Query ChatGPT against your data

Add further value to your data with the power of OpenAI embedded in your database. Easily build a Q&A bot to answer questions in your website, application, documentation or knowledge base.

Start free

Ask your data

Create interactive and engaging conversational interfaces with our embedded OpenAI integration.

Learn More

Vector embeddings supported

Store your vectors in Xata and find it’s nearest neighbors with our SDK helper functions.

Learn More

LangChain integration

Pair Xata with your favorite LLM as a vector or memory store.

Learn More

Highly tuneable

All the knobs and dials you need to fine tune AI for your application.

Learn More

Easily extend to chat

Level up your application with OpenAI chat experiences within your existing database through our ask endpoint.

// Question a specific table. In this case "Docs"
const result = await xata.db.Docs.ask(
  // Pass in a simple question
  'How do I install Xata?',
  {
    // Rules define how your chatbot responds
    rules: [
      'Do not answer questions about pricing or the free tier. Respond that Xata has several options available, please check https://xata.io/pricing for more information.',
      'When you give an example, this example must exist exactly in the context given.'
    ],
    searchType: 'keyword',
    // Use search parameters to query and weight results
    search: {
      fuzziness: 2,
      prefix: 'phrase',
      target: [{ column: 'title', weight: 4 }, 'content', { column: 'keywords', weight: 4 }]
    }
  }
);

Bring your own LLM

Bring your favorite LLM with LangChain and LangChain.js integrations for Xata as a vector and memory store.

Add column to table

Semantic search

Whether you're using our OpenAI integration or bring your own embeddings, Xata makes semantic search easy.

Add column to table

Explore more resources

Chatbot with Xata

Building a Retrieval-Augmented Generation Chatbot with SvelteKit and Xata Vector Search

By Rishi Raj Jain

February 28, 2024

Learn how to create a Retrieval-Augmented Generation Chatbot using Xata, SvelteKit, LiteLLM, TailwindCSS and Vercel.

Keyword versus vector search

Semantic or keyword search for finding ChatGPT context. Who searched it better?

By Tudor Golubenco

March 6, 2023

The blog post compares keyword search with semantic/vector search for the task of selecting context for an ChatGPT-based questions and answers bot.

Xata and ChatGPT logos

Xata & OpenAI: ChatGPT for your data

By Daniel Everts

March 2, 2023

Use Xata to ask your data questions and get the answers that matter most.

Learn by example

Try out a sample app

Built with Next.js, Chakra UI, and Xata, the sample app will help you learn how to query, paginate and search records with a heavy focus on file attachments.

View source on GitHub
Add column to table

Start free,
pay as you grow

Xata provides the best free plan in the industry. It is production ready by default and doesn't pause or cool-down. Take your time to build your business and upgrade when you're ready to scale.

Free plan includes
  • 10 database branches
  • High availability
  • Support-assisted daily backups
  • 15 GB data storage
  • 15 GB search engine storage
  • 2 GB file attachments
  • 250 AI queries per month
Start freeExplore all plans
Free plan includes
  • 10 database branches
  • High availability
  • Support-assisted daily backups
  • 15 GB data storage
  • 15 GB search engine storage
  • 2 GB file attachments
  • 250 AI queries per month
Add column to table

Copyright © 2024 Xatabase Inc.
All rights reserved.

Product

RoadmapFeature requestsPricingStatusAI solutionsFile attachments