Vanna: Chat with Your SQL Database Using LLMs and Agentic Retrieval
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
Vanna is an open-source Python library that enables natural language interaction with SQL databases, leveraging Large Language Models (LLMs) for accurate text-to-SQL generation. Version 2.0 introduces enterprise-grade features like user-aware permissions, a modern web interface, and streaming responses, making it ideal for secure and scalable data analytics applications.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
Vanna is an innovative open-source Python framework designed to transform natural language questions into actionable data insights from your SQL database. Leveraging Large Language Models (LLMs) and agentic retrieval, Vanna accurately generates SQL queries, making data accessible to a wider audience. The latest Vanna 2.0 release brings significant enhancements, focusing on enterprise-grade security, user-aware permissions, and a modern, streaming web interface. It allows users to effortlessly chat with their SQL database, receiving real-time progress updates, generated SQL code (for admins), interactive data tables, Plotly charts, and natural language summaries, all streamed directly to a web component.
Installation
Getting started with Vanna is straightforward. For a comprehensive guide and quick setup, refer to the official documentation:
Examples
Vanna provides a pre-built web component, <vanna-chat>, that can be easily embedded into any webpage, offering a rich, interactive experience.
Here's how you can drop the Vanna chat component into your HTML:
<!-- Drop into any existing webpage -->
<script src="https://img.vanna.ai/vanna-components.js"></script>
<vanna-chat
sse-endpoint="https://your-api.com/chat"
theme="dark">
</vanna-chat>
This component uses your existing cookies/JWTs and works seamlessly with frameworks like React, Vue, or plain HTML. Users can ask questions in natural language, and Vanna will return streaming progress updates, SQL code blocks (optionally for admins), interactive data tables, charts, and natural language summaries, all in real-time.
Why Use Vanna
Vanna 2.0 is built for production and offers a compelling set of features:
- Get Started Instantly: It provides a production-ready chat interface and a custom agent that integrates with your database, easily embeddable in any webpage.
- Enterprise-Ready Security: Features user-aware permissions at every layer, row-level security, comprehensive audit logs for compliance, and rate limiting via lifecycle hooks.
- Beautiful Web UI Included: The pre-built
<vanna-chat>component eliminates the need to build your own chat interface, offering streaming tables and charts, responsive design, customizable themes, and framework-agnostic compatibility. - Works With Your Stack: Vanna is highly flexible, supporting various LLMs (OpenAI, Anthropic, Google Gemini, etc.), databases (PostgreSQL, MySQL, Snowflake, BigQuery, etc.), your existing authentication systems (cookies, JWTs, OAuth), and popular frameworks like FastAPI and Flask.
- Extensible But Opinionated: It allows for custom tools, lifecycle hooks for quota checking and logging, LLM middlewares for caching and prompt engineering, built-in observability, and context enrichers for RAG and memory.
Links
For more detailed information, guides, and community support, please visit the official Vanna resources:
Related repositories
Similar repositories that may be relevant next.

Ragas: Supercharge Your LLM Application Evaluations
August 9, 2026
Ragas is an ultimate toolkit for evaluating and optimizing Large Language Model (LLM) applications. It offers objective metrics, intelligent test generation, and data-driven insights to move beyond subjective assessments. This framework helps developers build feedback loops and continuously improve their LLM applications.

awesome-cli-coding-agents: A Curated Directory of Terminal-Native AI Tools
August 9, 2026
The `awesome-cli-coding-agents` repository offers a comprehensive, curated directory of over 100 terminal-native AI coding agents. These powerful tools operate directly within your command line, enabling autonomous code reading, editing, and execution. The list also covers various harnesses and orchestration solutions for managing these agents.

QwenPaw: Your Personal AI Assistant for Local and Cloud Deployment
August 7, 2026
QwenPaw is a powerful personal AI assistant designed for easy installation and deployment, either on your local machine or in the cloud. It supports multiple chat applications and offers highly extensible capabilities, making it a versatile tool for various AI-driven tasks. With its robust memory system and security features, QwenPaw aims to be an intuitive and private partner in your digital life.

DeepTutor: Lifelong Personalized Tutoring with AI Agents
August 7, 2026
DeepTutor is an advanced AI-powered platform designed for lifelong personalized tutoring, integrating various learning modes into a single, extensible system. It leverages large language models and multi-agent systems to offer features like interactive chat, quiz generation, and skill development. This project provides a comprehensive environment for learners and educators seeking intelligent, adaptive educational tools.
Source repository
Open the original repository on GitHub.
19 counted GitHub visits