Clear the attributes

Clear all cached SPLADE models from memory. This is useful for: - Freeing memory when models are no longer needed - Forcing a

Create an index on a field. Vector index types (HNSW, IVF, FLAT) can only be applied to vector fields. Inverted index (`InvertIndexPa

Retrieve data pointer

Retrieve dimension of accumulator

Generate sparse embedding vector for the input text. This method uses the SPLADE model to convert input text into a sparse vector rep

Get the list of all scalar field names in this document. Returns: list[str]: A list of field names. Empty if no fields.

Retrieve index id

Retrieve non-zero if the value is a object

Test if the iterator is valid

* \brief Grab (get or clone) a JSON value * \param val The pointer of value * \return Null indicates failure */

Retrieve mutable score value

Retrieve count of documents transformed (mutable)

Retrieve native handle

Retrieve size of padding

Set revision id

Set count of documents trained

Append a feature

Retrieve check point of storage

Retrieve pointer of data

Retrieve size of data

Retrieve type information

Retrieve type information

Retrieve dimension

Retrieve dimension

Returns distance

Generate dense embedding vector for the input text. This method uses the Sentence Transformer model to convert input text into a dens

Generate BM25 sparse embedding for the input text. This method computes BM25 scores for the input text using DashText's SparseVectorE

Retrieve the error code of parser

Check if the query contains an FTS (full-text search) condition. Returns: bool: True if `fts` is set with a query_string or match

Check if the query is based on a document ID. Returns: bool: True if `id` is set, False otherwise.

Test if the iterator is valid

Locking (shared)

Normalize score

Retrieve count of pending tasks in pool

Re-rank documents using Qwen's TextReRank API. Sends document texts to DashScope TextReRank service along with the query. Returns doc

Reset context