Store word models in elasticsearch?

All word models logic currently happens entirely in python, with vector-related logic handled by gensim.

We might consider storing this data in elasticsearch instead. Basically, you could make a `parliament-uk-models` index to accompany `parliament-uk`, with the following fields + field types

- `date_start`: date
- `date_end`: date
- `term`: keyword
- `vector`: [dense vector](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html)

You can use the vector field to request, say, the N nearest neighbours based on cosine similarity.

This could work a lot faster than our current approach. Elasticsearch allows you to use an HNSW algorithm which takes some time to index, but saves time during search.

@BeritJanssen , what do you think?

Review the existing word-model logic in Python and the vector-related logic handled by gensim; the payload does not name specific files or tests. Compare the proposed parliament-uk-models index, its date, term, and dense-vector fields, and HNSW nearest-neighbour search with the current approach, then establish whether the Elasticsearch design is faster and complete.

Written by the indexing model from the issue text.