Wren AI is a text-to-SQL solution for data teams to get results and insights faster by asking business questions without writing SQL.
Play around with Wren AI yourself!
Wren AI’s mission is to democratize data by bringing text-to-SQL ability to any data source and industry. We believe that breakthroughs in Text-to-SQL technology will usher in a new era of Data Democratization.
Wren AI has implemented a semantic engine architecture to provide the LLM context of your business; you can easily establish a logical presentation layer on your data schema that helps LLM learn more about your business context.
With Wren AI, you can process metadata, schema, terminology, data relationships, and the logic behind calculations and aggregations with “Modeling Definition Language” (MDL), reducing duplicate coding and simplifying data joins.
When starting a new conversation in Wren AI, your question is used to find the most relevant tables. From these, LLM generates three relevant questions for the user to choose from. You can also ask follow-up questions to get deeper insights.
The AI self-learning feedback loop is designed to refine SQL augmentation and generation by collecting data from various sources. These include user query history, revision intentions, feedback, schema patterns, semantics enhancement, and query frequency.
We focus on providing an open, secure, and reliable text-to-SQL solution for everyone.
Wren AI makes it easy to onboard your data. Discover and analyze your data with our user interface. Effortlessly generate results without needing to code.
Your database contents will never be transmitted to the LLM. Only metadata, like schemas, documentation, and queries, will be used in semantic search.
Deploy Wren AI anywhere you like on your own data, LLM APIs, and environment, it's free.
Wren AI consists of three core services:
-
Wren UI: An intuitive user interface for asking questions, defining data relationships, and integrating data sources within Wren AI'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.
- How do we rewrite Wren AI LLM Service to support 1500+ concurrent users online?
- The new wave of Composable Data Systems and the Interface to LLM agents
- How do you use OpenAI GPT-4o to query your database?
- Top 4 Challenges using RAG with LLMs to Query Database (Text-to-SQL) and how to solve it.
- How we design our semantic engine for LLMs? The backbone of the semantic layer for LLM architecture.
- How do you use LangChain to build a Text-to-SQL solution? What are the challenges? How to solve it?
- Deep dive into how Pinterest built its Text-to-SQL solution.
- How Snowflake building the most powerful SQL LLM in the world
- How to directly access 150k+ Hugging Face Datasets with DuckDB and query using GPT-4o
Wren AI is currently in alpha version. The project team is actively working on progress and aiming to release new versions at least biweekly.
Using Wren AI is super simple, you can setup within 3 minutes, and start to interact with your own data!
- Visit our Installation Guide of Wren AI.
- Visit the Usage Guides to learn more about how to use Wren AI.
Visit Wren AI documentation to view the full documentation.
- 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 Wren AI community channels. Users are highly encouraged to read and adhere to them to avoid repercussions.