Originally from GPT-RAG
The RAG pattern enables businesses to use the reasoning capabilities of LLMs, using their existing models to process and generate responses based on new data. RAG facilitates periodic data updates without the need for fine-tuning, thereby streamlining the integration of LLMs into businesses.
The Enterprise RAG Solution Accelerator (GPT-RAG) offers a robust architecture tailored for enterprise-grade deployment of the RAG pattern. It ensures grounded responses and is built on Zero-trust security and Responsible AI, ensuring availability, scalability, and auditability. Ideal for organizations transitioning from exploration and PoC stages to full-scale production and MVPs.
GPT-RAG follows a modular approach, consisting of three components, each with a specific function.
-
Data Ingestion - Optimizes data chunking and indexing for the RAG retrieval step.
-
Orchestrator - Coordinates the flow to retrieve information and generate a user response using Semantic Kernel functions.
-
App Front-End - Uses the Backend for Front-End pattern to provide a scalable and efficient web interface.
If you want to learn more about the RAG Pattern and GPT-RAG architecture.
- Basic Architecture Deployment: for quick demos with no network isolation⚙️
Learn how to quickly set up the basic architecture for scenarios without network isolation. Click the link to proceed.
This guide will walk you through the deployment process of Enterprise RAG. Before beginning the deployment, please ensure you have prepared all the necessary tools and services as outlined in the Pre-requisites section.
Pre-requisites
- Azure Developer CLI: Download azd
- Ensure the correct OS is selected
- Powershell 7+ with AZ module (Windows only): Powershell, AZ Module
- Git: Download Git
- Node.js 16+ windows/mac linux/wsl
- Python 3.11: Download Python
- Initiate an Azure AI services creation and agree to the Responsible AI terms **
- ** If you have not created an Azure AI service resource in the subscription before
For quick demonstrations or proof-of-concept projects without network isolation requirements, you can deploy the accelerator using its basic architecture.
The deployment procedure is quite simple, just install the prerequisites mentioned above and follow these four steps using Azure Developer CLI (azd) in a terminal:
1 Download the Repository:
azd init1.a Give the environment a unique name. This will be used to create your resources. For example, cowboy-hats would create resource group rg-cowboy-hats.
Enter a new environment name: some-name-here2 Login to Azure:
2.a Azure Developer CLI:
azd auth login2.b Azure CLI:
az login2.c Select your Azure Subscription from list.
3 Start Building the infrastructure and components deployment:
azd up3.a Select your Azure Subscription from list.
3.b Select Azure region. Recommended: East US (eastus)
4 Add source documents to object storage from /datasources directory.
Upload your documents to the 'documents' folder located in the storage account. The name of this account should start with 'strag'. This is the default storage account, as shown in the sample image below.
Done! Basic deployment is completed.
Recommended: Add app authentication. Watch this quick tutorial for step-by-step guidance.
The standard deployment process sets up Azure resources and deploys the accelerator components with a standard configuration. To tailor the deployment to your specific needs, follow the steps in the Custom Deployment section for further customization options.
Expand your data retrieval capabilities by integrating new data sources such as Bing Custom Search, SQL Server, and Teradata. For detailed instructions, refer to the AI Integration Hub page.
Once you've successfully deployed the GPT-RAG solution as a proof of concept and you're ready to formalize the deployment using a proper CI/CD process to accelerate your deployment to production, refer to the multi-environment deployment guides for either Azure DevOps or GitHub.
If you encounter any errors during the deployment process, consult the Troubleshooting page for guidance on resolving common issues.
To assess the performance of your deployment, refer to the Performance Testing guide for testing methodologies and best practices.
Learn how to query and analyze conversation data by following the steps outlined in the How to Query and Analyze Conversations document.
Understand the cost implications of your deployment by reviewing the Pricing Model for detailed pricing estimation.
Ensure proper governance of your deployment by following the guidelines provided in the Governance Model.
We appreciate your interest in contributing to this project! Please refer to the CONTRIBUTING.md page for detailed guidelines on how to contribute, including information about the Contributor License Agreement (CLA), code of conduct, and the process for submitting pull requests.
Thank you for your support and contributions!
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.