8.24.0

Enhancements

• Adds support for approximate KNN (ANN) for Elasticsearch and OpenSearch in ReactiveSearch API. The same search endpoint allows faceting and text filtering alongside kNN vector search. Note: For OpenSearch, ANN requires lucene or faiss engines for use with faceting and text filtering.
• When AI preferences are configured, setting queryVector in the API is optional

Example with ReactiveSearch API:

{
    "query": [
        {
            "id": "term",
            "type": "term",
            "dataField": "tags.keyword",
            "value": "Fashion",
            "execute": false
        },
        {
            "id": "one-line-search",
            "type": "search",
            "dataField": "one_liner",
            "value": "dresses",
            "execute": false
        },
        {
            "id": "search",
            "vectorDataField": "vector_data", // instead of "dataField" to indicate kNN search type
            "includeFields": [
                "name",
                "one_liner",
                "tags"
            ],
            "react": {
                "and": [
                    "term",
                    "one-line-search"
                ]
            },
            "value": "personalise"
        }
    ],
    "settings": {
        "useCache": false
    }
}

Using KNN when AI preferences are configured is as simple as setting vectorDataField instead of dataField. ReactiveSearch uses the AI preferences (embedding model configured, currently supports OpenAI) to generate a query vector from the user passed value. If AI preferences are not configured, queryVector is expected to be passed alongside.

Chore

• Updates to Go 1.23.5 (latest current version)
• Removes use of Sentry for remote error tracking

8.23.2

Fixes

• Auth headers handling to strip RS auth when querying ES endpoints

8.23.1

Fixes

• Updates synonyms index to avoid conflict with Elasticsearch's internal index.

8.23.0

Release Notes

Enhancements

• Cache Performance Improvement: The cache now uses a SHA-256 fixed-length key for hashing URL and request body. This reduces conversion overhead, leading to improved latency when caching with Redis and Ristretto.
• Golang Update: The server image has been updated to use Golang 1.23.1, ensuring compatibility with the latest features and security patches.

Fixes

• Disk: Increased the frequency of pipeline, analytics, and logs rollover to enhance disk management and performance.
• Cache Handling: Resolved an issue where invalid Redis cache entries were mishandled, preventing multiple initialization of Redis cache during misconfiguration.
• Analytics: Fixed a marshaling error in analytics mappings that occurred during rollover.
• Cache Hit/Miss Tracking: Added cache hit/miss information in the stage change context and optimized the applycache function for better performance.

8.22.8

Fixes

• Pipelines: Adds support for new input variable setResponseToKV for HTTPRequest and ElasticsearchQuery stages

8.22.7

Fixes

• Pipeline Environment Variable for defining a default HTTP URL. This can be used by a stage as a default URL to call.

8.22.6

Improvements

• Fixes various possible errors while execution of pipeline stages
• Other QoL improvements

8.22.5

Improvements

• #156 Improves validation by performing an API call when saving AI preferences
• #159 Return complete error messages for AI errors, and don't save to session when there is an error
• Docker publish OSS release

8.22.4

Fixes

• Pipeline: Boost stage fix when hits aren't scored
• Follow-up AI Answer: Adds support for Azure OpenAI

8.22.3

Fixes

• Fixes support for Azure OpenAI service endpoint
• Improves response support for GPT-4 and above models