SELECT d.id id,
row_number() over (partition by d.id order by d.id) chunk_id,
vc.chunk_offset chunk_offset,
vc.chunk_length chunk_length,
vc.chunk_text chunk,
vector_embedding(doc_model using vc.chunk_text as data) vector
FROM documentation_tab d,
vector_chunks(d.text by words max 100 overlap 10 split RECURSIVELY) vc;
it produces a parser error due to the vector_chunks function which uses non-standard parameters.
The following statement is based on an example from https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/generate-and-use-embeddings-end-end-search.html:
it produces a parser error due to the vector_chunks function which uses non-standard parameters.