Skip to main content

4 posts tagged with "embeddings"

Embeddings related topics and usage

View All Tags

Spice v1.9.1 (Nov 24, 2025)

· 7 min read
Viktor Yershov
Viktor Yershov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.9.1!🔥

v1.9.1 introduces Amazon Bedrock Nova 2 Multimodal embeddings support with high-dimensional vectors up to 3,072 dimensions and purpose-optimized embeddings for semantic search and retrieval operations, DynamoDB timestamp filter pushdown for more efficient append-mode acceleration with configurable time formatting, HTTP Data Connector health probe configuration for improved endpoint validation reliability, and Spice .NET SDK v0.2 with expanded .NET version support and updated gRPC libraries. This release focuses on bug fixes, stability, and performance improvements.

Amazon Bedrock Nova 2 Multimodal embeddings​

Spice now supports the Amazon Nova 2 Multimodal embeddings models via the Bedrock models provider, enabling high-quality text embeddings for semantic search and vector similarity operations. The Nova embeddings model offers configurable dimensions and advanced features like truncation modes and embedding purpose optimization.

Key Features:

  • High-Dimensional Embeddings: Support for up to 3,072 dimensions for rich semantic representations
  • Configurable Truncation: Control how input text is truncated when exceeding token limits (START, END, or NONE)
  • Purpose Optimization: Optimize embeddings for specific use cases (GENERIC_INDEX, GENERIC_RETRIEVAL, or CLASSIFICATION)
  • Multimodal Model: Leverages Amazon's Nova 2 multimodal architecture for consistent embeddings across different content types

Example spicepod.yml configuration:

embeddings:
  - from: bedrock:amazon.nova-2-multimodal-embeddings-v1:0
    name: nova_embeddings
    params:
      dimensions: '3072' # Required: Output dimensions
      truncation_mode: START # Optional: START, END, or NONE (default: NONE)
      embedding_purpose: GENERIC_RETRIEVAL # Optional. GENERIC_INDEX is default

For more details on the embedding parameters and configuration options, refer to the Amazon Nova Embeddings Documentation and the Spice Embeddings Documentation.

DynamoDB Timestamp Filter Pushdown​

The DynamoDB Data Connector now supports timestamp filter pushdown, enabling more efficient append-mode acceleration refreshes by pushing timestamp filters directly to DynamoDB queries. Since DynamoDB stores timestamps as strings rather than native datetime types, this feature includes configurable timestamp formatting to ensure correct parsing and filtering.

Key Features:

  • Filters on timestamp columns are now pushed down to DynamoDB, reducing data transfer and improving query performance
  • Support for Go-style datetime formatting patterns to handle various timestamp string formats
  • Uses ISO 8601 format by default when no custom format is specified

Example spicepod.yml configuration:

datasets:
  - from: dynamodb:sales
    name: sales
    time_column: created_at
    time_format: timestamptz
    params:
      time_format: 2006-01-02T15:04:05.000Z07:00
    acceleration:
      enabled: true
      engine: duckdb
      refresh_mode: append

For more details, refer to the DynamoDB Data Connector Documentation.

HTTP Data Connector Health Probe Configuration​

The HTTP Data Connector now supports configurable health probe paths for endpoint validation. Instead of using a random non-existent path, the system can now validate endpoints using a user-specified path, improving flexibility and reliability for health checks.

Example spicepod.yml configuration:

datasets:
  - from: https://api.tvmaze.com
    name: tvmaze
    params:
      file_format: json
      health_probe: /health-check

For more details, refer to the HTTP Data Connector Documentation.

Spice .NET SDK v0.2​

The Spice .NET SDK has been upgraded with expanded .NET version support, custom User-Agent configuration, and updated gRPC libraries: spice-dotnet v0.2.0. The SDK is available on NuGet.

Key Features:

  • Expanded .NET Support: Now supports .NET Standard 2.0, .NET Core 8.0, 9.0, and 10.0.
  • Custom User-Agent: Configure custom User-Agent headers for client identification and telemetry.
  • Updated gRPC Libraries: Upgraded gRPC dependencies and netstandard for improved performance and reliability

Upgrade Example:

dotnet add package SpiceAI --version 0.2.0

For more details, refer to the .NET SDK Documentation.

Additional Improvements & Bug Fixes​

  • Reliability: Fixed view loading to respect topological order, preventing dependency resolution errors.
  • Reliability: Migrated from deprecated trust_dns_resolver to hickory_resolver for improved DNS resolution reliability.
  • Security: Fixed arbitrary file access vulnerability during archive extraction ("Zip Slip") to prevent potential security exploits.
  • Distributed Query: Fixed object store initialization across scheduler/executor gap, improving reliability for distributed query execution.
  • Distributed Query: Optimized query routing by preventing runtime.* schema queries from being sent to the scheduler, improving performance for metadata queries.
  • Performance: Added Blake3 and xxHash support with xxh3_64 as the default caching hashing algorithm for improved cache and query performance.
  • Performance: Optimized default Zstd compression level to 6 for better balance between compression ratio and speed.
  • UX: Improved dataset loading output with clearer progress indicators and status messages.

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 v1.9.1, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.9.1 image:

docker pull spiceai/spiceai:1.9.1

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​

  • fix integration tests: order by the query to make snapshots deterministic by @phillipleblanc in #8198
  • Add health probe override by @lukekim in #8236
  • Use Moka optionally_get_with for SWR single-in-flight semantics by @lukekim in #8231
  • fix: Arbitrary file access during archive extraction ("Zip Slip") by @phillipleblanc in #8242
  • Migrate trust_dns_resolver to hickory_resolver by @phillipleblanc in #8243
  • fix: Deny assert macros in non-test code by @peasee in #8223
  • Distributed query: Object store initialization across scheduler/executor gap, misc bugfixes & improvements by @mach-kernel in #8009
  • Add Blake3, enable xxHash, set xxh3_64 as default, add bench by @lukekim in #8157
  • Make cache zstd default compression level 6 by @lukekim in #8234
  • Use seed for xxh3 by @lukekim in #8232
  • DynamoDB Timestamp Filter Pushdown by @krinart in #8235
  • Add ready_wait for mongo-arrow benchmarks by @krinart in #8246
  • Add support for amazon.nova-2-multimodal-embeddings-v1:0 by @Jeadie in #8225
  • Improve the output of dataset loading by @lukekim in #8256
  • Load views in topological order by @lukekim in #8255
  • Distributed query: Do not send runtime.* schema queries to scheduler by @mach-kernel in #8271
  • Remove input length check for Nova model. by @Jeadie in #8270

Spice v1.7.0 (Sep 23, 2025)

· 21 min read
Sergei Grebnov
Sergei Grebnov
Senior Software Engineer at Spice AI

Announcing the release of Spice v1.7.0! ⚡

Spice v1.7.0 upgrades to DataFusion v49 for improved performance and query optimization, introduces real-time full-text search indexing for CDC streams, EmbeddingGemma support for high-quality embeddings, new search table functions powering the /v1/search API, embedding request caching for faster and cost-efficient search and indexing, and OpenAI Responses API tool calls with streaming. This release also includes numerous bug fixes across CDC streams, vector search, the Kafka Data Connector, and error reporting.

What's New in v1.7.0​

DataFusion v49 Highlights​

DataFusion Clickbench Performance Graph Source: DataFusion 49.0.0 Release Blog.

Performance Improvements 🚀

  • Equivalence System Upgrade: Faster planning for queries with many columns, enabling more sophisticated sort-based optimizations.
  • Dynamic Filters & TopK Pushdown: Queries with ORDER BY and LIMIT now use dynamic filters and physical filter pushdown, skipping unnecessary data reads for much faster top-k queries.
  • Compressed Spill Files: Intermediate files written during sort/group spill to disk are now compressed, reducing disk usage and improving performance.
  • WITHIN GROUP for Ordered-Set Aggregates: Support for ordered-set aggregate functions (e.g., percentile_disc) with WITHIN GROUP.
  • REGEXP_INSTR Function: Find regex match positions in strings.

Spice Runtime Highlights​

EmbeddingGemma Support: Spice now supports EmbeddingGemma, Google's state-of-the-art embedding model for text and documents. EmbeddingGemma provides high-quality, efficient embeddings for semantic search, retrieval, and recommendation tasks. You can use EmbeddingGemma via HuggingFace in your Spicepod configuration:

Example spicepod.yml snippet:

embeddings:
  - from: huggingface:huggingface.co/google/embeddinggemma-300m
    name: embeddinggemma
    params:
      hf_token: ${secrets:HUGGINGFACE_TOKEN}

Learn more about EmbeddingGemma in the official documentation.

POST /v1/search API Use Search Table Functions: The /v1/search API now uses the new text_search and vector_search Table Functions for improved performance.

Embedding Request Caching: The runtime now supports caching embedding requests, reducing latency and cost for repeated content and search requests.

Example spicepod.yml snippet:

runtime:
  caching:
    embeddings:
      enabled: true
      max_size: 128mb
      item_ttl: 5s

See the Caching documentation for details.

Real-Time Indexing for Full Text Search: Full Text search indexing is now supported for connectors that enable real-time changes, such as Debezium CDC streams. Adding a full-text index on a column with refresh_mode: changes works as it does for full/append-mode refreshes, enabling instant search on new data.

Example spicepod.yml snippet:

datasets:
  - from: debezium:cdc.public.question
    name: questions
    acceleration:
      enabled: true
      engine: duckdb
      primary_key: id
      refresh_mode: changes # Use 'changes'
    params: *kafka_params
    columns:
      - name: title
        full_text_search:
          enabled: true # Enable full-text-search indexing
          row_id:
            - id

OpenAI Responses API Tool Calls with Streaming: The OpenAI Responses API now supports tool calls with streaming, enabling advanced model interactions such as web_search and code_interpreter with real-time response streaming. This allows you to invoke OpenAI-hosted tools and receive results as they are generated.

Learn more in the OpenAI Model Provider documentation.

Runtime Output Level Configuration: You can now set the output_level parameter in the Spicepod runtime configuration to control logging verbosity in addition to the existing CLI and environment variable support. Supported values are info, verbose, and very_verbose. The value is applied in the following priority: CLI, environment variables, then YAML configuration.

Example spicepod.yml snippet:

runtime:
  output_level: info # or verbose, very_verbose

For more details on configuring output level, see the Troubleshooting documentation.

Bug Fixes​

Several bugs and issues have been resolved in this release, including:

  • CDC Streams: Fixed issues where refresh_mode: changes could prevent the Spice runtime from becoming Ready, and improved support for full-text indexing on CDC streams.
  • Vector Search: Fixed bugs where vector search HTTP pipeline could not find more than one IndexedTableProvider, and resolved errors with field mismatches in vector_search UDTF.
  • Kafka Integration: Improved Kafka schema inference with configurable sample size, improved consumer group persistence for SQLite and Postgres accelerations, and added cooperative mode support.
  • Perplexity Web Search: Fixed bug where Perplexity web search sometimes used incorrect query schema (limit).
  • Databricks: Fixed issue with unparsing embedded columns.
  • Error Reporting: ThrottlingException is now reported correctly instead of as InternalError.
  • Iceberg Data Connector: Added support for LIMIT pushdown.
  • Amazon S3 Vectors: Fixed ingestion issues with zero-vectors and improved handling when vector index is full.
  • Tracing: Fixed vector search tracing to correctly report SQL status.

Contributors​

New Contributors​

Breaking Changes​

No breaking changes.

Cookbook Updates​

The Spice Cookbook includes 78 recipes to help you get started with Spice quickly and easily.

Upgrading​

To upgrade to v1.7.0, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.7.0 image:

docker pull spiceai/spiceai:1.7.0

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​

Dependencies​

Changelog​

Spice v1.5.1 (July 28, 2025)

· 5 min read
Jack Eadie
Jack Eadie
Token Plumber at Spice AI

Announcing the release of Spice v1.5.1! 🔑

Spice v1.5.1 expands the GitHub data connector to include pull-request comments, adds a configurable rate limiting for AWS Bedrock embedding models, expands partition pruning with inequality operators, and adds client-supplied cache keys for granular caching control in the HTTP and Arrow Flight SQL APIs.

What's New in v1.5.1​

GitHub Data Connector Pull Request Comments: Configure GitHub pulls datasets to include comments.

Example Spicepod.yaml:

datasets:
  - from: github:github.com/spiceai/spiceai/pulls
    name: spiceai.pulls
    params:
      github_include_comments: all # 'review', 'discussion', or 'none'. Defaults to 'none'.
      github_max_comments_fetched: '25' # Defaults to 100
      # ...

For details, see the GitHub Data Connector documentation.

AWS Bedrock Embedding Models Invocation Control: Improved rate limiting control for AWS Bedrock embedding models with max_concurrent_invocations configuration.

embeddings:
  - from: bedrock:cohere.embed-english-v3
    name: cohere-embeddings
    params:
      max_concurrent_invocations: '41'
      # ...

For details, see the AWS Bedrock Embeddings Model Provider documentation.

Improved Query Partitioning: Expanded partition pruning support with additional inequality operators (e.g. >, >=, <, <=).

For details, see the Query Partitioning documentation.

Client-Supplied Cache Keys: Support for a new Spice-Cache-Key header/metadata-key in the HTTP and Arrow Flight SQL query APIs to for fine-grained client-side caching control.

Example HTTP API usage:

$ curl -vvS -XPOST http://localhost:8090/v1/sql \
-H"spice-cache-key: 1851400_20170216_north_america" \
-d "select * from scihub_journals_accessed
    where user_id = '1851400'
      and date_trunc('DAY', timestamp) = '2017-02-16'
      and city = 'New York';"

Example Response:

< HTTP/1.1 200 OK
< content-type: application/json
< x-cache: Hit from spiceai
< results-cache-status: HIT
< vary: Spice-Cache-Key
< vary: origin, access-control-request-method, access-control-request-headers
< content-length: 604
< date: Wed, 23 Jul 2025 20:26:12 GMT
<
[{
"timestamp": "2017-02-16 09:55:06",
"doi": "10.1155/2012/650929",
"ip_identifier": 1000856,
"user_id": 1851400,
"country": "United States",
"city": "New York",
"longitude": 40.7830603,
"latitude": -73.9712488
},
...
]

For details, see the Cache Control documentation.

Contributors​

New Contributors​

Breaking Changes​

  • N/A

Cookbook Updates​

No new recipes added in this release.

The Spice Cookbook includes 74 recipes to help you get started with Spice quickly and easily.

Upgrading​

To upgrade to v1.5.1, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.5.1 image:

docker pull spiceai/spiceai:1.5.1

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai

What's Changed​

Dependencies​

No major dependency updates.

Changelog​

  • Fix refresh via Api when dataset is already accelerated and no refresh interval is set by @sgrebnov in #6549
  • Add support for custom GraphQL unnesting behavior by @Advayp in #6540
  • Regex Update to disallow hyphens dataset names by @varunguleriaCodes in #6383
  • Enforce max limit on comments fetched per PR by @Advayp in #6580
  • Fix accelerated refresh issue by @Advayp in #6590
  • Enable configurations of max invocations for Bedrock models by @Advayp in #6592
  • Client-supplied cache keys (Spice-Cache-Key) by @mach-kernel in #6579
  • Improved partition pruning by @kczimm in #6582
  • Fix retention filter when both retention_sql and period are set by @sgrebnov in #6595
  • Initial support for PR comments by @Advayp in #6569
  • chore: Update croner by @peasee in #6547
  • fix databricks streaming for Claude model by @peasee in #6601
  • Remove FullTextUDTFAnalyzerRule and move FTS code into search crate by @jeadie in #6596
  • Remove download of legacy sentence transformers config by @jeadie in #6605
  • re-add snapshot tests by @jeadie
  • Embedding column config to support client-specified vector sizes by @mach-kernel in #6610
  • Fix mismatch in columns for the GitHub PR table type by @Advayp in #6616
  • bump version to 1.5.1 by @phillipleblanc
  • fix issues with cherry-picking by @jeadie
  • Add integration tests for GitHub PRs with comments by @Advayp in #6581
  • Add view name to view creation errors by @lukekim in #6611
  • CDC: Compute embeddings on ingest by @mach-kernel in #6612

Spice v1.2.2 (May 13, 2025)

· 5 min read
Jack Eadie
Jack Eadie
Token Plumber at Spice AI

Announcing the release of Spice v1.2.2! 🌟

Spice v1.2.2 introduces support for Databricks Mosaic AI model serving and embeddings, alongside the existing Databricks catalog and dataset integrations. It adds configurable service ports in the Helm chart and resolves several bugs to improve stability and performance.

Highlights in v1.2.2​

  • Databricks Model & Embedding Provider: Spice integrates with Databricks Model Serving for models and embeddings, enabling secure access via machine-to-machine (M2M) OAuth authentication with service principal credentials. The runtime automatically refreshes tokens using databricks_client_id and databricks_client_secret, ensuring uninterrupted operation. This feature supports Databricks-hosted large language models and embedding models.

    models:
      - from: databricks:databricks-llama-4-maverick
        name: llama-4-maverick
        params:
          databricks_endpoint: dbc-46470731-42e5.cloud.databricks.com
          databricks_client_id: ${secrets:DATABRICKS_CLIENT_ID}
          databricks_client_secret: ${secrets:DATABRICKS_CLIENT_SECRET}

    embeddings:
      - from: databricks:databricks-gte-large-en
        name: gte-large-en
        params:
          databricks_endpoint: dbc-42424242-4242.cloud.databricks.com
          databricks_client_id: ${secrets:DATABRICKS_CLIENT_ID}
          databricks_client_secret: ${secrets:DATABRICKS_CLIENT_SECRET}

    For detailed setup instructions, refer to the Databricks Model Provider documentation.

  • Configurable Helm Chart Service Ports: The Helm chart now supports custom ports for flexible network configurations for deployments. Specify non-default ports in your Helm values file.

  • Resolved Issues:

    • MCP Nested Tool Calling: Fixed a bug preventing nested tool invocation when Spice operates as the MCP server federating to MCP clients.

    • Dataset Load Concurrency: Corrected a failure to respect the dataset_load_parallelism setting during dataset loading.

    • Acceleration Hot-Reload: Addressed an issue where changes to acceleration enable/disable settings were not detected during hot reload of Spicepod.yaml.

Contributors​

Breaking Changes​

No breaking changes.

Cookbook Updates​

Updated cookbooks:

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

Upgrading​

To upgrade to v1.2.2, use one of the following methods:

CLI:

spice upgrade

Homebrew:

brew upgrade spiceai/spiceai/spice

Docker:

Pull the spiceai/spiceai:1.2.2 image:

docker pull spiceai/spiceai:1.2.2

For available tags, see DockerHub.

Helm:

helm repo update
helm upgrade spiceai spiceai/spiceai

What's Changed​

Dependencies​

  • No major dependency changes.

Changelog​

- Update spark-connect-rs to override user agent string by @ewgenius in https://github.com/spiceai/spice/pull/5798
- Merge pull request by @ewgenius in https://github.com/spiceai/spice/pull/5796
- Pass the default user agent string to the Databricks Spark, Delta, and Unity clients by @ewgenius in https://github.com/spiceai/spice/pull/5717
- bump to 1.2.2 by @Jeadie in https://github.com/spiceai/spice/pull/none
- Helm chart: support for service ports overrides by @sgrebnov in https://github.com/spiceai/spice/pull/5774
- Update spice cli login command with client-id and client-secret flags for Databricks by @ewgenius in https://github.com/spiceai/spice/pull/5788
- Fix bug where setting Cache-Control: no-cache doesn't compute the cache key by @phillipleblanc in https://github.com/spiceai/spice/pull/5779
- Update to datafusion-contrib/datafusion-table-providers#336 by @phillipleblanc in https://github.com/spiceai/spice/pull/5778
- Lru cache: limit single cached record size to u32::MAX (4GB) by @sgrebnov in https://github.com/spiceai/spice/pull/5772
- Fix LLMs calling nested MCP tools by @Jeadie in https://github.com/spiceai/spice/pull/5771
- MySQL: Set the character_set_results/character_set_client/character_set_connection session variables on connection setup by @Sevenannn in https://github.com/spiceai/spice/pull/5770
- Control the parallelism of acceleration refresh datasets with runtime.dataset_load_parallelism by @phillipleblanc in https://github.com/spiceai/spice/pull/5763
- Fix Iceberg predicates not matching the Arrow type of columns read from parquet files by @phillipleblanc in https://github.com/spiceai/spice/pull/5761
- fix: Use decimal_cmp for numerical BETWEEN in SQLite by @peasee in https://github.com/spiceai/spice/pull/5760
- Support product name override in databricks user agent string by @ewgenius in https://github.com/spiceai/spice/pull/5749
- Databricks U2M Token Provider support by @ewgenius in https://github.com/spiceai/spice/pull/5747
- Remove HTTP auth from LLM config and simplify Databricks models logic by using static headers by @Jeadie in https://github.com/spiceai/spice/pull/5742
- clear plan cache when dataset updates by @kczimm in https://github.com/spiceai/spice/pull/5741
- Support Databricks M2M auth in LLMs + Embeddings by @Jeadie in https://github.com/spiceai/spice/pull/5720
- Retrieve Github App tokens in background; make TokenProvider not async by @Jeadie in https://github.com/spiceai/spice/pull/5718
- Make 'token_providers' crate by @Jeadie in https://github.com/spiceai/spice/pull/5716
- Databricks AI: Embedding models & LLM streaming by @Jeadie in https://github.com/spiceai/spice/pull/5715

See the full list of changes at: v1.2.1...v1.2.2