spiceai/docs

title: 'Spice.ai Features' sidebar_label: 'Features' sidebar_position: 3 description: 'Explore Spice.ai features including data federation, data acceleration, caching, search, LLM integration, embeddings, observability, and more for building data-driven AI applications.' keywords: [spice.ai, features, data federation, data acceleration, caching, search, llm, embeddings, observability, cdc, machine learning] image: /img/og/spiceai.png pagination_prev: null pagination_next: null

import DocCardList from '@theme/DocCardList';

Spice provides a set of features for building data-driven applications and AI agents. This page gives an overview of each feature area.

Data Query and Federation

Query Federation (opens in a new tab) connects multiple data sources—databases, data warehouses, and data lakes—through a single SQL interface. Write one query that joins data across PostgreSQL, Snowflake, S3, and other sources. Spice pushes query operations to source databases when possible to reduce data transfer.

Data Acceleration and Caching

Data Acceleration (opens in a new tab) materializes remote datasets locally in memory or on disk using engines like Arrow, DuckDB, SQLite, or PostgreSQL. Accelerated datasets stay current through scheduled refreshes, append mode, or Change Data Capture (CDC) (opens in a new tab). Caching (opens in a new tab) stores query and search results in memory with configurable TTLs and eviction policies to avoid redundant computation.

AI and Language Models

Large Language Models (opens in a new tab) provides an OpenAI-compatible API gateway for hosted models (OpenAI, Anthropic, xAI) and locally served models (Llama, Phi) with CUDA and Metal acceleration. Models can call tools to query datasets, run SQL, and retrieve schemas. Embeddings (opens in a new tab) generates vector representations of text for semantic search and RAG workflows.

Search

Search (opens in a new tab) supports three methods: vector search (semantic similarity using embeddings), full-text search (keyword matching with BM25 scoring), and hybrid search (combining both with Reciprocal Rank Fusion). All search methods are accessible through SQL UDTFs like vector_search() and text_search().

Monitoring and Observability

Observability (opens in a new tab) exposes Prometheus-compatible metrics, OpenTelemetry metric export, and distributed tracing with Zipkin. Integrations are available for Datadog, Grafana, and other monitoring platforms.

title: 'Spice.ai Features' sidebar_label: 'Features' sidebar_position: 3 description: 'Explore Spice.ai features including data federation, data acceleration, caching, search, LLM integration, embeddings, observability, and more for building data-driven AI applications.' keywords: [spice.ai, features, data federation, data acceleration, caching, search, llm, embeddings, observability, cdc, machine learning] image: /img/og/spiceai.png pagination_prev: null pagination_next: null

import DocCardList from '@theme/DocCardList';

Spice provides a set of features for building data-driven applications and AI agents. This page gives an overview of each feature area.

Data Query and Federation

Query Federation connects multiple data sources—databases, data warehouses, and data lakes—through a single SQL interface. Write one query that joins data across PostgreSQL, Snowflake, S3, and other sources. Spice pushes query operations to source databases when possible to reduce data transfer.

Data Acceleration and Caching

Data Acceleration materializes remote datasets locally in memory or on disk using engines like Arrow, DuckDB, SQLite, or PostgreSQL. Accelerated datasets stay current through scheduled refreshes, append mode, or Change Data Capture (CDC). Caching stores query and search results in memory with configurable TTLs and eviction policies to avoid redundant computation.

AI and Language Models

Large Language Models provides an OpenAI-compatible API gateway for hosted models (OpenAI, Anthropic, xAI) and locally served models (Llama, Phi) with CUDA and Metal acceleration. Models can call tools to query datasets, run SQL, and retrieve schemas. Embeddings generates vector representations of text for semantic search and RAG workflows.

Search supports three methods: vector search (semantic similarity using embeddings), full-text search (keyword matching with BM25 scoring), and hybrid search (combining both with Reciprocal Rank Fusion). All search methods are accessible through SQL UDTFs like vector_search() and text_search().

Monitoring and Observability

Observability exposes Prometheus-compatible metrics, OpenTelemetry metric export, and distributed tracing with Zipkin. Integrations are available for Datadog, Grafana, and other monitoring platforms.