Nejc Ilenic

Categorical features are automatically encoded as numerical data during the loading of CSV files. The label encoder constructed during that process should be modified and exposed for reuse during test...

This needs a discussion on what functionality should be implemented first. If anyone has a suggestion or wants to tackle any of this, feel free to propose a roadmap. Some...

Implement the inference stage

2

I.e. training in which only the paragraph matrix is updated (word vectors are pre-trained and frozen), as described in Q. V. Le et al., Distributed Representations of Sentences and Documents.

Implement the "resume training" functionality

2

The user should be able to continue training from the last saved checkpoint.

Compare the implementation with Genism's, identify bottlenecks.

Implement concatenation of word and paragraph vectors for the Distributed Memory model. Currently, only the sum operation is supported.

A subsampling approach described in Distributed Representations of Words and Phrases and their Compositionality, T. Mikolov et al.

Range type should have the ability to hold both f64 and i64 fields

1

Hi, [according to the docs](https://qdrant.tech/documentation/concepts/filtering/#range), it is possible to use range filtering on both float and integer payloads but the `Range` client type can only hold f64 optional fields, i.e.:...