October 2024, Release Update 23.6
Included are some notable Oracle AI Vector Search updates with Oracle Database 23ai, Release Update 23.6.
Note:
Certain features require the COMPATIBLE
initialization parameter to
be manually updated in order to be available for use. For information about the
COMPATIBLE
parameter and how to change it, see Oracle Database Upgrade
Guide.
If you are using RAC instances, certain features must be enabled using Oracle RAC two-stage rolling updates to ensure that any patches are enabled on all nodes. For more information, see Oracle Real Application Clusters Administration and Deployment Guide.
Feature | Description |
---|---|
Hybrid Search using Hybrid Vector Indexes |
You can use a hybrid vector index to index and query data using a combination of full-text search and vector similarity search. Hybrid searches can enhance the relevance (quality) of your search results by integrating the keyword matching capabilities of Oracle Text indexes with the semantic precision of vector indexes. An end-to-end indexing pipeline facilitates the indexing of documents without requiring you to be an expert in various text processing, chunking, or embedding strategies. As part of this feature, new preference helper procedures have been added to the existing A new PL/SQL package, A new dictionary view |
Updated AI Vector Search Workflow |
The AI Vector Search Workflow included in this guide has been updated to include support for hybrid vector indexes and hybrid search. |
Updated Documentation Map to GenAI Prompts |
The documentation map to GenAI prompts has been updated to include the new features available in Release Update 23.6. |
Extended SQL Quick Start |
The SQL Quick Start Using a Vector Embedding Model Uploaded into the Database has been extended to include steps for creating a hybrid vector index and running a hybrid search. SQL Quick Start Using a Vector Embedding Model Uploaded into the Database |
Support for Ollama |
You can use open embedding models (such as mxbai-embed-large, nomic-embed-text, or all-minilm) and large language models (such as Llama 3, Phi 3, Mistral, or Gemma 2) using the local host REST endpoint provider, Ollama. Ollama is a free and open-source command-line interface tool that allows you to run these models locally and privately on your Linux, Windows, and macOS systems. |
Support for |
In addition to The |
Integration with LlamaIndex |
Oracle AI Vector Search's integration with LlamaIndex allows you to use LlamaIndex's open-source data framework with vector search capabilities. This provides a powerful foundation for building sophisticated AI applications that can leverage both structured and unstructured data within the Oracle ecosystem. |
Jaccard Distance |
|
Hamming Distance |
|
Transaction Support for HNSW Indexes |
Transactions are maintained on tables with Hierarchical Navigable Small World (HNSW) index graphs by using data structures, such as private journal and shared journal. A private journal records vectors that are added or deleted by a transaction, whereas a shared journal records all the commit system change numbers (SCNs) and corresponding modified rows. If using RAC instances, you must enable Patch 36932885 using Oracle RAC two-stage rolling updates. |
HNSW Index Duplication and Reload |
By default, a duplication mechanism is used to create HNSW indexes in an Oracle RAC environment or when an HNSW index repopulation operation is triggered. When an Oracle Database instance starts again, a reload mechanism is triggered to recreate the HNSW graph in memory as quickly as possible. HNSW full checkpoints are used to reload the graph in memory. You can use the If using RAC instances, you must enable Patch 36932885 using Oracle RAC two-stage rolling updates. Understand HNSW Index Population Mechanisms in Oracle RAC or Single Instance |
Update to the default for |
The default value for the Understand HNSW Index Population Mechanisms in Oracle RAC or Single Instance |
Global and Local Partitioning for IVF Indexes |
Inverted File Flat (IVF) vector indexes support both global and local indexes on partitioned tables. By default, IVF indexes are globally partitioned by centroid. You can choose to create a local IVF index, which provides a one-to-one relationship between the base table partitions or subpartitions and the index partitions. If using RAC instances, you must enable Patch 36932885 using Oracle RAC two-stage rolling updates. |
|
New procedures are available with the
|
|
A new dictionary view |
Relational Data Vectorization |
You can use Oracle Machine Learning (OML) Feature Extraction algorithms with the Vectorize Relational Tables Using OML Feature Extraction Algorithms |
Document Reranking |
You can use the |
|
In addition to the existing textual input, the |
|
In addition to the existing textual input, the |
List of REST Endpoints |
You can refer to the list of REST endpoints and corresponding REST calls supported for all third-party REST providers. |
Parent topic: Oracle Database 23ai Release Updates