readme.md

Welcome to Spice.ai

The Spice.ai Cloud Platform is an AI application and agent cloud — an AI-backend-as-a-service with composable, ready-to-use building blocks including high-speed SQL query, LLM inference, vector search, and RAG, built on cloud-scale, managed Spice.ai OSS.

This documentation covers the Spice.ai Cloud Platform.

Table of Contents

Feature Description Link
🚀 Get Started Sign up and run your first query in minutes Get Started
Federated SQL Query Query across any data source with one SQL interface /pages/JSLAgkGEzRdATtrY2WbZ
🤖 AI Gateway OpenAI-compatible API for LLM inference /pages/xPzXLnuTVGxNphNmkCqK
🔍 Search & Retrieval Vector and hybrid search for RAG workflows /pages/fTHrnT4bxBvNnzdKaEO7
🔌 Data Connectors Connect to 30+ databases, warehouses, and lakes /pages/N3bRKIkaBpwkNfccYrXd
📊 Monitoring Observe performance with Grafana, Datadog, and more Monitoring

What You Can Do

With the Spice.ai Cloud Platform you can:

Use Cases

Use Case Description
Agentic AI Apps Build AI agent backends with unified data and model access
Database CDN Cache and accelerate hot data for low-latency applications
Data Lakehouse Federated queries across warehouses, lakes, and databases
Enterprise Search Semantic search across enterprise data sources
Enterprise RAG Retrieval-augmented generation with your own data

Quick Start

Get up and running in minutes:

  1. Sign in with GitHub
  2. Create a Spice app
  3. Add a dataset and query data
  4. Add an AI model and chat

Sample Code

from spicepy import Client

client = Client("YOUR_API_KEY")
reader = client.query(
    "SELECT * FROM my_table LIMIT 10"
)
df = reader.read_pandas()
print(df)

Community & Support

Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the ask query parameter, and the optional goal query parameter:

GET https://docs.spice.ai/getting-started/readme.md?ask=<question>&goal=<endgoal>

ask is the immediate question: it should be specific, self-contained, and written in natural language. goal is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.