Oracle VecDB Python API Reference

The Oracle VecDB Python SDK provides functions for model operations, vector table management, vector data operations, vector search, and index management.

Models

Use these operations to load and manage embedding and reranking models.

Method	Description
`load_model`	Load an embedding or reranking model into the database.
`list_models`	List models available in the database.
`describe_model`	View a model’s metadata and status.
`drop_model`	Remove a model from the database.

Vector Tables

Use these operations to create and manage vector tables.

Method	Description
`describe_vector_database`	Retrieves summary counts for vector tables, vectors, and models in the caller schema.
`create_vector_table`	Creates a new vector table.
`list_vector_tables`	Lists vector tables available in the caller schema.
`describe_vector_table`	Retrieves metadata information about a vector table.
`update_vector_table_annotation`	Updates a vector table’s public comment and annotations.
`drop_vector_table`	Drops an existing vector table.

Manage Data

These functions enable you to generate embeddings, manage vector data, and load vectors.

Method	Description
`generate_embedding`	Generates vector embeddings from text.
`list_vectors`	Lists existing vectors by ID or with pagination from a specified vector table.
`load_vectors`	Bulk loads vector data from a CSV file in cloud storage into an existing vector table.
`upsert_vectors`	Inserts or updates vectors in a specified vector table.
`list_vector_load_jobs`	Lists vector load jobs.
`describe_vector_load_job`	Retrieves the status of a vector load job.
`get_vector_load_job_log`	Retrieves the log for a vector load job.
`delete_vectors`	Deletes existing vectors by ID from a specified vector table.

Search Data

These functions enable you to perform similarity search and rerank search results.

Method	Description
`query`	Performs similarity search with query text, a query vector, or a record ID.
`rerank`	Reranks documents against a query.

Indexes

These functions enable you to create, check, rebuild, and drop vector indexes.

Method	Description
`create_index`	Creates or updates vector and metadata indexes for a specified vector table.
`describe_index`	Retrieves vector index build status for a vector table.
`list_index_jobs`	Lists index jobs.
`describe_index_job`	Retrieves the status of an index job.
`get_index_job_log`	Retrieves the log for an index job.
`rebuild_index`	Rebuilds vector and metadata indexes for a vector table.
`drop_index`	Drops existing vector and metadata indexes.