Skip to content

Commit

Permalink
Merge pull request #895 from microsoft/cmcclearydocs-update
Browse files Browse the repository at this point in the history
copilot to agent updates
  • Loading branch information
lon-tierney authored Oct 28, 2024
2 parents 4ac11b4 + 1b11ff6 commit 6f72169
Show file tree
Hide file tree
Showing 32 changed files with 114 additions and 114 deletions.
2 changes: 1 addition & 1 deletion CONTRIBUTING.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Contributing to Information Assistant copilot template
# Contributing to Information Assistant agent template

This project welcomes contributions and suggestions. Most contributions require you to agree to a
Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
Expand Down
30 changes: 15 additions & 15 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Information Assistant (IA) copilot template
# Information Assistant (IA) agent template

> [!IMPORTANT]
> As of November 15, 2023, Azure Cognitive Search has been renamed to Azure AI Search. Azure Cognitive Services have also been renamed to Azure AI Services.
Expand Down Expand Up @@ -38,15 +38,15 @@

[![Open in GitHub Codespaces](https://img.shields.io/static/v1?style=for-the-badge&label=GitHub+Codespaces&message=Open&color=brightgreen&logo=github)](https://github.com/codespaces/new?hide_repo_select=true&ref=main&repo=601652366&machine=basicLinux32gb&devcontainer_path=.devcontainer%2Fdevcontainer.json&location=eastus)

Information Assistant (IA) copilot template provides a starting point for organizations to build their own custom generative AI capability to extend the power of Azure OpenAI. It showcases a common scenario using large language models (LLMs) to “chat with your own data” through the [Retrieval Augmented Generation (RAG) pattern](https://learn.microsoft.com/azure/search/retrieval-augmented-generation-overview). This pattern lets you use the reasoning abilities of LLMs to generate responses based on your domain data without fine-tuning the model.
Information Assistant (IA) agent template provides a starting point for organizations to build their own custom generative AI capability to extend the power of Azure OpenAI. It showcases a common scenario using large language models (LLMs) to “chat with your own data” through the [Retrieval Augmented Generation (RAG) pattern](https://learn.microsoft.com/azure/search/retrieval-augmented-generation-overview). This pattern lets you use the reasoning abilities of LLMs to generate responses based on your domain data without fine-tuning the model.

Information Assistant copilot template is an end-to-end solution which is a comprehensive reference sample including documentation, source code, and deployment to allow you to take and extend for your own purposes.
Information Assistant agent template is an end-to-end solution which is a comprehensive reference sample including documentation, source code, and deployment to allow you to take and extend for your own purposes.

This copilot template showcases integration between Azure and OpenAI's LLMs. It leverages Azure AI Search for data retrieval and ChatGPT-style Q&A interactions. Using the RAG design pattern with Azure OpenAI's GPT models, it provides a natural language interaction to discover relevant responses to user queries. Azure AI Search simplifies data ingestion, transformation, indexing, and multilingual translation.
This agent template showcases integration between Azure and OpenAI's LLMs. It leverages Azure AI Search for data retrieval and ChatGPT-style Q&A interactions. Using the RAG design pattern with Azure OpenAI's GPT models, it provides a natural language interaction to discover relevant responses to user queries. Azure AI Search simplifies data ingestion, transformation, indexing, and multilingual translation.

The copilot adapts prompts based on the model type for enhanced performance. Users can customize settings like temperature and persona for personalized AI interactions. It offers features like explainable thought processes, referenceable citations, and direct content for verification.
The agent adapts prompts based on the model type for enhanced performance. Users can customize settings like temperature and persona for personalized AI interactions. It offers features like explainable thought processes, referenceable citations, and direct content for verification.

Please [see this video](https://aka.ms/InfoAssist/video) for use cases that may be achievable with Information Assistant copilot template.
Please [see this video](https://aka.ms/InfoAssist/video) for use cases that may be achievable with Information Assistant agent template.

# Response generation approaches

Expand All @@ -66,7 +66,7 @@ It generates response by using LLM as a reasoning engine. The key strength lies

## Features

The Information Assistant copilot template contains several features, many of which have their own documentation.
The Information Assistant agent template contains several features, many of which have their own documentation.

- Examples of custom Retrieval Augmented Generation (RAG), Prompt Engineering, and Document Pre-Processing
- Azure AI Search Integration to include text search of both text documents and images
Expand Down Expand Up @@ -115,15 +115,15 @@ For a detailed review see our [Features](./docs/features/features.md) page.

## Deployment

Please follow the instructions in [the deployment guide](/docs/deployment/deployment.md) to install the Information Assistant copilot template in your Azure subscription.
Please follow the instructions in [the deployment guide](/docs/deployment/deployment.md) to install the Information Assistant agent template in your Azure subscription.

Once completed, follow the [instructions for using Information Assistant copilot template for the first time](/docs/deployment/using_ia_first_time.md).
Once completed, follow the [instructions for using Information Assistant agent template for the first time](/docs/deployment/using_ia_first_time.md).

You may choose to **[view the deployment and usage click-through guides](https://aka.ms/InfoAssist/deploy)** to see the steps in action. These videos may be useful to help clarify specific steps or actions in the instructions.

## Responsible AI

The Information Assistant (IA) copilot template and Microsoft are committed to the advancement of AI driven by ethical principles that put people first.
The Information Assistant (IA) agent template and Microsoft are committed to the advancement of AI driven by ethical principles that put people first.

### Transparency Note

Expand Down Expand Up @@ -151,7 +151,7 @@ The software may collect information about you and your use of the software and

### About Data Collection

Data collection by the software in this repository is used by Microsoft solely to help justify the efforts of the teams who build and maintain this copilot template for our customers. It is your choice to leave this enabled, or to disable data collection.
Data collection by the software in this repository is used by Microsoft solely to help justify the efforts of the teams who build and maintain this agent template for our customers. It is your choice to leave this enabled, or to disable data collection.

Data collection is implemented by the presence of a tracking GUID in the environment variables at deployment time. The GUID is associated with each Azure resource deployed by the installation scripts. This GUID is used by Microsoft to track the Azure consumption this open source solution generates.

Expand All @@ -177,13 +177,13 @@ docs/deployment/ | Detailed documentation on how to deploy and start using Infor
docs/features/ | Detailed documentation of specific features and development level configuration for Information Assistant.
docs/ | Other supporting documentation that is primarily linked to from the other markdown files.
functions/ | The pipeline of Azure Functions that handle the document extraction and chunking as well as the custom CosmosDB logging.
infra/ | The Terraform scripts that deploy the entire IA copilot template. The overall copilot template is orchestrated via the `main.tf` file but most of the resource deployments are modularized under the **core** folder.
pipelines/ | Azure DevOps pipelines that can be used to enable CI/CD deployments of the copilot template.
infra/ | The Terraform scripts that deploy the entire IA agent template. The overall agent template is orchestrated via the `main.tf` file but most of the resource deployments are modularized under the **core** folder.
pipelines/ | Azure DevOps pipelines that can be used to enable CI/CD deployments of the agent template.
scripts/environments/ | Deployment configuration files. This is where all external configuration values will be set.
scripts/ | Supporting scripts that perform the various deployment tasks such as infrastructure deployment, Azure WebApp and Function deployments, building of the webapp and functions source code, etc. These scripts align to the available commands in the `Makefile`.
tests/ | Functional Test scripts that are used to validate a deployed Information Assistant's document processing pipelines are working as expected.
Makefile | Deployment command definitions and configurations. You can use `make help` to get more details on available commands.
README.md | Starting point for this repo. It covers overviews of the copilot template, Responsible AI, Environment, Deployment, and Usage of the copilot template.
README.md | Starting point for this repo. It covers overviews of the agent template, Responsible AI, Environment, Deployment, and Usage of the agent template.

### References

Expand All @@ -206,7 +206,7 @@ This project may contain trademarks or logos for projects, products, or services

## Microsoft Legal Notice

**Notice**. The Information Assistant copilot template (the "IA") is PROVIDED "AS-IS," "WITH ALL FAULTS," AND "AS AVAILABLE," AND ARE EXCLUDED FROM THE SERVICE LEVEL AGREEMENTS AND LIMITED WARRANTY. The IA may employ lesser or different privacy and security measures than those typically present in Azure Services. Unless otherwise noted, The IA should not be used to process Personal Data or other data that is subject to legal or regulatory compliance requirements. The following terms in the DPA do not apply to the IA: Processing of Personal Data, GDPR, Data Security, and HIPAA Business Associate. We may change or discontinue the IA at any time without notice. The IA (1) is not designed, intended, or made available as legal services, (2) is not intended to substitute for professional legal counsel or judgment, and (3) should not be used in place of consulting with a qualified professional legal professional for your specific needs. Microsoft makes no warranty that the IA is accurate, up-to-date, or complete. You are wholly responsible for ensuring your own compliance with all applicable laws and regulations.
**Notice**. The Information Assistant agent template (the "IA") is PROVIDED "AS-IS," "WITH ALL FAULTS," AND "AS AVAILABLE," AND ARE EXCLUDED FROM THE SERVICE LEVEL AGREEMENTS AND LIMITED WARRANTY. The IA may employ lesser or different privacy and security measures than those typically present in Azure Services. Unless otherwise noted, The IA should not be used to process Personal Data or other data that is subject to legal or regulatory compliance requirements. The following terms in the DPA do not apply to the IA: Processing of Personal Data, GDPR, Data Security, and HIPAA Business Associate. We may change or discontinue the IA at any time without notice. The IA (1) is not designed, intended, or made available as legal services, (2) is not intended to substitute for professional legal counsel or judgment, and (3) should not be used in place of consulting with a qualified professional legal professional for your specific needs. Microsoft makes no warranty that the IA is accurate, up-to-date, or complete. You are wholly responsible for ensuring your own compliance with all applicable laws and regulations.

## Code of Conduct

Expand Down
2 changes: 1 addition & 1 deletion SUPPORT.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ Please provide as much information as possible when filing an issue (please reda

For help and questions about using this project, please use the [Discussion](https://github.com/microsoft/PubSec-Info-Assistant/discussions) forums on our GitHub repo page.

For customer support deploying Information Assistant copilot template, please reach out to your local Microsoft representative or email the [Public Sector Industries & Regulated Products Accelerators Team](mailto:[email protected]).
For customer support deploying Information Assistant agent template, please reach out to your local Microsoft representative or email the [Public Sector Industries & Regulated Products Accelerators Team](mailto:[email protected]).

## Providing feedback

Expand Down
2 changes: 1 addition & 1 deletion app/frontend/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
<meta charset="UTF-8" />
<link rel="icon" type="image/x-icon" href="/favicon.ico" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>Information Assistant copilot template</title>
<title>Information Assistant agent template</title>
</head>
<body>
<div id="root"></div>
Expand Down
2 changes: 1 addition & 1 deletion app/frontend/src/pages/content/Content.tsx
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ const Content = () => {
<SparkleFilled fontSize={"60px"} primaryFill={"rgba(115, 118, 225, 1)"} aria-hidden="true" aria-label="Supported File Types" />
<h1 className={styles.EmptyStateTitle}>Supported file types</h1>
<span className={styles.EmptyObjectives}>
The Information Assistant copilot template currently supports the following file types:
The Information Assistant agent template currently supports the following file types:
</span>
<span className={styles.EmptyObjectivesList}>
<span className={styles.EmptyObjectivesListItem}>
Expand Down
8 changes: 4 additions & 4 deletions docs/costestimator.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
# Information Assistant (IA) copilot template - Estimation
# Information Assistant (IA) agent template - Estimation

The Azure pricing calculator helps estimate costs by considering the amount of data to be processed and stored, as well as the expected performance level. It allows users to customize and combine different Azure services for Information Assistant copilot template, version 1.2, and provides cost estimates based on the chosen configurations.
The Azure pricing calculator helps estimate costs by considering the amount of data to be processed and stored, as well as the expected performance level. It allows users to customize and combine different Azure services for Information Assistant agent template, version 1.2, and provides cost estimates based on the chosen configurations.

| Solution | Environment | Azure Pricing Calculator Link |
| :------------------:|:-----------------------------:|:------------------------------------------------:|
| IA copilot template, version 1.2 | Sandbox | [Sample Azure Estimation](https://azure.com/e/bd6e516bb0b549abb6d39cce088af684) |
| IA agent template, version 1.2 | Sandbox | [Sample Azure Estimation](https://azure.com/e/bd6e516bb0b549abb6d39cce088af684) |

## Azure Services

The following list of Azure Services will be deployed for IA copilot template, version 1.2:
The following list of Azure Services will be deployed for IA agent template, version 1.2:

- App Service (App Service Plan) [:link:](https://azure.microsoft.com/en-ca/pricing/details/app-service/linux/)
- Application Insights [:link:](https://azure.microsoft.com/en-ca/pricing/details/monitor/)
Expand Down
2 changes: 1 addition & 1 deletion docs/deployment/accepting_responsible_ai_notice.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Accepting Azure AI Service Responsible AI Notice

To be able to install the Information Assistant copilot template, you must have manually accepted the Azure AI Services Responsible AI Notice once for your subscription. To do this follow these steps:
To be able to install the Information Assistant agent template, you must have manually accepted the Azure AI Services Responsible AI Notice once for your subscription. To do this follow these steps:

## Manually create an "Azure AI services" in your Azure subscription and accept "Responsible AI Notice"

Expand Down
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Accepting Azure AI Services Multi-service Account Responsible AI Notice

To be able to install the Information Assistant copilot template, you must have manually accepted the Azure AI Services Multi-service Account Responsible AI Notice once for your subscription. To do this follow these steps:
To be able to install the Information Assistant agent template, you must have manually accepted the Azure AI Services Multi-service Account Responsible AI Notice once for your subscription. To do this follow these steps:

## Manually create an "Azure AI Services Multi-service Account" in your Azure subscription and accept "Responsible AI Notice"

Expand Down
2 changes: 1 addition & 1 deletion docs/deployment/configure_local_dev_environment.md
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ In your Ubuntu 22.04(WSL) terminal from the previous step, follow the directions

## Configure Local Development Environment

Follow these steps to get the copilot template up and running in a subscription of your choice.
Follow these steps to get the agent template up and running in a subscription of your choice.

### Clone Repo

Expand Down
6 changes: 3 additions & 3 deletions docs/deployment/considerations_production.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Considerations For Adopting Into Production

This documentation highlights key considerations for transitioning from an Information Assistant (IA) copilot template to a production-ready deployment. Emphasizing scalability, high availability, security, and proactive management, the recommendations cover components such as App Server scaling, Load Balancing strategies, and global-scale content delivery. Additional guidance addresses GPT Model throttling, security enhancements, proactive monitoring, and redundancy. It stresses the importance of safeguarding against cyber threats, seamless integration with existing ecosystems, and proactive environment management through monitoring and alerts.
This documentation highlights key considerations for transitioning from an Information Assistant (IA) agent template to a production-ready deployment. Emphasizing scalability, high availability, security, and proactive management, the recommendations cover components such as App Server scaling, Load Balancing strategies, and global-scale content delivery. Additional guidance addresses GPT Model throttling, security enhancements, proactive monitoring, and redundancy. It stresses the importance of safeguarding against cyber threats, seamless integration with existing ecosystems, and proactive environment management through monitoring and alerts.

## Scalability and High Availability

Expand Down Expand Up @@ -82,7 +82,7 @@ Diagnostic settings have been enabled in IA as part of our secure mode. You can

## Document Ingestion Limitations

**Consideration:** This copilot template uses Azure Document Intelligence for PDF's and Unstructured.io for document processing. These tools have their own limitations when it comes to document sizes they can handle. The page limit and document size limits for PDFs on Document Intelligence can vary by subscription tier. Learn more about Document Intelligence [here](https://learn.microsoft.com/en-us/legal/cognitive-services/document-intelligence/characteristics-and-limitations).
**Consideration:** This agent template uses Azure Document Intelligence for PDF's and Unstructured.io for document processing. These tools have their own limitations when it comes to document sizes they can handle. The page limit and document size limits for PDFs on Document Intelligence can vary by subscription tier. Learn more about Document Intelligence [here](https://learn.microsoft.com/en-us/legal/cognitive-services/document-intelligence/characteristics-and-limitations).

More info on unstructured.io for other supported document types can be found [here](https://unstructured-io.github.io/unstructured/introduction.html).

Expand All @@ -107,4 +107,4 @@ This can be achieved by modifying the currently provided UI by making a couple o

## In Summary

Ensure that your IA copilot template seamlessly integrates into your existing ecosystem, considering compatibility and interoperability. Use the IA copilot template as a blueprint to plan integration into your ecosystem.
Ensure that your IA agent template seamlessly integrates into your existing ecosystem, considering compatibility and interoperability. Use the IA agent template as a blueprint to plan integration into your ecosystem.
Loading

0 comments on commit 6f72169

Please sign in to comment.