A RAG chat app that answers natural-language questions about rows in a PostgreSQL table, using pgvector search and OpenAI models, deployable to Azure.
Azure-Samples/chat-with-your-data-solution-accelerator
An Azure-hosted RAG accelerator that grounds a chat assistant in your own documents, returning answers with inline citations to sources.
- Stars
- 1,188
- Forks
- 650
- Open issues
- 39
- Last commit
- 4 days ago
What is it?
Chat with Your Data is a deployable retrieval-augmented generation (RAG) solution for Azure. It ingests your documents, such as contracts, policies, product manuals, and benefit guides, or public web pages, then answers natural-language questions using only the relevant indexed passages. Each answer streams to a chat page with inline citations that link back to the source files.
The solution runs on Azure Container Apps with a React single-page frontend, a FastAPI backend, and an Azure Functions ingestion worker. Models and retrieval come from Azure AI Foundry. Operators choose at deploy time between Azure AI Search with Cosmos DB or PostgreSQL with pgvector as the index and chat-history store, and between Agent Framework or LangGraph as the orchestrator. Access to downstream services uses a single user-assigned managed identity with Azure RBAC, and deployment is done with `azd up`.
An admin interface handles ingestion, dataset inspection, and prompt configuration. The sample data is synthetic and intended for demonstration; the project is a starting point that requires evaluation of retrieval quality and responsible-AI considerations before production use.
Key features
- 01Answers include inline citations linking back to source documents.
- 02Ingests uploaded files or public web pages through a parse, chunk, and embed pipeline.
- 03Choice of Azure AI Search with Cosmos DB or PostgreSQL with pgvector as the storage backend.
- 04Choice of Agent Framework or LangGraph as the orchestrator.
- 05Azure AI Content Safety screens prompts and responses.
- 06Voice input through speech-to-text and an admin interface for managing data and prompts.
Use cases
- Letting employees query internal HR policies and benefits documents with cited answers.
- Searching and summarizing contracts to surface obligations, deadlines, and clauses.
- Making customer-facing documents and account notes queryable by account teams.
Quick start
- 1
Open the deployment guide for the quick deploy steps
- 2
Deploy the solution to your Azure subscription with azd
azd up - 3
Remove all created resources when finished
azd down
Things to know
- Deploys only to Azure and needs an Azure subscription with quota for Azure AI Foundry models.
- Described as a starting point, not a turnkey production system; retrieval and answer quality must be evaluated on your own data.
- Resources keep incurring charges until deleted with azd down.
In collections
Topics
FAQ
- What is chat-with-your-data-solution-accelerator?
- An Azure-hosted RAG accelerator that grounds a chat assistant in your own documents, returning answers with inline citations to sources. Chat with Your Data is a deployable retrieval-augmented generation (RAG) solution for Azure. It ingests your documents, such as contracts, policies, product manuals, and benefit guides, or public web pages, then answers natural-language questions using only the relevant indexed passages. Each answer streams to a chat page with inline citations that link back to the source files.
- Is chat-with-your-data-solution-accelerator free to use? What license does it have?
- chat-with-your-data-solution-accelerator is open source under the MIT license. Check the license terms before using it in commercial products.
- Is chat-with-your-data-solution-accelerator still maintained?
- Actively maintained. The last commit to chat-with-your-data-solution-accelerator was on Nov 3, 2026.
- What can I use chat-with-your-data-solution-accelerator for?
- Letting employees query internal HR policies and benefits documents with cited answers. Searching and summarizing contracts to surface obligations, deadlines, and clauses. Making customer-facing documents and account notes queryable by account teams.
- How do I install chat-with-your-data-solution-accelerator?
- Open the deployment guide for the quick deploy steps Deploy the solution to your Azure subscription with azd: azd up Remove all created resources when finished: azd down
- Where can I get chat-with-your-data-solution-accelerator?
- The source code and installation instructions are on GitHub: https://github.com/Azure-Samples/chat-with-your-data-solution-accelerator
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Azure-based solution accelerator that mines conversational and document data with generative AI, offering chat exploration and auto-generated insight dashboards.
A Python chat web app that calls Azure OpenAI with managed identity, provisioned and deployed to Azure Container Apps via azd.
A local retrieval-augmented generation app that answers questions over your PDFs, Word and text files with citations to file and page, running on Ollama.
Scripts and tools to evaluate RAG chat apps using the Azure AI Evaluate SDK and OpenAI-based graders.
Self-hosted platform for building AI agents and assistants that answer questions from your own documents, with citations and any model.