Skip to main content

3 posts tagged with "caching"

Results Cache related topics and usage

View All Tags

Spice v1.10.0 (Dec 9, 2025)

· 18 min read
William Croxson
William Croxson
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.10.0! ⚡

Spice v1.10.0 introduces a new Caching Acceleration Mode with stale-while-revalidate (SWR) semantics for disk-persisted, low-latency queries with background refresh. This release also adds the TinyLFU eviction policy for the SQL results cache, a preview of the DynamoDB Streams connector for real-time CDC, S3 location predicate pruning for faster partitioned queries, improved distributed query execution, and multiple security hardening improvements.

What's New in v1.10.0​

Caching Acceleration Mode​

Low-Latency Queries with Background Refresh: This release introduces a new caching acceleration mode that implements the stale-while-revalidate (SWR) pattern. Queries return cached results immediately while data refreshes asynchronously in the background, eliminating query latency spikes during refresh cycles. Cached data persists to disk using DuckDB, SQLite, or Cayenne file modes.

Key Features:

  • Stale-While-Revalidate (SWR): Returns cached data immediately while refreshing in the background, reducing query latency
  • Disk Persistence: Cached results persist across restarts using DuckDB, SQLite, or Cayenne file modes
  • Configurable Refresh: Control refresh intervals with refresh_check_interval to balance freshness and source load

Recommendation: Use retention configuration with caching acceleration to ensure stale data is cleaned up over time.

Example spicepod.yaml configuration:

datasets:
  - from: http://localhost:7400
    name: cached_data
    time_column: fetched_at
    acceleration:
      enabled: true
      engine: duckdb
      mode: file # Persist cache to disk
      refresh_mode: caching
      refresh_check_interval: 10m
      retention_check_enabled: true
      retention_period: 24h
      retention_check_interval: 1h

For more details, refer to the Data Acceleration Documentation.

TinyLFU Cache Eviction Policy​

Higher Cache Hit Rates for SQL Results Cache: A new TinyLFU cache eviction policy is now available for the SQL results cache. TinyLFU is a probabilistic cache admission policy that maintains higher hit rates than LRU while keeping memory usage predictable, making it ideal for workloads with varying query frequency patterns.

Example spicepod.yaml configuration:

runtime:
  caching:
    sql_results:
      enabled: true
      eviction_policy: tiny_lfu # default: lru

For more details, refer to the Caching Documentation and the Moka TinyLFU Documentation for details of the algorithm.

DynamoDB Streams Data Connector (Preview)​

Real-Time Change Data Capture for DynamoDB: The DynamoDB connector now integrates with DynamoDB Streams for real-time change data capture (CDC). This enables continuous synchronization of DynamoDB table changes into Spice for real-time query, search, and LLM-inference.

Key Features:

  • Real-Time CDC: Automatically captures inserts, updates, and deletes from DynamoDB tables as they occur
  • Table Bootstrapping: Performs an initial full table scan before streaming changes, ensuring complete data consistency
  • Acceleration Integration: Works with refresh_mode: changes to incrementally update accelerated datasets

Note: DynamoDB Streams must be enabled on your DynamoDB table. This feature is in preview.

Example spicepod.yaml configuration:

datasets:
  - from: dynamodb:my_table
    name: orders_stream
    acceleration:
      enabled: true
      refresh_mode: changes # Enable Streams capture

For more details, refer to the DynamoDB Connector Documentation.

OpenTelemetry Metrics Exporter​

Spice can now push metrics to an OpenTelemetry collector, enabling integration with platforms such as Jaeger, New Relic, Honeycomb, and other OpenTelemetry-compatible backends.

Key Features:

  • Protocol Support: Supports the gRPC (default port 4317) protocol
  • Configurable Push Interval: Control how frequently metrics are pushed to the collector

Example spicepod.yaml configuration for gRPC:

runtime:
  telemetry:
    enabled: true
    otel_exporter:
      endpoint: 'localhost:4317'
      push_interval: '30s'

For more details, refer to the Observability & Monitoring Documentation.

S3 Connector Improvements​

S3 Location Predicate Pruning: The S3 data connector now supports location-based predicate pruning, dramatically reducing data scanned by pushing down location filter predicates to S3 listing operations. For partitioned datasets (e.g., year=2025/month=12/), Spice now skips listing irrelevant partitions entirely, significantly reducing query latency and S3 API costs.

AWS S3 Tables Write Support: Full read/write capability for AWS S3 Tables, enabling direct integration with AWS's managed table format for S3. Use standard SQL INSERT INTO to write data.

For more details, refer to the S3 Data Connector Documentation and Glue Data Connector Documentation.

Faster Distributed Query Execution​

Distributed query planning and execution have been significantly improved:

  • Fixed executor registration in cluster mode for more reliable distributed deployments
  • Improved hostname resolution for Flight server binding, enabling better executor discovery
  • Distributed accelerator registration: Data accelerators now properly register in distributed mode
  • Optimized query planning: DistributeFileScanOptimizer improvements for faster planning with large datasets

For more details, refer to the Distributed Query Documentation.

Search Improvements​

Search capabilities have been improved with several performance and reliability enhancements:

  • Fixed FTS query blocking: Full-text search queries no longer block unnecessarily, improving query responsiveness
  • Optimized vector index operations: Eliminated unnecessary list_vectors calls for better performance
  • Improved limit pushdown: IndexerExec now properly handles limit pushdown for more efficient searches

For more details, refer to the Search Documentation.

Security Hardening​

Multiple security improvements have been implemented:

  • SQL Identifier Quoting: Hardened SQL identifier quoting across all database connectors (PostgreSQL, MySQL, DuckDB, etc.) to prevent SQL injection attacks through table or column names
  • Token Redaction: Sensitive authentication tokens are now fully redacted in debug and error output, preventing accidental credential exposure in logs
  • Path Traversal Prevention: Fixed tar extraction operations to prevent directory traversal vulnerabilities when processing archived files
  • Input Sanitization: Added strict validation for top_n_sample order_by clause parsing to prevent injection attacks
  • Glue Credential Handling: Prevented automatic loading of AWS credentials from environment in Glue connector, ensuring explicit credential configuration

Developer Experience Improvements​

  • Health probe metrics: Added health probe latency metrics for better observability
  • CLI improvements: Fixed .clear history command in the REPL to fully clear persisted history

Contributors​

Breaking Changes​

No breaking changes.

Cookbook Updates​

No major cookbook updates.

The Spice Cookbook includes 82 recipes to help you get started with Spice quickly and easily.

Upgrading​

To upgrade to v1.10.0, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.10.0 image:

docker pull spiceai/spiceai:1.10.0

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai

AWS Marketplace:

🎉 Spice is now available in the AWS Marketplace!

What's Changed​

Changelog​

Spice v1.10.0-rc.1 (Dec 2, 2025)

· 11 min read
David Stancu
David Stancu
Principal Software Engineer at Spice AI

Announcing the release of Spice v1.10.0-rc.1! ⚡

v1.10.0-rc1 is a release candidate for early testing of v1.10 features including an all new caching acceleration mode, tiny_lfu caching policy, a new DynamoDB Streams connector (Preview), improvements to the DynamoDB connector, faster distributed query execution, S3 connector improvements, and security hardening for v1.10.0-stable.

What's New in v1.10.0-rc1​

Caching Acceleration Mode with SWR and TinyLFU​

This release introduces a new caching acceleration mode that implements the stale-while-revalidate (SWR) pattern using Data Accelerators such as DuckDB or Cayenne, enabling queries to return file-persisted cached results immediately while asynchronously refreshing data in the background. Combined with the new TinyLFU cache eviction policy, Spice can now maintain higher cache hit rates while keeping memory usage predictable.

Key Features:

  • Stale-While-Revalidate (SWR): Returns cached data immediately while refreshing in the background
  • Data Accelerator Support: Cached accelerators can persist data to disk using DuckDB, SQLite, or Cayenne file modes.
  • TinyLFU Cache Policy: Probabilistic cache admission policy that maintains high hit rates with minimal overhead
  • Predictable Memory Usage: Configurable memory limits with automatic eviction of less frequently used entries

Example Spicepod.yml configuration:

runtime:
  caching:
    sql_results:
      enabled: true
      eviction_policy: tiny_lfu # default lru

datasets:
  - from: s3://my-bucket/data.parquet
    name: cached_data
    acceleration:
      enabled: true
      engine: duckdb
      mode: file # Persist cache to disk
      refresh_mode: caching
      refresh_check_interval: 10m

For more details, refer to the Data Acceleration Documentation and Caching Documentation.

DynamoDB Streams Data Connector in Preview​

DynamoDB Connector now integrates with DynamoDB Streams which enables real-time streaming with support for both table bootstrapping and continuous change data capture (CDC). This connector automatically detects changes in DynamoDB tables and streams them into Spice for real-time query, search, and LLM-inference.

Key Features:

  • Real-Time CDC: Automatically captures inserts, updates, and deletes from DynamoDB tables
  • Table Bootstrapping: Initial full table load before streaming changes

Example Spicepod.yml configuration:

datasets:
  - from: dynamodb:my_table
    name: orders_stream
    acceleration:
      enabled: true
      refresh_mode: changes

For more details, refer to the DynamoDB Connector Documentation.

Cayenne Accelerator Enhancements​

The Cayenne data accelerator now supports:

  • Sort Columns Configuration: Optimize inserts by pre-sorting data on specified columns for improved query performance

Example Spicepod.yml configuration:

datasets:
  - from: s3://my-bucket/data.parquet
    name: sorted_data
    acceleration:
      enabled: true
      engine: cayenne
      mode: file_create
      params:
        sort_columns: timestamp,region

For more details, refer to the Cayenne Documentation.

S3 Connector Improvements​

S3 Location Predicate Pruning: The S3 data connector now supports location-based predicate pruning, dramatically reducing data scanned by pushing down predicates to S3 listing operations. This optimization is especially effective for partitioned datasets stored in S3.

AWS S3 Tables Write Support: Full read/write capability for AWS S3 Tables, enabling fast integration with AWS's table format for S3.

For more details, refer to the S3 Tables Data Connector Documentation and Glue Data Connection Documentation.

Faster Distributed Query Execution​

Distributed query planning and execution have been significantly improved:

  • Fixed executor registration in cluster mode for more reliable distributed deployments
  • Improved hostname resolution for Flight server binding, enabling better executor discovery
  • Distributed accelerator registration: Data accelerators now properly register in distributed mode
  • Optimized query planning: DistributeFileScanOptimizer improvements for faster planning with large datasets

For more details, refer to the Distributed Query Documentation.

Search Improvements​

Search capabilities have been improved with several performance and reliability enhancements:

  • Fixed FTS query blocking: Full-text search queries no longer block unnecessarily, improving query responsiveness
  • Optimized vector index operations: Eliminated unnecessary list_vectors calls for better performance
  • Improved limit pushdown: IndexerExec now properly handles limit pushdown for more efficient searches

For more details, refer to the Search Documentation.

Security Hardening​

Multiple security improvements have been implemented:

  • SQL identifier quoting: Hardened SQL identifier quoting across all connectors to prevent injection attacks
  • Token redaction: Sensitive tokens are now fully redacted in debug output to prevent credential leakage
  • Path traversal prevention: Fixed tar extraction to prevent path traversal vulnerabilities
  • Input sanitization: Added validation for top_n_sample order_by parsing
  • Improved credential handling: Improved credential management in Glue connector

Developer Experience Improvements​

  • Health probe metrics: Added health probe latency metrics for better observability
  • CLI improvements: Fixed .clear history command in the REPL to fully clear persisted history

Contributors​

Breaking Changes​

No breaking changes.

Cookbook Updates​

No major cookbook updates. The Spice Cookbook still offers 82+ recipes to help you prototype quickly.

Upgrading​

To try v1.10.0-rc1, use one of the following methods:

CLI:

spice upgrade --version 1.10.0-rc1

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.10.0-rc1 image:

docker pull spiceai/spiceai:1.10.0-rc1

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai --version 1.10.0-rc1

AWS Marketplace:

🎉 Spice is available in the AWS Marketplace.

What's Changed​

Changelog​

Spice v1.1.1 (Apr 7, 2025)

· 6 min read
Phillip LeBlanc
Phillip LeBlanc
Co-Founder and CTO of Spice AI

Announcing the release of Spice v1.1.1! 📊

Spice v1.1.1 introduces several key updates, including a new Component Metrics System, improved Delta Data Connector performance, improved MCP tool descriptions, and expanded runtime results caching options. This release also adds detailed MySQL connection pool metrics for better observability. Component Metrics are Prometheus-compatible and accessible via the metrics endpoint.

Highlights v1.1.1​

  • Component Metrics System: A new system for monitoring components, starting with MySQL connection pool metrics. These metrics provide insights into MySQL connection performance and can be selectively enabled in the dataset configuration. Metrics are exposed in Prometheus format via the metrics endpoint.

For more details, see the Component Metrics documentation.

  • Results Caching Enhancements: Added a cache_key_type option for runtime results caching. Options include:
    • plan (Default): Uses the query's logical plan as the cache key. Matches semantically equivalent queries but requires query parsing.
    • sql: Uses the raw SQL string as the cache key. Provides faster lookups but requires exact string matches. Use sql for predictable queries without dynamic functions like NOW().

Example spicepod.yaml configuration:

runtime:
  results_cache:
    enabled: true
    cache_max_size: 128MiB
    cache_key_type: sql # Use SQL for the results cache key
    item_ttl: 1s

For more details, see the runtime configuration documentation.

  • Delta Data Connector: Improved scan performance for faster query performance.

  • MCP Tools: Improved descriptions for built-in MCP tools to improve usability.

  • MySQL Component Metrics: Added detailed metrics for monitoring MySQL connections, such as connection count and pool activity.

Example spicepod.yaml configuration:

datasets:
  - from: mysql:my_table
    name: my_dataset
    metrics:
      - name: connection_count
        enabled: true
      - name: connections_in_pool
        enabled: true
      - name: active_wait_requests
        enabled: true
    params:
      mysql_host: localhost
      mysql_tcp_port: 3306
      mysql_user: root
      mysql_pass: ${secrets:MYSQL_PASS}

For more details, see the MySQL Data Connector documentation.

  • spice.js SDK: The spice.js SDK has been updated to v2.0.1 and includes several important security updates.

New Contributors 🎉​

Contributors​

Breaking Changes​

No breaking changes in this release.

Cookbook Updates​

The Spice Cookbook now includes 65 recipes to help you get started with Spice quickly and easily.

Upgrading​

To upgrade to v1.1.1, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.1.1 image:

docker pull spiceai/spiceai:1.1.1

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai

What's Changed​

Dependencies​

  • No major dependency changes.

Changelog​

- fix: Testoperator DuckDB, SQLite, Postgres, Spicecloud by [@peasee](https://github.com/peasee) in [#5190](https://github.com/spiceai/spiceai/pull/5190)
- Update Helm Chart and SECURITY.md to v1.1.0 by [@lukekim](https://github.com/lukekim) in [#5223](https://github.com/spiceai/spiceai/pull/5223)
- Update version.txt to v1.1.1-unstable by [@lukekim](https://github.com/lukekim) in [#5224](https://github.com/spiceai/spiceai/pull/5224)
- Update Cargo.lock to v1.1.1-unstable by [@lukekim](https://github.com/lukekim) in [#5225](https://github.com/spiceai/spiceai/pull/5225)
- Add tests for `verify_schema_source_path` in `ListingTableConnector` by [@phillipleblanc](https://github.com/phillipleblanc) in [#5221](https://github.com/spiceai/spiceai/pull/5221)
- Reduce noise from debug logging by [@phillipleblanc](https://github.com/phillipleblanc) in [#5227](https://github.com/spiceai/spiceai/pull/5227)
- Improve `openai_test_chat_messages` integration test reliability by [@Sevenannn](https://github.com/Sevenannn) in [#5222](https://github.com/spiceai/spiceai/pull/5222)
- Verify the checkpoints existence before shutting down runtime in integration tests directly querying checkpoint by [@Sevenannn](https://github.com/Sevenannn) in [#5232](https://github.com/spiceai/spiceai/pull/5232)
- Fix CORS support for json content-type api by [@sgrebnov](https://github.com/sgrebnov) in [#5241](https://github.com/spiceai/spiceai/pull/5241)
- Fix ModelGradedScorer error: The 'metadata' parameter is only allowed when 'store' is enabled. by [@sgrebnov](https://github.com/sgrebnov) in [#5231](https://github.com/spiceai/spiceai/pull/5231)
- fix: Use `pulls-with-spice-action` and switch to `spiceai-macos` runners by [@peasee](https://github.com/peasee) in [#5238](https://github.com/spiceai/spiceai/pull/5238)
- Use v1.0.3 pulls with spice action by [@lukekim](https://github.com/lukekim) in [#5244](https://github.com/spiceai/spiceai/pull/5244)
- feat: Build ODBC binaries, run testoperator on ODBC by [@peasee](https://github.com/peasee) in [#5237](https://github.com/spiceai/spiceai/pull/5237)
- Bump timeout for several integration test runtime load_components & readiness check by [@Sevenannn](https://github.com/Sevenannn) in [#5229](https://github.com/spiceai/spiceai/pull/5229)
- Validate port is available before binding port for docker container in integration tests by [@Sevenannn](https://github.com/Sevenannn) in [#5248](https://github.com/spiceai/spiceai/pull/5248)
- Update datafusion-table-providers to fix the schema for PostgreSQL materialized views by [@ewgenius](https://github.com/ewgenius) in [#5259](https://github.com/spiceai/spiceai/pull/5259)
- Verify flight server is ready for flight integration tests by [@Sevenannn](https://github.com/Sevenannn) in [#5240](https://github.com/spiceai/spiceai/pull/5240)
- fix: Publish to MinIO inside of matrix on build_and_release by [@peasee](https://github.com/peasee) in [#5258](https://github.com/spiceai/spiceai/pull/5258)
- fix: TPCDS on zero results benchmarks by [@peasee](https://github.com/peasee) in [#5263](https://github.com/spiceai/spiceai/pull/5263)
- Use model as a judge scorer for Financebench by [@sgrebnov](https://github.com/sgrebnov) in [#5264](https://github.com/spiceai/spiceai/pull/5264)
- Fix FinanceBench llm scorer secret name by [@sgrebnov](https://github.com/sgrebnov) in [#5276](https://github.com/spiceai/spiceai/pull/5276)
- Implements support for `runtime.results_cache.cache_key_type` by [@phillipleblanc](https://github.com/phillipleblanc) in [#5265](https://github.com/spiceai/spiceai/pull/5265)
- fix: Testoperator MS SQL, query overrides, dispatcher by [@peasee](https://github.com/peasee) in [#5279](https://github.com/spiceai/spiceai/pull/5279)
- refactor: Delete old benchmarks by [@peasee](https://github.com/peasee) in [#5283](https://github.com/spiceai/spiceai/pull/5283)
- Imporve embedding column parsing performance test by [@Sevenannn](https://github.com/Sevenannn) in [#5268](https://github.com/spiceai/spiceai/pull/5268)
- Add Support for AWS Session Token in S3 Data Connector by [@kczimm](https://github.com/kczimm) in [#5243](https://github.com/spiceai/spiceai/pull/5243)
- Implement Component Metrics system + MySQL connection pool metrics by [@phillipleblanc](https://github.com/phillipleblanc) in [#5290](https://github.com/spiceai/spiceai/pull/5290)
- Add default descriptions to built-in MCP tools by [@lukekim](https://github.com/lukekim) in [#5293](https://github.com/spiceai/spiceai/pull/5293)
- fix: Vector search with cased columns by [@peasee](https://github.com/peasee) in [#5295](https://github.com/spiceai/spiceai/pull/5295)
- Run delta kernel scan in a blocking Tokio thread. by [@phillipleblanc](https://github.com/phillipleblanc) in [#5296](https://github.com/spiceai/spiceai/pull/5296)
- Expose the `mysql_pool_min` and `mysql_pool_max` connection pool parameters by [@phillipleblanc](https://github.com/phillipleblanc) in [#5297](https://github.com/spiceai/spiceai/pull/5297)
- use patched pdf-extract by [@kczimm](https://github.com/kczimm) in [#5270](https://github.com/spiceai/spiceai/pull/5270)

Full Changelog: v1.1.0...v1.1.1