Spice.ai Logo
Docs

Build fast data and AI APIs.

Spice makes it easy for developers to create production-ready
AI-native data warehouses using Apache Arrow, DuckDB, and SQLite.

Spice.ai breakdown

Spice is a portable, open-source runtime for fast, last-mile SQL query and AI inference.

Federated Data Access

Query structured and unstructed data using SQL across databases, data warehouses, and data lakes.

Docs

Self-Hostable and Open-Source

Self-hostable binary or Docker image, platform-agnostic, and Apache 2.0 licensed. Built on industry standard technologies including Apache DataFusion and Apache Arrow.

Data Acceleration

Materialize data and content in DuckDB, SQLite, and PostgreSQL; in-memory or on disk. Results caching included.

Docs

Secure AI/ML Gateway

Load-balance across local models and OpenAI compatible endpoints with full observability, metrics, telemetry, query/task history, data flows, and tracing.

Before Spice to With Spice

See how Spice has been deployed in production architectures.

Before and After Slide

Slow 15 sec queries across 100B+ rows.

Poor user experience with slow page loads.

Unnecessary Databricks workspace expense.

Use-Cases

Unified SQL Interface for effortlessly materializing, accelerating, and querying data from any database, data warehouse, or data lake.

Install the Spice CLI

Try materializing and querying Parquet files from S3, on your laptop, in under 60 seconds.

QuickstartsSamplesDocs

Blog Highlights

View all
Spice v0.20-beta (Nov 4, 2024)
Spice v0.20-beta (Nov 4, 2024)

Announcing the release of Spice v0.20-beta 🧩 Spice v0.20.0-beta improves federated query performance with column pruning and adds support for Metal (Apple Silicon) and CUDA (NVidia) accelerators. The S3, PostgreSQL, MySQL, and GitHub Data Connectors have graduated from Beta to Release Candidates. The Arrow, DuckDB, and SQLite Data Accelerators have graduated from Alpha to Beta.

Continue reading
Spice v0.19.4-beta (Oct 30, 2024)
Spice v0.19.4-beta (Oct 30, 2024)

Announcing the release of Spice v0.19.4-beta ☘️ Spice v0.19.4-beta introduces a new `localpod` Data Connector, improvements to accelerator resiliency and control, and a new configuration to control when accelerated datasets are considered ready.

Continue reading
Spice v0.19.3-beta (Oct 28, 2024)
Spice v0.19.3-beta (Oct 28, 2024)

Announcing the release of Spice v0.19.3-beta 📈 Spice v0.19.3-beta improves the performance and stability of data connectors and accelerators, including faster queries across multiple federated sources by optimizing how filters are applied. Anthropic has also been added as a LLM model provider.

Continue reading
Spice.ai Logo

Secure, highly-available access to data. Ridiculously easy setup. Super fast query & AI inference.

“We have been looking for a way to accelerate queries from our Databricks workspaces. Spice was the perfect solution, as it was super simple to setup and it was easy to define and query accelerated datasets without a lot of overhead.”

Andy Blyler

Chief Data Officer at Barracuda

EigenLayer
Andy