WrenAI/README.md

WrenAI

WrenAI is a text-to-SQL solution for data teams to get results and insights faster by asking business questions without writing SQL.

▶️ Video Introduction

🎯 Our Mission

WrenAI is reimagining how businesses can interact with and leverage their data through LLM by bringing comprehension capabilities to database data structures.

👉 Learn more about our mission

👊 Why WrenAI?

1. Reduce Hallucination

WrenAI offers detailed, explainable responses, ensuring users understand the origins and context of their data, thereby reducing hallucinations in LLMs.

2. Augment Your LLM Knowledge Base

WrenAI enriches LLMs with your specific business context, with additional metadata for your data schema, such as semantics and relationships.

3. Self-Learning Feedback Loop

WrenAI evolves with every interaction. It learns from user feedback and behavioral patterns, continuously refining its suggestions.

🔥 Preview

Ask your business questions and follow-up insights

Modeling with semantics, such as relationships, metrics and calculations

🤔 Benefits using WrenAI

WrenAI leverages Large Language Models (LLM) with Retrieval-Augmented Generation (RAG) technology to enhance comprehension of internal data. Below are the three key benefits:

1. Fast Onboarding

Discover and analyze your data with our user interface. Suitable for data analysts, and non-technical users to use.

2. Secure By Design

Your database contents will never be transmitted to the LLM. Only metadata, like schemas, documentation, and queries, will be used in semantic search.

3. Open-Source

Deploy WrenAI anywhere you like on your own data, LLM APIs, and environment, it's free.

🤖 WrenAI's Architecture

WrenAI is consist of three core services:

• Wren UI: An intuitive user interface for asking questions, defining data relationships, and integrating data sources within WrenAI's framework.

• Wren AI Service: Processes queries using a vector database for context retrieval, guiding LLMs to produce precise SQL outputs.

• Wren Engine: Serves as the semantic engine, mapping business terms to data sources, defining relationships, and incorporating predefined calculations and aggregations.

🤩 Learn More About Text-to-SQL

• Top 4 Challenges using RAG with LLMs to Query Database (Text-to-SQL) and how to solve it.
• How do you use LangChain to build a Text-to-SQL solution? What are the challenges? How to solve it?
• What we learned from Pinterest’s Text-to-SQL solution?

🤞 Design Philosophies

We have some core design philosophies that were used when developing WrenAI.

• Explainability: WrenAI ensures that every SQL query generated in natural language is accurate, concise, and reliable.
• Interoperability: WrenAI enables users to query data from multiple sources without dealing with the complexities of different data formats and dialects, providing a standard interface across different sources.
• Interactive Experience: WrenAI is designed to engage users in a dialogue, clarifying their queries and refining results in real time.
• Continuous Learning: WrenAI will proactively learn through ongoing query history, feedback, and interactions. Incorporating new patterns, information, and data structures into our LLM knowledge base.

🚧 Project Status

WrenAI is currently in alpha version. The project team is actively working on progress and aiming to release new versions at least biweekly.

🚀 Getting Started

Using WrenAI is super simple, you can setup within 3 minutes, and start to interact with your own data!

• Visit our Installation Guide of WrenAI.
• Visit the Usage Guides to learn more about how to use WrenAI.

📚 Documentation

Visit WrenAI documentation to view the full documentation.

⭐️ Community

• Welcome to our Discord server to give us feedback!
• If there is any issues, please visit GitHub Issues.

Do note that our Code of Conduct applies to all WrenAI community channels. Users are highly encouraged to read and adhere to them to avoid repercussions.