azure-search-openai-demo and entaoai

Both tools provide a sample application for implementing a Retrieval-Augmented Generation (RAG) pattern to chat with custom data using Azure OpenAI, making them direct competitors as they address the same core use case.

entaoai
51
Established
Maintenance 23/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 7,602
Forks: 5,266
Downloads:
Commits (30d): 23
Language: Python
License: MIT
Stars: 867
Forks: 246
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About azure-search-openai-demo

Azure-Samples/azure-search-openai-demo

A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.

Implements document indexing via Azure AI Document Intelligence with support for multiple formats, includes in-UI settings for prompt engineering experimentation, and optionally layers multimodal vision capabilities for image-heavy content analysis. The backend uses Python with Infrastructure-as-Code (Bicep) for reproducible Azure deployments, while offering optional features like persistent chat history via Cosmos DB, speech accessibility, and Microsoft Entra identity integration for role-based data access control.

About entaoai

akshata29/entaoai

Chat and Ask on your own data. Accelerator to quickly upload your own enterprise data and use OpenAI services to chat to that uploaded data and ask questions

Implements retrieval-augmented generation (RAG) using Azure OpenAI embeddings with pluggable vector stores (Pinecone, Redis, Azure Cognitive Search) for semantic search over enterprise documents. Supports multiple interaction patterns including streaming chat, Q&A with follow-up generation, and SQL natural language queries, with built-in evaluation metrics (groundedness, coherence, similarity) and optional Azure Prompt Flow integration for production deployments.

Scores updated daily from GitHub, PyPI, and npm data. How scores work