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
Overview
EntaoAI is an open-source sample application that demonstrates how to create ChatGPT-like conversational experiences over enterprise data. Built on Azure OpenAI Service, it provides a complete pipeline for uploading proprietary documents and enabling natural language interactions with that data. The tool supports multiple vector storage options including Pinecone, Redis, and Azure Cognitive Search for data indexing and retrieval. EntaoAI implements Retrieval Augmented Generation (RAG) patterns, allowing organizations to leverage large language models while maintaining control over their data. The platform includes advanced features like multi-modal RAG capabilities, streaming chat responses, and comprehensive evaluation tools through Azure ML Prompt Flow. With built-in evaluation metrics for groundedness, coherence, and similarity scoring, teams can assess and improve their RAG implementations. The tool has evolved through multiple iterations, with recent updates focusing on core chat, Q&A, upload, and admin functionality. While designed as a sample application, EntaoAI provides a solid foundation for organizations looking to implement enterprise AI chat solutions using their own data sources.
Pros
- + Supports multiple vector stores (Pinecone, Redis, Azure Cognitive Search) providing flexibility in deployment options
- + Includes comprehensive evaluation framework with Prompt Flow integration and metrics like groundedness and Ada similarity
- + Active development with regular updates and refactoring to improve core functionality and remove complexity
Cons
- - Designed as a sample application rather than production-ready solution, requiring additional development for enterprise deployment
- - Specifically tied to Azure OpenAI Service, limiting flexibility in LLM provider choice
- - Has undergone multiple refactoring cycles that removed features, suggesting potential instability in feature set
Use Cases
- • Enterprise document Q&A systems where employees need to query internal knowledge bases using natural language
- • Internal chatbots for customer support teams to quickly access company policies and procedures
- • Research and development teams building custom RAG applications for proprietary data analysis