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.

Open Index: A Deterministic Memory Layer for Your AI Agents
September 16, 2026
Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a "brain," a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.
tooltrim: Drastically Reduce LLM Agent Tool Output Tokens, Improve Accuracy
September 16, 2026
tooltrim provides drop-in compression for LLM agent tool outputs, drastically cutting tokens while often improving answer accuracy. This provider-agnostic solution offers content-aware compression, faithfulness benchmarks, and seamless integration with popular frameworks or as an OpenAI-compatible proxy.

AgentShield: Python Firewall for AI Agent Spend Control
September 16, 2026
AgentShield is a pure Python library designed to prevent runaway AI agents from exceeding budget limits. It offers 10 composable spend rules, evaluated in under 1ms, providing robust cost control. Although its core development has transitioned to sipi.bot, the AgentShield Python package remains available for existing users and its test fixtures are open-source.

DA-Forge: Streamlining Declarative Agent Creation for Copilot Notebooks
September 12, 2026
DA-Forge is a Python-based tool by Microsoft designed to automate the creation and deployment of Declarative Agents for Copilot Notebooks. It significantly reduces the manual effort and time required to set up AI assistants with specific grounding references, transforming an 85-minute process into just a few minutes. This tool is essential for developers and researchers working with Copilot Notebooks and Declarative Agents.
Source repository
Open the original repository on GitHub.
26 counted GitHub visits