Skip to main content
Evgenii Khramkov
Senior Software Engineer at Spice AI
View all authors

Spice v1.5.0 (July 21, 2025)

· 14 min read
Evgenii Khramkov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.5.0! 🔍

Spice v1.5.0 brings major upgrades to search and retrieval. It introduces native support for Amazon S3 Vectors, enabling petabyte scale vector search directly from S3 vector buckets, alongside SQL-integrated vector and tantivy-powered full-text search, partitioning for DuckDB acceleration, and automated refreshes for search indexes and views. It includes the AWS Bedrock Embeddings Model Provider, the Oracle Database connector, and the now-stable Spice.ai Cloud Data Connector, and the upgrade to DuckDB v1.3.2.

What's New in v1.5.0

Amazon S3 Vectors Support: Spice.ai now integrates with Amazon S3 Vectors, launched in public preview on July 15, 2025, enabling vector-native object storage with built-in indexing and querying. This integration supports semantic search, recommendation systems, and retrieval-augmented generation (RAG) at petabyte scale with S3’s durability and elasticity. Spice.ai manages the vector lifecycle—ingesting data, creating embeddings with models like Amazon Titan or Cohere via AWS Bedrock, or others available on HuggingFace, and storing it in S3 Vector buckets.

Spice integration with Amazon S3 Vectors

Example Spicepod.yml configuration for S3 Vectors:

datasets:
- from: s3://my_data_bucket/data/
name: my_vectors
params:
file_format: parquet
acceleration:
enabled: true
vectors:
engine: s3_vectors
params:
s3_vectors_aws_region: us-east-2
s3_vectors_bucket: my-s3-vectors-bucket
columns:
- name: content
embeddings:
- from: bedrock_titan
row_id:
- id

Example SQL query using S3 Vectors:

SELECT *
FROM vector_search(my_vectors, 'Cricket bats', 10)
WHERE price < 100
ORDER BY score

For more details, refer to the S3 Vectors Documentation.

SQL-integrated Search: Vector and BM25-scored full-text search capabilities are now natively available in SQL queries, extending the power of the POST v1/search endpoint to all SQL workflows.

Example Vector-Similarity-Search (VSS) using the vector_search UDTF on the table reviews for the search term "Cricket bats":

SELECT review_id, review_text, review_date, score
FROM vector_search(reviews, "Cricket bats")
WHERE country_code="AUS"
LIMIT 3

Example Full-Text-Search (FTS) using the text_search UDTF on the table reviews for the search term "Cricket bats":

SELECT review_id, review_text, review_date, score
FROM text_search(reviews, "Cricket bats")
LIMIT 3

DuckDB v1.3.2 Upgrade: Upgraded DuckDB engine from v1.1.3 to v1.3.2. Key improvements include support for adding primary keys to existing tables, resolution of over-eager unique constraint checking for smoother inserts, and 13% reduced runtime on TPC-H SF100 queries through extensive optimizer refinements. The v1.2.x release of DuckDB was skipped due to a regression in indexes.

Partitioned Acceleration: DuckDB file-based accelerations now support partition_by expressions, enabling queries to scale to large datasets through automatic data partitioning and query predicate pruning. New UDFs, bucket and truncate, simplify partition logic.

New UDFs useful for partition_by expressions:

  • bucket(num_buckets, col): Partitions a column into a specified number of buckets based on a hash of the column value.
  • truncate(width, col): Truncates a column to a specified width, aligning values to the nearest lower multiple (e.g., truncate(10, 101) = 100).

Example Spicepod.yml configuration:

datasets:
- from: s3://my_bucket/some_large_table/
name: my_table
params:
file_format: parquet
acceleration:
enabled: true
engine: duckdb
mode: file
partition_by: bucket(100, account_id) # Partition account_id into 100 buckets

Full-Text-Search (FTS) Index Refresh: Accelerated datasets with search indexes maintain up-to-date results with configurable refresh intervals.

Example refreshing search indexes on body every 10 seconds:

datasets:
- from: github:github.com/spiceai/docs/pulls
name: spiceai.doc.pulls
params:
github_token: ${secrets:GITHUB_TOKEN}
acceleration:
enabled: true
refresh_mode: full
refresh_check_interval: 10s
columns:
- name: body
full_text_search:
enabled: true
row_id:
- id

Scheduled View Refresh: Accelerated Views now support cron-based refresh schedules using refresh_cron, automating updates for accelerated data.

Example Spicepod.yml configuration:

views:
- name: my_view
sql: SELECT 1
acceleration:
enabled: true
refresh_cron: '0 * * * *' # Every hour

For more details, refer to Scheduled Refreshes.

Multi-column Vector Search: For datasets configured with embeddings on more than one column, POST v1/search and similarity_search perform parallel vector search on each column, aggregating results using reciprocal rank fusion.

Example Spicepod.yml for multi-column search:

datasets:
- from: github:github.com/apache/datafusion/issues
name: datafusion.issues
params:
github_token: ${secrets:GITHUB_TOKEN}
columns:
- name: title
embeddings:
- from: hf_minilm
- name: body
embeddings:
- from: openai_embeddings

AWS Bedrock Embeddings Model Provider: Added support for AWS Bedrock embedding models, including Amazon Titan Text Embeddings and Cohere Text Embeddings.

Example Spicepod.yml:

embeddings:
- from: bedrock:cohere.embed-english-v3
name: cohere-embeddings
params:
aws_region: us-east-1
input_type: search_document
truncate: END
- from: bedrock:amazon.titan-embed-text-v2:0
name: titan-embeddings
params:
aws_region: us-east-1
dimensions: '256'

For more details, refer to the AWS Bedrock Embedding Models Documentation.

Oracle Data Connector: Use from: oracle: to access and accelerate data stored in Oracle databases, deployed on-premises or in the cloud.

Example Spicepod.yml:

datasets:
- from: oracle:"SH"."PRODUCTS"
name: products
params:
oracle_host: 127.0.0.1
oracle_username: scott
oracle_password: tiger

See the Oracle Data Connector documentation.

GitHub Data Connector: The GitHub data connector supports query and acceleration of members, the users of an organization.

Example Spicepod.yml configuration:

datasets:
- from: github:github.com/spiceai/members # General format: github.com/[org-name]/members
name: spiceai.members
params:
# With GitHub Apps (recommended)
github_client_id: ${secrets:GITHUB_SPICEHQ_CLIENT_ID}
github_private_key: ${secrets:GITHUB_SPICEHQ_PRIVATE_KEY}
github_installation_id: ${secrets:GITHUB_SPICEHQ_INSTALLATION_ID}
# With GitHub Tokens
# github_token: ${secrets:GITHUB_TOKEN}

See the GitHub Data Connector Documentation

Spice.ai Cloud Data Connector: Graduated to Stable.

spice-rs SDK Release: The Spice Rust SDK has updated to v3.0.0. This release includes optimizations for the Spice client API, adds robust query retries, and custom metadata configurations for spice queries.

Contributors

Breaking Changes

  • Search HTTP API Response: POST v1/search response payload has changed. See the new API documentation for details.
  • Model Provider Parameter Prefixes: Model Provider parameters use provider-specific prefixes instead of openai_ prefixes (e.g., hf_temperature for HuggingFace, anthropic_max_completion_tokens for Anthropic, perplexity_tool_choice for Perplexity). The openai_ prefix remains supported for backward compatibility but is deprecated and will be removed in a future release.

Cookbook Updates

The Spice Cookbook now includes 72 recipes to help you get started with Spice quickly and easily.

Upgrading

To upgrade to v1.5.0, download and install the specific binary from github.com/spiceai/spiceai/releases/tag/v1.5.0 or pull the v1.5.0 Docker image (spiceai/spiceai:1.5.0).

What's Changed

Dependencies

Changelog

  • fix: openai model endpoint (#6394) by @Sevenannn in #6394
  • Enable configuring otel endpoint from spice run (#6360) by @Advayp in #6360
  • Enable Oracle connector in default build configuration (#6395) by @sgrebnov in #6395
  • fix llm integraion test (#6398) by @Sevenannn in #6398
  • Promote spice cloud connector to stable quality (#6221) by @Sevenannn in #6221
  • v1.5.0-rc.1 release notes (#6397) by @lukekim in #6397
  • Fix model nsql integration tests (#6365) by @Sevenannn in #6365
  • Fix incorrect UDTF name and SQL query (#6404) by @lukekim in #6404
  • Update v1.5.0-rc.1.md (#6407) by @sgrebnov in #6407
  • Improve error messages (#6405) by @lukekim in #6405
  • build(deps): bump Jimver/cuda-toolkit from 0.2.25 to 0.2.26 (#6388) by @app/dependabot in #6388
  • Upgrade dependabot dependencies (#6411) by @phillipleblanc in #6411
  • Fix projection pushdown issues for document based file connector (#6362) by @Advayp in #6362
  • Add a PartitionedDuckDB Accelerator (#6338) by @kczimm in #6338
  • Use vector_search() UDTF in HTTP APIs (#6417) by @Jeadie in #6417
  • add supported types (#6409) by @kczimm in #6409
  • Enable session time zone override for MySQL (#6426) by @sgrebnov in #6426
  • Acceleration-like indexing for full text search indexes. (#6382) by @Jeadie in #6382
  • Provide error message when partition by expression changes (#6415) by @kczimm in #6415
  • Add support for Oracle Autonomous Database connections (Oracle Cloud) (#6421) by @sgrebnov in #6421
  • prune partitions for exact and in list with and without UDFs (#6423) by @kczimm in #6423
  • Fixes and reenable FTS tests (#6431) by @Jeadie in #6431
  • Upgrade DuckDB to 1.3.2 (#6434) by @phillipleblanc in #6434
  • Fix issue in limit clause for the Github Data connector (#6443) by @Advayp in #6443
  • Upgrade iceberg-rust to 0.5.1 (#6446) by @phillipleblanc in #6446
  • v1.5.0-rc.2 release notes (#6440) by @lukekim in #6440
  • Oracle: add automated TPC-H SF1 benchmark tests (#6449) by @sgrebnov in #6449
  • fix: Update benchmark snapshots (#6455) by @app/github-actions in #6455
  • Preserve ArrowError in arrow_tools::record_batch (#6454) by @mach-kernel in #6454
  • fix: Update benchmark snapshots (#6465) by @app/github-actions in #6465
  • Add option to preinstall Oracle ODPI-C library in Docker image (#6466) by @sgrebnov in #6466
  • Include Oracle connector (federated mode) in automated benchmarks (#6467) by @sgrebnov in #6467
  • Update crates/llms/src/bedrock/embed/mod.rs by @lukekim in #6468
  • v1.5.0-rc.3 release notes (#6474) by @lukekim in #6474
  • Add integration tests for S3 Vectors filters pushdown (#6469) by @sgrebnov in #6469
  • check for indexedtableprovider when finding tables to search on (#6478) by @Jeadie in #6478
  • Parse fully qualified table names in UDTFs (#6461) by @Jeadie in #6461
  • Add integration test for S3 Vectors to cover data update (overwrite) (#6480) by @sgrebnov in #6480
  • Add 'Run all tests' option for models tests and enable Bedrock tests (#6481) by @sgrebnov in #6481
  • Add support for a members table type for the GitHub Data Connector (#6464) by @Advayp in #6464
  • S3 vector data cannot be null (#6483) by @Jeadie in #6483
  • Don't infer FixedSizeList size during indexing vectors. (#6487) by @Jeadie in #6487
  • Add support for retention_sql acceleration param (#6488) by @sgrebnov in #6488
  • Make dataset refresh progress tracing less verbose (#6489) by @sgrebnov in #6489
  • Use RwLock on tantivy index in FullTextDatabaseIndex for update concurrency (#6490) by @Jeadie in #6490
  • Add tests for dataset retention logic and refactor retention code (#6495) by @sgrebnov in #6495
  • Upgade dependabot dependencies (#6497) by @phillipleblanc in #6497
  • Add periodic tracing of data loading progress during dataset refresh (#6499) by @sgrebnov in #6499
  • Promote Oracle Data Connector to Alpha (#6503) by @sgrebnov in #6503
  • Use AWS SDK to provide credentials for Iceberg connectors (#6498) by @phillipleblanc in #6498
  • Add integration tests for partitioning (#6463) by @kczimm in #6463
  • Use top-level table in full-text search JOIN ON (#6491) by @Jeadie in #6491
  • Use accelerated table in vector_search JOIN operations when appropriate (#6516) by @Jeadie in #6516
  • Fix 'additional_column' for quoted columns (fix for qualified columns broke it) (#6512) by @Jeadie in #6512
  • Also use AWS SDK for inferring credentials for S3/Delta/Databricks Delta data connectors (#6504) by @phillipleblanc in #6504
  • Add per-dataset availability monitor configuration (#6482) by @phillipleblanc in #6482
  • Suppress the warning from the AWS SDK if it can't load credentials (#6533) by @phillipleblanc in #6533
  • Change default value of check_availability from default to auto (#6534) by @lukekim in #6534
  • README.md improvements for v1.5.0 (#6539) by @lukekim in #6539
  • Temporary disable s3_vectors_basic (#6537) by @sgrebnov in #6537
  • Ensure binder errors show before query and other (#6374) by @suhuruli in #6374
  • Update spiceai/duckdb-rs -> DuckDB 1.3.2 + index fix (#6496) by @mach-kernel in #6496
  • Update table-providers to latest version with DuckDB fixes (#6535) by @phillipleblanc in #6535
  • S3: default to public access if no auth is provided (#6532) by @sgrebnov in #6532

Spice v1.2.0 (Apr 28, 2025)

· 16 min read
Evgenii Khramkov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.2.0! 🚀

Spice v1.2.0 is a significant update. It upgrades DataFusion to v45 and Arrow to v54. This release brings faster query performance, support for parameterized queries in SQL and HTTP APIs, and the ability to accelerate views. Several bugs have been fixed and dependencies updated for better stability and speed.

DataFusion v45 Highlights

Spice.ai is built on the DataFusion query engine. The v45 release brings:

  • Faster Performance 🚀: DataFusion is now the fastest single-node engine for Apache Parquet files in the clickbench benchmark. Performance improved by over 33% from v33 to v45. Arrow StringView is now on by default, making string and binary data queries much faster, especially with Parquet files.

  • Better Quality 📋: DataFusion now runs over 5 million SQL tests per push using the SQLite sqllogictest suite. There are new checks for logical plan correctness and more thorough pre-release testing.

  • New SQL Functions ✨: Added show functions, to_local_time, regexp_count, map_extract, array_distance, array_any_value, greatest, least, and arrays_overlap.

See the DataFusion 45.0.0 release notes for details.

Spice.ai upgrades to the latest minus one DataFusion release to ensure adequate testing and stability. The next upgrade to DataFusion v46 is planned for Spice v1.3.0 in May.

What's New in v1.2.0

  • Parameterized Queries: Parameterized queries are now supported with the Flight SQL API and HTTP API. Positional and named arguments via $1 and :param syntax are supported, respectively. Logical plans for SQL statements are cached for faster repeated queries.

    Example Cookbook recipes:

    See the API Documentation for additional details.

  • Accelerated Views: Views, not just datasets, can now be accelerated. This provides much better performance for views that perform heavy computation.

    Example spicepod.yaml:

    views:
    - name: accelerated_view
    acceleration:
    enabled: true
    engine: duckdb
    primary_key: id
    refresh_check_interval: 1h
    sql: |
    select * from dataset_a
    union all
    select * from dataset_b

    See the Data Acceleration documentation.

  • Memory Usage Metrics & Configuration: Runtime now tracks memory usage as a metric, and a new runtime memory_limit parameter is available. The memory limit parameter applies specifically to the runtime and should be used in addition to existing memory usage configuration, such as duckdb_memory_limit. Memory usage for queries beyond the memory limit will spill to disk.

    See the Memory Reference for details.

  • New Worker Component: Workers are new configurable compute units in the Spice runtime. They help manage compute across models and tools, handle errors, and balance load. Workers are configured in the workers section of spicepod.yaml.

    Example spicepod.yaml:

    workers:
    - name: round-robin
    description: |
    Distributes requests between 'foo' and 'bar' models in a round-robin fashion.
    models:
    - from: foo
    - from: bar
    - name: fallback
    description: |
    Tries 'bar' first, then 'foo', then 'baz' if earlier models fail.
    models:
    - from: foo
    order: 2
    - from: bar
    order: 1
    - from: baz
    order: 3

    See the Workers Documentation for details.

  • Databricks Model Provider: Databricks models can now be used with from: databricks:model_name.

    Example spicepod.yaml:

    models:
    - from: databricks:llama-3_2_1_1b_instruct
    name: llama-instruct
    params:
    databricks_endpoint: dbc-46470731-42e5.cloud.databricks.com
    databricks_token: ${ secrets:SPICE_DATABRICKS_TOKEN }

See the Databricks model documentation.

  • spice chat CLI Improvements: The spice chat command now supports an optional --temperature parameter. A one-shot chat can also be sent with spice chat <message>.

  • More Type Support: Added support for Postgres JSON type and DuckDB Dictionary type.

  • Other Improvements:

    • New image tags let you pick memory allocators for different use-cases: jemalloc, sysalloc, and mimalloc.
    • Better error handling and logging for chat and model operations.

Contributors

Cookbook Updates

New recipes for:

The Spice Cookbook now includes 68 recipes to help you get started with Spice quickly and easily.

Upgrading

To upgrade to v1.2.0, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.2.0 image:

docker pull spiceai/spiceai:1.2.0

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai

What's Changed

Dependencies

Spice is now built with Rust 1.85.0 and Rust 2024.

Changelog

- Update end_game.md (#5312) by @peasee in https://github.com/spiceai/spiceai/pull/5312
- feat: Add initial testoperator query validation (#5311) by @peasee in https://github.com/spiceai/spiceai/pull/5311
- Update Helm + Prepare for next release (#5317) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5317
- Update spicepod.schema.json (#5319) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5319
- add integration test for reading encrypted PDFs from S3 (#5308) by @kczimm in https://github.com/spiceai/spiceai/pull/5308
- Stop `load_components` during runtime shutdown (#5306) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5306
- Update openapi.json (#5321) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5321
- feat: Implement record batch data validation (#5331) by @peasee in https://github.com/spiceai/spiceai/pull/5331
- Update QA analytics for v1.1.1 (#5320) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5320
- fix: Update benchmark snapshots (#5337) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5337
- Enforce pulls with Spice v1.0.4 (#5339) by @lukekim in https://github.com/spiceai/spiceai/pull/5339
- Upgrade to DataFusion 45, Arrow 54, Rust 1.85 & Edition 2024 (#5334) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5334
- feat: Allow validating testoperator in benchmark workflow (#5342) by @peasee in https://github.com/spiceai/spiceai/pull/5342
- Upgrade `delta_kernel` to 0.9 (#5343) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5343
- deps: Update odbc-api (#5344) by @peasee in https://github.com/spiceai/spiceai/pull/5344
- Fix schema inference for Snowflake tables with large number of columns (#5348) by @ewgenius in https://github.com/spiceai/spiceai/pull/5348
- feat: Update testoperator dispatch for validation, version metric (#5349) by @peasee in https://github.com/spiceai/spiceai/pull/5349
- fix: validate_results not validate (#5352) by @peasee in https://github.com/spiceai/spiceai/pull/5352
- revert to previous pdf-extract; remove test for encrypted pdf support (#5355) by @kczimm in https://github.com/spiceai/spiceai/pull/5355
- Stablize the test `verify_similarity_search_chat_completion` (#5284) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5284
- Turn off `delta_kernel::log_segment` logging and refactor log filtering (#5367) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5367
- Upgrade to DuckDB 1.2.2 (#5375) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5375
- Update Readme - fix broken and outdated links (#5376) by @ewgenius in https://github.com/spiceai/spiceai/pull/5376
- Upgrade dependabot dependencies (#5385) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5385
- fix: Remove IMAP oauth (#5386) by @peasee in https://github.com/spiceai/spiceai/pull/5386
- Bump Helm chart to 1.1.2 (#5389) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5389
- Refactor accelerator registry as part of runtime. (#5318) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5318
- Include `vnd.spiceai.sql/nsql.v1+json` response examples (openapi docs) (#5388) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5388
- docs: Update endgame template with SpiceQA, update qa analytics (#5391) by @peasee in https://github.com/spiceai/spiceai/pull/5391
- Make graceful shutdown timeout configurable (#5358) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5358
- docs: Update release criteria with note on max columns (#5401) by @peasee in https://github.com/spiceai/spiceai/pull/5401
- Update openapi.json (#5392) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5392
- FinanceBench: update scorer instructions and switch scoring model to `gpt-4.1` (#5395) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5395
- feat: Write OTel metrics for testoperator (#5397) by @peasee in https://github.com/spiceai/spiceai/pull/5397
- Update nsql openapi title (#5403) by @ewgenius in https://github.com/spiceai/spiceai/pull/5403
- Track `ai_inferences_count` with used tools flag. Extensible runtime request context. (#5393) by @ewgenius in https://github.com/spiceai/spiceai/pull/5393
- Include newly detected view as changed view (#5408) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5408
- Track used_tools in ai_inferences_with_spice_count as number (#5409) by @ewgenius in https://github.com/spiceai/spiceai/pull/5409
- Update openapi.json (#5406) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5406
- Tweak enforce pulls with Spice (#5411) by @lukekim in https://github.com/spiceai/spiceai/pull/5411
- Allow `flightsql` and `spiceai` connectors to override flight max message size (#5407) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5407
- Retry model graded scorer once on successful, empty response (#5405) by @Jeadie in https://github.com/spiceai/spiceai/pull/5405
- use span task name in 'spice trace' tree, not span_id (#5412) by @Jeadie in https://github.com/spiceai/spiceai/pull/5412
- Rename to `track_ai_inferences_with_spice_count` in all places (#5410) by @ewgenius in https://github.com/spiceai/spiceai/pull/5410
- Update qa_analytics.csv (#5421) by @peasee in https://github.com/spiceai/spiceai/pull/5421
- Remove the filter for the `list_datasets` tool in the AI inferences metric count. (#5417) by @ewgenius in https://github.com/spiceai/spiceai/pull/5417
- fix: Testoperator uses an exact API key for benchmark metric submission (#5413) by @peasee in https://github.com/spiceai/spiceai/pull/5413
- feat: Enable testoperator metrics in workflow (#5422) by @peasee in https://github.com/spiceai/spiceai/pull/5422
- Upgrade mistral.rs (#5404) by @Jeadie in https://github.com/spiceai/spiceai/pull/5404
- Include all FinanceBench documents in benchmark tests (#5426) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5426
- Handle second Ctrl-C to force runtime termination (#5427) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5427
- Add optional `--temperature` parameter for `spice chat` CLI command (#5429) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5429
- Remove `with_runtime_status` from the `RuntimeBuilder` (#5430) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5430
- Fix spice chat error handling (#5433) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5433
- Add more test models to FinanceBench benchmark (#5431) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5431
- support 'from: databricks:model_name' (#5434) by @Jeadie in https://github.com/spiceai/spiceai/pull/5434
- Upgrade Pulls with Spice to v1.0.6 and add concurrency control (#5442) by @lukekim in https://github.com/spiceai/spiceai/pull/5442
- Upgrade DataFusion table providers (#5443) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5443
- Test spice chat in e2e_test_spice_cli (#5447) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5447
- Allow for one-shot chat request using `spice chat <message>` (#5444) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5444
- Enable parallel data sampling for NSQL (#5449) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5449
- Upgrade Go from v1.23.4 to v1.24.2 (#5462) by @lukekim in https://github.com/spiceai/spiceai/pull/5462
- Update PULL_REQUEST_TEMPLATE.md (#5465) by @lukekim in https://github.com/spiceai/spiceai/pull/5465
- Enable captured outputs by default when spiced is started by the CLI (spice run) (#5464) by @lukekim in https://github.com/spiceai/spiceai/pull/5464
- Parameterized queries via Flight SQL API (#5420) by @kczimm in https://github.com/spiceai/spiceai/pull/5420
- fix: Update benchmarks readme badge (#5466) by @peasee in https://github.com/spiceai/spiceai/pull/5466
- delay auth check for binding parameterized queries (#5475) by @kczimm in https://github.com/spiceai/spiceai/pull/5475
- Add support for `?` placeholder syntax in parameterized queries (#5463) by @kczimm in https://github.com/spiceai/spiceai/pull/5463
- enable task name override for non static span names (#5423) by @Jeadie in https://github.com/spiceai/spiceai/pull/5423
- Allow parameter queries with no parameters (#5481) by @kczimm in https://github.com/spiceai/spiceai/pull/5481
- Support unparsing UNION for distinct results (#5483) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5483
- add rust-toolchain.toml (#5485) by @kczimm in https://github.com/spiceai/spiceai/pull/5485
- Add parameterized query support to the HTTP API (#5484) by @kczimm in https://github.com/spiceai/spiceai/pull/5484
- E2E test for spice chat <message> behavior (#5451) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5451
- Renable and fix huggingface models integration tests (#5478) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5478
- Update openapi.json (#5488) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5488
- feat: Record memory usage as a metric (#5489) by @peasee in https://github.com/spiceai/spiceai/pull/5489
- fix: update dispatcher to run all benchmarks, rename metric, update spicepods, add scale factor (#5500) by @peasee in https://github.com/spiceai/spiceai/pull/5500
- Fix ILIKE filters support (#5502) by @ewgenius in https://github.com/spiceai/spiceai/pull/5502
- fix: Update test spicepod locations and names (#5505) by @peasee in https://github.com/spiceai/spiceai/pull/5505
- fix: Update benchmark snapshots (#5508) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5508
- fix: Update benchmark snapshots (#5512) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5512
- Fix Delta Lake bug for: Found unmasked nulls for non-nullable StructArray field "predicate" (#5515) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5515
- fix: working directory for duckdb e2e test spicepods (#5510) by @peasee in https://github.com/spiceai/spiceai/pull/5510
- Tweaks to README.md (#5516) by @lukekim in https://github.com/spiceai/spiceai/pull/5516
- Cache logical plans of SQL statements (#5487) by @kczimm in https://github.com/spiceai/spiceai/pull/5487
- Fix `content-type: application/json` (#5517) by @Jeadie in https://github.com/spiceai/spiceai/pull/5517
- Validate postgres results in testoperator dispatch (#5504) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5504
- fix: Update benchmark snapshots (#5511) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5511
- Fix results cache by SQL with prepared statements (#5518) by @kczimm in https://github.com/spiceai/spiceai/pull/5518
- Add initial support for views acceleration (#5509) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5509
- fix: Update benchmark snapshots (#5527) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5527
- Support switching the memory allocator Spice uses via `alloc-*` features. (#5528) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5528
- fix: Update benchmark snapshots (#5525) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5525
- Add test spicepod for tpch mysql-duckdb[file acceleration] (#5521) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5521
- Fix nightly arm build - change tag `-default` to `-models` (#5529) by @ewgenius in https://github.com/spiceai/spiceai/pull/5529
- LLM router via `worker` spicepod component (#5513) by @Jeadie in https://github.com/spiceai/spiceai/pull/5513
- Apply Spice advanced acceleration logic and params support to accelerated views (#5526) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5526
- Enable DatasetCheckpoint logic for accelerated views (#5533) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5533
- Fix public '.model' name for router workers (#5535) by @Jeadie in https://github.com/spiceai/spiceai/pull/5535
- feat: Add Runtime memory limit parameter (#5536) by @peasee in https://github.com/spiceai/spiceai/pull/5536
- For fallback worker, check first item in `chat/completion` stream. (#5537) by @Jeadie in https://github.com/spiceai/spiceai/pull/5537
- Move rate limit check to after parameterized query binding (#5540) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5540
- Update spicepod.schema.json (#5545) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5545
- Accelerate views: refresh_on_startup, ready_state, jitter params support (#5547) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5547
- Add integration test for accelerated views (#5550) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5550
- Don't install make or expect on spiceai-macos runners (#5554) by @lukekim in https://github.com/spiceai/spiceai/pull/5554
- `event_stream` crate for emitting events from tracing::Span; used in v1/chat/completions streaming. (#5474) by @Jeadie in https://github.com/spiceai/spiceai/pull/5474
- Fix typo in method (#5559) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5559
- Run test operator every day and current and previous commits (#5557) by @lukekim in https://github.com/spiceai/spiceai/pull/5557
- Add aws_allow_http parameter for delta lake connector (#5541) by @Sevenannn in https://github.com/spiceai/spiceai/pull/5541
- feat: Add branch name to metric dimensions in testoperator (#5563) by @peasee in https://github.com/spiceai/spiceai/pull/5563
- fix: Update the tpch benchmark snapshots for: ./test/spicepods/tpch/sf1/federated/odbc[databricks].yaml (#5565) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5565
- fix: Split scheduled dispatch into a separate job (#5567) by @peasee in https://github.com/spiceai/spiceai/pull/5567
- fix: Use outputs.SPICED_COMMIT (#5568) by @peasee in https://github.com/spiceai/spiceai/pull/5568
- fix: Use refs in testoperator dispatch instead of commits (#5569) by @peasee in https://github.com/spiceai/spiceai/pull/5569
- fix: actions/checkout ref does not take a full ref (#5571) by @peasee in https://github.com/spiceai/spiceai/pull/5571
- fix: Testoperator dispatch (#5572) by @peasee in https://github.com/spiceai/spiceai/pull/5572
- Respect `update-snapshots` when running all benchmarks manually (#5577) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5577
- Use FETCH_HEAD instead of ${{ inputs.ref }} to list commits in setup_spiced (#5579) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5579
- Add additional test scenarios for benchmarks (#5582) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5582
- fix: Update the tpch benchmark snapshots for: test/spicepods/tpch/sf1/accelerated/databricks[delta_lake]-duckdb[file].yaml (#5590) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5590
- fix: Update the tpch benchmark snapshots for: test/spicepods/tpch/sf1/accelerated/mysql-duckdb[file].yaml (#5591) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5591
- Fix Snowflake data connector rows ordering (#5599) by @sgrebnov in https://github.com/spiceai/spiceai/pull/5599
- fix: Update benchmark snapshots (#5595) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5595
- fix: Update the tpch benchmark snapshots for: test/spicepods/tpch/sf1/accelerated/databricks[delta_lake]-arrow.yaml (#5594) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5594
- fix: Update benchmark snapshots (#5589) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5589
- fix: Update benchmark snapshots (#5583) by @app/github-actions in https://github.com/spiceai/spiceai/pull/5583
- Downgrade DuckDB to 1.1.3 (#5607) by @phillipleblanc in https://github.com/spiceai/spiceai/pull/5607
- Add prepared statement integration tests (#5544) by @kczimm in https://github.com/spiceai/spiceai/pull/5544

Full Changelog: v1.1.2...v1.2.0

Spice v1.0-rc.5 (Jan 13, 2025)

· 9 min read
Evgenii Khramkov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.0-rc.5 🛠️

Spice v1.0.0-rc.5 is the fifth release candidate for the first major version of Spice.ai OSS. This release focuses production readiness and critical bug fixes. In addition, a new DynamoDB data connector has been added along with automatic detection for GPU acceleration when running Spice using the CLI.

Highlights in v1.0-rc.5

  • Automatic GPU Acceleration Detection: Automatically detect and utilize GPU acceleration when running by CLI. Install AI components locally using the CLI command spice install ai. Currently supports NVIdia CUDA and Apple Metal (M-series).

  • DynamoDB Data Connector: Query AWS DynamoDB tables using SQL with the new DynamoDB Data Connector.

datasets:
- from: dynamodb:users
name: users
params:
dynamodb_aws_region: us-west-2
dynamodb_aws_access_key_id: ${secrets:aws_access_key_id}
dynamodb_aws_secret_access_key: ${secrets:aws_secret_access_key}
acceleration:
enabled: true
sql> describe users;
+----------------+-----------+-------------+
| column_name | data_type | is_nullable |
+----------------+-----------+-------------+
| created_at | Utf8 | YES |
| date_of_birth | Utf8 | YES |
| email | Utf8 | YES |
| account_status | Utf8 | YES |
| updated_at | Utf8 | YES |
| full_name | Utf8 | YES |
| ... |
+----------------+-----------+-------------+
  • File Data Connector: Graduated to Stable.

  • Dremio Data Connector: Graduated to Release Candidate (RC).

  • Spice.ai, Spark, and Snowflake Data Connectors: Graduated to Beta.

Dependencies

No major dependency changes.

Contributors

  • @Jeadie
  • @phillipleblanc
  • @ewgenius
  • @peasee
  • @Sevenannn
  • @lukekim

What's Changed

* Update acknowledgements by @github-actions in https://github.com/spiceai/spiceai/pull/4190
* Ensure non-nullity of primary keys in `MemTable`; check validity of initial data. by @Jeadie in https://github.com/spiceai/spiceai/pull/4158
* Bump version to v1.0.0 stable by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4191
* Fix metal + models download by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4193
* Update spice.ai connector beta roadmap by @ewgenius in https://github.com/spiceai/spiceai/pull/4194
* feat: verify on zero results snapshots by @peasee in https://github.com/spiceai/spiceai/pull/4195
* Add throughput test module to `test-framework` by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4196
* Update Spice.ai TPCH snapshots by @ewgenius in https://github.com/spiceai/spiceai/pull/4202
* Replace all usage of `lazy_static!` with `LazyLock` by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4199
* Fix model + metal download by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4200
* Run Clickbench for Dremio by @Sevenannn in https://github.com/spiceai/spiceai/pull/4138
* Update openapi.json by @github-actions in https://github.com/spiceai/spiceai/pull/4205
* Fix the typo in connector stable criteria by @Sevenannn in https://github.com/spiceai/spiceai/pull/4213
* feat: Add throughput test example by @peasee in https://github.com/spiceai/spiceai/pull/4214
* feat: calculate throughput test query percentiles by @peasee in https://github.com/spiceai/spiceai/pull/4215
* feat: Add throughput test to actions by @peasee in https://github.com/spiceai/spiceai/pull/4217
* Implement DynamoDB Data Connector by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4218
* 1.0 doc updates by @lukekim in https://github.com/spiceai/spiceai/pull/4181
* Improve clarity and concison of use-cases by @lukekim in https://github.com/spiceai/spiceai/pull/4220
* Remove macOS Intel build by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4221
* fix: Test operator throughput test workflow by @peasee in https://github.com/spiceai/spiceai/pull/4222
* DynamoDB: Automatically load AWS credentials from IAM roles if access key not provided by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4226
* File connector clickbench snapshots results by @ewgenius in https://github.com/spiceai/spiceai/pull/4225
* Spice.ai Catalog Connector by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4204
* feat: Add test framework metrics collection by @peasee in https://github.com/spiceai/spiceai/pull/4227
* Add badges for build/test status on README.md by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4228
* Release Dremio to RC by @Sevenannn in https://github.com/spiceai/spiceai/pull/4224
* feat: Add more test spicepods by @peasee in https://github.com/spiceai/spiceai/pull/4229
* feat: Add load test to testoperator by @peasee in https://github.com/spiceai/spiceai/pull/4231
* Add TSV format to all `object_store`-based connectors by @Jeadie in https://github.com/spiceai/spiceai/pull/4192
* Move test-framework to dev-dependencies for Runtime by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4230
* Document limitation for correlated subqueries in TPCH for Spice.ai connector by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4235
* Changes for CUDA by @Jeadie in https://github.com/spiceai/spiceai/pull/4130
* fix: Collect batches from test framework, load test updates by @peasee in https://github.com/spiceai/spiceai/pull/4234
* Suppress opentelemetry_sdk warnings - they aren't useful by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4243
* fix: Set dataset status first, update test framework by @peasee in https://github.com/spiceai/spiceai/pull/4244
* feat: Re-enable defaults on test spicepods by @peasee in https://github.com/spiceai/spiceai/pull/4248
* Add usage for streaming local models; Fix spice chat usage bar TPS expansion by @Jeadie in https://github.com/spiceai/spiceai/pull/4232
* refactor: Use composite testoperator setup, add query overrides by @peasee in https://github.com/spiceai/spiceai/pull/4246
* Enable expand_views_at_output for DF optimizer and transform schema to expanded view types by @ewgenius in https://github.com/spiceai/spiceai/pull/4237
* Add throughput test spicepod for databricks delta mode connector by @Sevenannn in https://github.com/spiceai/spiceai/pull/4241
* Spark data connector - update and enable TPCH and TPCDS benchmarks by @ewgenius in https://github.com/spiceai/spiceai/pull/4240
* Increase the timeout minutes of load test to 10 hours by @Sevenannn in https://github.com/spiceai/spiceai/pull/4254
* Improve partition column counts error for delta table by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4247
* Add e2e test for databricks catalog connector (mode: delta_lake) by @Sevenannn in https://github.com/spiceai/spiceai/pull/4255
* Spark connector integration tests by @ewgenius in https://github.com/spiceai/spiceai/pull/4256
* Run benchmark test with the new test framework by @Sevenannn in https://github.com/spiceai/spiceai/pull/4245
* Configure databricks delta secrets to run load test by @Sevenannn in https://github.com/spiceai/spiceai/pull/4257
* Support `properties` for emitted telemetry by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4249
* feat: Add `ready_wait` test operator workflow input by @peasee in https://github.com/spiceai/spiceai/pull/4259
* Handle 'LargeStringArray' for embedding tables by @Jeadie in https://github.com/spiceai/spiceai/pull/4263
* `llms` tests for alpha/beta model criteria by @Jeadie in https://github.com/spiceai/spiceai/pull/4261
* Configurable runner type for load and throughput tests by @ewgenius in https://github.com/spiceai/spiceai/pull/4262
* Handle NULL partition columns for Delta Lake tables by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4264
* Add integration test for Snowflake by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4266
* Add Snowflake TPCH queries by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4268
* Handle `LargeStringArray` in `v1/search`. by @Jeadie in https://github.com/spiceai/spiceai/pull/4265
* Fix `build_cuda` in Update spiced_docker.yml by @Jeadie in https://github.com/spiceai/spiceai/pull/4269
* Run Snowflake benchmark in GitHub Actions by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4270
* Allow Snowflake query override for CI tests by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4271
* Don't run GPU builds for trunk by @Jeadie in https://github.com/spiceai/spiceai/pull/4272
* Fix InvalidTypeAction not working by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4273
* Add xAI key to llm integration tests by @Jeadie in https://github.com/spiceai/spiceai/pull/4274
* Update openai snapshots by @Jeadie in https://github.com/spiceai/spiceai/pull/4275
* Fix federation bug for correlated subqueries by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4276
* Update end_game.md by @ewgenius in https://github.com/spiceai/spiceai/pull/4278
* Promote Snowflake to Beta by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4277
* Set version to 1.0.0-rc.5 by @ewgenius in https://github.com/spiceai/spiceai/pull/4283
* Update cargo.lock by @ewgenius in https://github.com/spiceai/spiceai/pull/4285
* Update spice.ai data connector snapshots by @ewgenius in https://github.com/spiceai/spiceai/pull/4281
* Promote the Spice.ai Data Connector to Beta by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4282
* Revert change to `integration_models__models__search__openai_chunking_response.snap` by @Jeadie in https://github.com/spiceai/spiceai/pull/4279
* Allow for a subset of build artifacts to be published to minio by @Jeadie in https://github.com/spiceai/spiceai/pull/4280
* Promote File Data Connector to Stable by @ewgenius in https://github.com/spiceai/spiceai/pull/4286
* Add Iceberg to Supported Catalogs by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4287
* Update openapi.json by @github-actions in https://github.com/spiceai/spiceai/pull/4289
* Fix Spark benchmark credentials, add back overrides by @ewgenius in https://github.com/spiceai/spiceai/pull/4295
* Promote Spark Data Connector to Beta by @ewgenius in https://github.com/spiceai/spiceai/pull/4296
* Add Dremio throughput test spicepod by @Sevenannn in https://github.com/spiceai/spiceai/pull/4233
* Add error message for invalid databricks mode parameter by @Sevenannn in https://github.com/spiceai/spiceai/pull/4299
* Fix pre-release check to look for `build` string by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4300
* Promote databricks catalog connector (mode: delta_lake) to beta by @Sevenannn in https://github.com/spiceai/spiceai/pull/4301
* Properly delegate `load_table` to Rest Catalog by @phillipleblanc in https://github.com/spiceai/spiceai/pull/4303
* Update acknowledgements by @github-actions in https://github.com/spiceai/spiceai/pull/4302
* docs: Update ROADMAP.md by @peasee in https://github.com/spiceai/spiceai/pull/4306
* v1.0.0-rc.5 Release Notes by @ewgenius in https://github.com/spiceai/spiceai/pull/4298

**Full Changelog**: https://github.com/spiceai/spiceai/compare/v1.0.0-rc.4...v1.0.0-rc.5

Resources

Community

Spice.ai started with the vision to make AI easy for developers. We are building Spice.ai in the open and with the community. Reach out on Discord or by email to get involved.