NaturalLanguageSearchTrainingConfig

Training config for the NATURAL_LANGUAGE_SEARCH problem type

KEY TYPE Description
SEARCH_CHUNK_SIZE int Chunk size for indexing the documents.
NUM_COMPLETION_TOKENS int Default for maximum number of tokens for chat answers. Reducing this will get faster responses which are more succinct
LARGER_EMBEDDINGS bool Use a higher dimension embedding model.
INDEX_FRACTION float Fraction of the chunk to use for indexing.
ABACUS_INTERNAL_MODEL bool Use a Abacus.AI LLM to answer questions about your data without using any external APIs
CHUNK_OVERLAP_FRACTION float Overlap in chunks while indexing the documents.
© Copyright