conflicts. That's likely because you've run the sample multiple times and deleted the resources you've been creating each time, but are forgetting to purge them. Azure keeps resources for 48 hours unless you purge from soft delete. See this article on purging resources.

  5. You see CERTIFICATE_VERIFY_FAILED when the prepdocs.py script runs. That's typically due to incorrect SSL certificates setup on your machine. Try the suggestions in this StackOverflow answer.

  6. After running ./app/start.ps1 on Windows PowerShell you get The file C:\path\to\azure-search-openai-demo-java\app\start.ps1 is not digitally signed. You cannot run this script on the current system. Try to run Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass and try to re-run ./app/start.ps1

  7. After running ./app/start.ps1 or ./app/start.sh you get "Failed to execute goal org.apache.maven.plugins:maven-compiler-plugin:3.10.1:compile (default-compile) on project myproject: Fatal error compiling: invalid target release: 17". It means you are not using JDK 17 but a previous version. Be sure to set the JAVA_HOME env variable to your Java 17 installation directory and update your PATH env variable to have the Java 17 bin folder as the first occurrence amongst the listed directories. More info here

  8. After running ./app/start.sh on Ubuntu 16.04 or later, the first time you try to create a virtual environment with Python 3.6, Python 3.7, Python 3.8 or Python 3.9, you'll get the following error "The virtual environment was not created successfully because ensurepip is not available". Just follow the hint provided in the error message and run apt-get install python3-venv to install the missing packages. More info here

  9. While running azd up in VS Code Dev Containers you got this error ".. Maven: failed finding mvnw in repository path: exec: /azure-search-openai-demo-java/app/backend/mvnw: permission denied ". Run chmod +x ./azure-search-openai-demo-javaapp/backend/mvnw to fix it and rerun azd up.