Skip to main content

2 posts tagged with "metal"

View All Tags

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

ยท 7 min read
Evgenii Khramkov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.0-rc.5 ๐Ÿ› ๏ธ

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.5โ€‹

  • 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.

Dependenciesโ€‹

No major dependency changes.

Contributorsโ€‹

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

What's Changedโ€‹

* 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

Resourcesโ€‹

Communityโ€‹

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.

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

ยท 3 min read
Phillip LeBlanc
Co-Founder and CTO of Spice AI

Announcing the release of Spice v0.20-beta ๐Ÿงฉ

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.

Highlights in v0.20.0-betaโ€‹

Data Connectors: The S3, PostgreSQL, MySQL, and GitHub Data Connectors have graduated from beta to release candidate.

Data Accelerators: The Arrow, DuckDB, and SQLite Data Accelerators have graduated from alpha to beta.

Metal and CUDA Support: Added support for Metal (Apple Silicon) and CUDA (NVidia) for AI/ML workloads including embeddings and local LLM inference.

For instructions on compiling a Meta or CUDA binary, see the Installation Docs.

Breaking Changesโ€‹

  • The ODBC Data Connector now requires ODBC drivers specified in connection strings are registered in the system ODBC driver manager.

Example invalid connection string:

DRIVER={/path/to/driver.so};SERVER=localhost;DATABASE=master

Example valid connection string:

DRIVER={My ODBC Driver};SERVER=localhost;DATABASE=master

Where My ODBC Driver is the name of an ODBC driver registered in the ODBC driver manager.

Contributorsโ€‹

  • @ewgenius
  • @peasee
  • @phillipleblanc
  • @sgrebnov
  • @Jeadie
  • @barracudarin
  • @Sevenannn

What's Changedโ€‹

- Update Helm for v0.19.4-beta and add release notes by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3310>
- Update spicepod.schema.json by @github-actions in <https://github.com/spiceai/spiceai/pull/3311>
- `metal` & `cuda` flags for spice by @Jeadie in <https://github.com/spiceai/spiceai/pull/3212>
- Promote postgres connector to RC quality by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3305>
- docs: Update ROADMAP.md by @peasee in <https://github.com/spiceai/spiceai/pull/3322>
- feat: Enable federation for in-memory accelerators by @peasee in <https://github.com/spiceai/spiceai/pull/3325>
- fix: Only allow env files from the current dir by @peasee in <https://github.com/spiceai/spiceai/pull/3327>
- Always read TimezoneTZ from PostgreSQL as UTC by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3330>
- For multi-sink acceleration refreshes, ensure parent table completes before the children. by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3329>
- Update TPC-DS Q49 (Decimal to Float) to match SQLite's type system by @sgrebnov in <https://github.com/spiceai/spiceai/pull/3323>
- Enable parquet pushdown in Spice by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3245>
- Use spice object_store fork to fix S3 ambiguous error by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3304>
- Don't mix commented out queries for s3 connectors and accelerators by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3331>
- Allow only valid WHERE conditions in vector searches by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3335>
- fix: Allow only ODBC profiles by @peasee in <https://github.com/spiceai/spiceai/pull/3324>
- Track how many times an acceleration falls back during initialization by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3339>
- Anthropic model regex and fix tool parsing aggregation bug by @Jeadie in <https://github.com/spiceai/spiceai/pull/3334>
- Upgrade runtime along with CLI on `spice upgrade` by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3341>
- Update upcoming Roadmap by @phillipleblanc in <https://github.com/spiceai/spiceai/pull/3343>
- fix: Prevent acceleration files outside of working directory by @peasee in <https://github.com/spiceai/spiceai/pull/3340>
- Document S3 connector limitations by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3333>
- Update Object Store Patch by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3361>
- Promote SQLite Data Accelerator to Beta by @sgrebnov in <https://github.com/spiceai/spiceai/pull/3365>
- Promote S3 connector to RC quality by @Sevenannn in <https://github.com/spiceai/spiceai/pull/3362>
- Revert "fix: Only allow env files from the current dir" by @peasee in <https://github.com/spiceai/spiceai/pull/3368>
- docs: Fix typo for S3 release status in README.md by @peasee in <https://github.com/spiceai/spiceai/pull/3370>
- Include unnecessary columns pruning step during federated plan creation by @sgrebnov in <https://github.com/spiceai/spiceai/pull/3363>

**Full Changelog**: <https://github.com/spiceai/spiceai/compare/v0.19.4-beta...v0.20.0-beta>

Resourcesโ€‹

Communityโ€‹

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.