All Classes and Interfaces

Class	Description
Chunk	Encapsulate chunks dbms_vector_chain.utl_to_chunks returns chunks in the following format: {"chunk_id": id, "chunk_offset": offset, "chunk_length": length, "chunk_data": "content"}
CreateOption	Options which configure the creation of database schema objects, such as tables and indexes.
DirectoryPreference	Document loader directory preference To specify a directory, dbms_vector_chain.utl_to_text expects the following JSON: {"dir": "directory name"}
Embedding	Encapsulate embeddings dbms_vector_chain.utl_to_embeddings returns embeddings in the following format: {"embed_id": "id", "embed_data": "content", "embed_vector": "[1, 2, 3, ...]"}
EmbeddingTable	Represents a database table where embeddings, text, and metadata are stored.
EmbeddingTable.Builder	A builder that configures and builds an EmbeddingTable.
FilePreference	Document loader file preference To specify a file, dbms_vector_chain.utl_to_text expects the following JSON: {"file": "filename"}
Index	Represents a database index.
IVFIndexBuilder	This index builder allows to configure an Inverted File Flat index on the embedding column of the EmbeddingTable.
JSONIndexBuilder	This index builder allows to configure indexes on one or several keys of the metadata column of the EmbeddingTable.
JSONIndexBuilder.Order	Use ASC or DESC to indicate whether the index should be created in ascending or descending order.
OracleDocumentLoader	Load documents Load documents either from the file system or the database.
OracleDocumentSplitter	Split documents Use dbms_vector_chain.utl_to_chunks to split documents.
OracleEmbeddingModel	Embed documents Use dbms_vector_chain.utl_to_embeddings to get embeddings.
OracleEmbeddingStore	An EmbeddingStore which uses AI Vector Search capabilities of Oracle Database.
OracleEmbeddingStore.Builder	Builder which configures and creates instances of OracleEmbeddingStore.
OracleSummaryLanguageModel	Summarize documents Use dbms_vector_chain.utl_to_summary to summarize documents.
TablePreference	Document loader file preference To specify a table, dbms_vector_chain.utl_to_text expects the following JSON: {"owner": "owner", "tablename": "table name", "colname": "column name"}