2.1 Restrictions for Oracle AI Vector Search

The following are restrictions for Oracle AI Vector Search in Oracle Database 23ai.

• The feature Open Neural Network Exchange (ONNX) is only supported on the x86-64 Linux platform. It is not supported on Microsoft Windows.
• To size the Vector Pool, use the VECTOR_MEMORY_SIZE initialization parameter. You can dynamically modify this parameter at the following levels:
  • At the multitenant container database (CDB) level, VECTOR_MEMORY_SIZE specifies the current size of the Vector Pool. Reducing the parameter value evicts vector usage that exceeds the new size.
  • At the pluggable database (PDB), level VECTOR_MEMORY_SIZE specifies the maximum Vector Pool usage allowed by a PDB. Reducing the parameter value evicts vector usage that exceeds the new quota.

• Table-Level Support

  • Truncate or move table operations are supported but will mark vector indexes unusable.

  • Partition management (PMOP) operations (for example, DROP, TRUNCATE, EXCHANGE, MERGE, MOVE, COALESCE, and SPLIT) are supported but will mark vector indexes unusable.

  • Adding a hash partition will also mark vector indexes unusable. However, adding a range or list partition will not mark vector indexes unusable.

  • Vector columns are not supported either in or as the following:

    • External tables
    • Index organized tables (IOTs) (neither as a primary key or as a non-key column)
    • Clusters or cluster tables
    • Global temporary tables
    • Blockchain tables
    • Immutable tables
    • Partitioning and subpartitioning keys
    • Primary and foreign keys
    • Unique and check constraints
    • Default value
    • Modify column
    • Manual segment space management (MSSM) tablespace (only a SYS user can create vectors as BasicFiles in MSSM tablespace)
    • Continuous Query Notification (CQN) queries
    • Non-vector indexes such as B-tree, bitmap, reverse key, text, spatial indexes

• Type-Level Support

  Vector column specification does not support the following:

  • Encryption clause
  • SecureFiles storage clause

• Query-Level Support

  • The partition row-limiting clause does not use vector indexes.

  • There is limited cost-based optimization support for vector indexes.

  • SQL constructs with vector columns do not support the following:

    • Distinct, Count Distinct
    • Order By, Group By
    • Join condition
    • Comparison operators (for example, >, <, =)

• Index-Level Support

  • Vector indexes do not support the following:

    • External tables
    • IOTs
    • Clusters or cluster tables
    • Global temporary tables
    • Blockchain tables
    • Immutable tables
    • Materialized views

  • There is no support for the following:

    • Vector index creation on non-vector columns (for example, VARCHAR, NUMBER, and so on)
    • Function-based vector index
    • Alter index DDL for vector indexes
    • Local partitioned vector indexes
    • Online creation of vector indexes

  • INMEMORY NEIGHBOR GRAPH restrictions include:

    • DMLs are not supported on base tables that have an INMEMORY NEIGHBOR GRAPH index.
• The latest python-oracledb, node-oracledb, JDBC, ODP.NET, and OCI drivers enable native binds.
  • All other SQL drivers need to use CLOBs or VARCHAR2 for binds and for vector definitions.
  • Oracle clients from release 19c and release 21c will see vectors as CLOBs.
• Integration with the following is not supported:
  • Vector indexes with transportable tablespaces are not supported with Oracle Data Pump.
  • Oracle Database Advanced Queuing
  • Oracle Database Gateways
• A maximum of 65535 dimensions is supported.
• Data redaction is not supported for the VECTOR data type. Specifically, you cannot:
  • Add a data redaction policy on a vector column.
  • Alter a table to modify a column to the VECTOR data type if the column has a redaction policy defined on it.