llms.txt

Spice AI

Spice.ai is a data and AI platform that combines federated SQL query, hybrid search, and LLM inference in a portable, open-source runtime

Spice AI provides a unified data and AI infrastructure platform. Our open-source runtime enables federated SQL query across multiple data sources, hybrid vector and full-text search, and seamless LLM inference integration.

Documentation

Spice AI Documentation: Complete documentation for Spice AI
GitHub Repository: Open-source codebase and examples

Local Content

About Us: Learn about Spice AI's mission, team, and vision for empowering developers to build intelligent apps with unified data and AI infrastructure.
2025 Spice AI Year in Review: From day one, Spice was designed to simplify building modern, intelligent applications. In 2025 that vision turned into reality.
A Developer's Guide to Understanding Spice.ai: Learn what Spice.ai is, when to use it, and how it solves enterprise data challenges. A developer-focused guide to federation, acceleration, search, and AI.
A New Class of Applications That Learn and Adapt: Explore the history of decision engines and how modern machine learning enables applications that learn, adapt, and make better decisions over time with Spice.ai.
Adding Spice - The Next Generation of Spice.ai OSS: Learn how Spice.ai OSS was rebuilt in Rust to deliver fast, local SQL queries across databases, warehouses, and data lakes.
AI needs AI-ready data: An introduction to AI-ready data and how Spice.ai handles normalization, encoding, and real-time data preparation for ML applications.
Spice.ai Now Supports Amazon S3 Vectors For Vector Search at Petabyte Scale!: Spice AI has partnered with AWS to integrate Amazon S3 Vectors into the Spice.ai Open Source data and AI compute engine.
Announcing Spice.ai Open Source 1.0-stable: A Portable Compute Engine for Data-Grounded AI - Now Ready for Production: Learn how Spice.ai OSS grounds AI in real data with federated query, fast retrieval, and portable deployment anywhere.
Spice Cloud v1.7.0: DataFusion v49, Full-Text Search Updates & More: Spice Cloud v1.7.0 includes DataFusion v49, EmbeddingGemma support, and real-time indexing for full-text search
Apache Ballista at Spice AI: Distributed Query Execution Without the Operational Tax: A technical deep-dive into how Spice AI integrates Apache Ballista for distributed query execution with multi-active schedulers, fault-tolerant shuffle, and distributed acceleration.
Apache Iceberg at Spice AI: How we Query, Accelerate, and Write to Open Table Formats: A technical deep-dive into how Spice AI integrates Apache Iceberg for federated queries, sub-second acceleration, and ACID-compliant writes to open table formats.
AWS Workshop: Federated Queries and Hybrid Search with Spice.ai: A new AWS catalog workshop that walks through deploying Spice as a data and AI substrate across AWS infrastructure for federated queries, hybrid search, and LLM inference.
Barracuda Networks Gains 100x Faster Query Responses and 50% Reduction in Operational Costs with Spice.ai OSS: Barracuda Networks used Spice.ai OSS to accelerate archival and audit data access, improving query performance by up to 100x while reducing operational costs by 50%.
Basis Set Ventures Deploys Spice.ai to Power Natural Language Queries and Mitigate Hallucinations: Basis Set Ventures uses Spice.ai Enterprise to power natural language searches directly against real-time datasets.
Localhost Latency at Scale: The Spice Cluster-Sidecar Architecture: How the Spice cluster-sidecar architecture gives applications, services, and AI agents a sandboxed, localhost-latency data and inference plane backed by a distributed Spice cluster, without exposing underlying data systems.
Spice AI Announces Contribution of TableProviders for PostgreSQL, MySQL, DuckDB, and SQLite to the Apache DataFusion Project: Spice AI has contributed new TableProviders for PostgreSQL, MySQL, DuckDB, and SQLite to the Apache DataFusion project.
Announcing Our Partnership with Databricks!: Spice partners with Databricks to accelerate operational AI apps with fast SQL queries, Mosaic AI embeddings, and Unity Catalog governance.
Getting started with Amazon S3 Vectors and Spice: Learn how Spice AI integrates Amazon S3 Vectors for scalable, cost-effective vector search - combining semantic, full-text, and SQL queries in one runtime.
How we use Apache DataFusion at Spice AI: A technical overview of how Spice extends Apache DataFusion with custom table providers, optimizer rules, and UDFs to power federated SQL, search, and AI inference.
Interviewing at Spice AI: A guide to the Spice AI interview process, covering what to expect at each stage, how we evaluate candidates, and tips for preparation.
Introducing Spice Cayenne: The Next-Generation Data Accelerator Built on Vortex for Performance and Scale: Spice Cayenne is the next-generation Spice.ai data accelerator built for high-scale and low latency data lake workloads.
Introducing Spice Skills for AI Agents: Spice Skills is a collection of packaged agent instructions for working with Spice.ai OSS -- covering setup, data connections, acceleration, search, AI, and more.
Making Apps That Learn And Adapt: Building intelligent applications is still too hard for most developers-not because ML is impossible, but because it's treated as something separate from the app.
Making Object Storage Operational for Real-Time and AI Workloads: Transform object stores into real-time AI platforms. Spice adds federation, acceleration, hybrid search, and inference capabilities.
Multi-Tenancy for AI Agents without the Pipelines: Learn how to serve multi-tenant AI agents from disparate enterprise data sources with tenant isolation, federated SQL, and no per-tenant pipelines.
On Writing: Writing is fundamental to formalizing thoughts, communicating effectively, and is the ultimate creation tool.
Building an Enterprise SRE Agent with OpenClaw and Spice: How to build an OpenClaw SRE with Spice for safe, unified, and observable access to production data, demonstrated with real-world incident workflows.
Operationalizing Amazon S3 for AI: From Data Lake to AI-Ready Platform in Minutes: Transform Amazon S3 from passive storage to an AI-ready platform. Real-world example using Spice and S3 for hybrid search and LLM inference.
Real-Time Control Plane Acceleration with DynamoDB Streams: How to sync DynamoDB data to thousands of nodes with sub-second latency using a two-tier architecture with DynamoDB Streams and Spice acceleration.
Real-Time Hybrid Search Using RRF: A Hands-On Guide with Spice: Learn how to build hybrid search with Reciprocal Rank Fusion (RRF) directly in SQL using Spice - combining text, vector, and time-based relevance in one query for faster, more accurate results.
Spice 2.0: Real-Time Analytical Query on Operational Data, Without ETL: Spice 2.0 is now available: add real-time analytical query and search to operational data without ETL via high-throughput CDC replication, petabyte-scale distributed compute built on Apache Ballista, and enterprise-grade controls.
Spice AI achieves SOC 2 Type II compliance: Spice AI completes SOC 2 Type II audit, demonstrating enterprise-grade security and compliance for its data and AI infrastructure platform.
The Spice.ai for GitHub Copilot Extension is now available!: With the Spice.ai Extension, developers can interact with data, like product requirements documents (PRDs), tickets, and tabular data, from any external data source directly within GitHub Copilot. Save hours copying and pasting across various platforms, relevant data and answers are now surfaced in Copilot Chat, right when you need it.
Spice.ai is now generally available!: Spice.ai is now available for everyone, including a new community-centric developer hub and Community Edition complimentary for developers.
Faster, Simpler Dashboards with Spice and Power BI: Spice AI built a Microsoft Power BI Connector on top of the Flight SQL ADBC driver that makes it easy for Power BI users to query across operational databases, analytical warehouses, and object stores.
Spice Cloud v1.10: Caching Acceleration Mode, DynamoDB Streams Support, & More!: Spice v1.10 includes a new caching acceleration mode, a new DynamoDB Streams data connector in preview, Amazon S3 location-based pruning, S3 Tables write support, and several performance and security improvements.
Spice Cloud v1.11: Spice Cayenne Reaches Beta, Apache DataFusion v51, DynamoDB Streams Improvements, & More: v1.11 brings Spice Cayenne to Beta, DataFusion v51 and Apache Arrow v57.2, improved DynamoDB Streams, and more.
Spice Cloud v1.8.0: Iceberg Write Support, Acceleration Snapshots & More: Announcing Spice Cloud v1.8.0 - now with Iceberg write support, acceleration snapshots, partitioned S3 Vectors indexes & a new AI SQL function
Spice Cloud v1.9.0: Introducing the Spice Cayenne Data Accelerator: Spice Cloud v1.9.0 adds the Cayenne Data Accelerator, Apache DataFusion v50, HTTP data connector support for querying endpoints as tables, and much more.
Spice Cloud v2.0-rc.2: Cayenne RC, ADBC BigQuery, and Catalog Connectors: Spice Cloud v2.0-rc.2 introduces Spice Cayenne release candidate status, ADBC with BigQuery support, new catalog connectors, and major developer experience upgrades.
Spice Firecache | Cloud-Scale DuckDB: Cloud-Scale DuckDB
Spice OSS, rebuilt in Rust: Spice.ai OSS has been rebuilt from the ground up in Rust, delivering the performance, safety, and portability needed for production data infrastructure.
Getting Started with Spice.ai SQL Query Federation & Acceleration: Learn how to use Spice.ai to federate and accelerate queries across operational and analytical systems with zero ETL.
Spice.ai's approach to Time-Series AI: Explore the challenges of time-series AI and why Spice.ai uses a data-driven reinforcement learning approach to help developers build adaptive, intelligent applications.
Spicepods: From Zero to Hero: A step-by-step guide to authoring a Spicepod from scratch and using it to build an application that learns and adapts over time.
Teaching Apps how to Learn with Spicepods: Learn how Spicepods define application goals, rewards, and learning behavior - making it easy for developers to build applications that learn and adapt over time.
True Hybrid Search: Vector, Full-Text, and SQL in One Runtime: Build hybrid search without managing multiple systems. Query vectors, run full-text search, and execute SQL in one unified runtime.
Vortex at Spice AI: The Columnar Format for Data-Intensive Workloads: How Spice AI uses the Vortex columnar format in Cayenne to improve query latency, reduce memory overhead, and support high-concurrency data-intensive workloads.
What Data Informs AI-driven Decision Making?: Learn the three classes of data required for intelligent decision-making and how Spice.ai simplifies runtime data engineering for AI-powered applications.
Write to Apache Iceberg Tables with SQL in Spice: Spice v1.8 adds native Apache Iceberg write support with standard SQL INSERT INTO statements. Build complete data workflows without ETL - query, accelerate, and write from one runtime.

Spice AI

Documentation

Local Content

Blog