Add quantization option for pgvector with support for halfvec

[lucagiac81]

This PR adds a quantization option for pgvector.

The option is quantization_type, following the same naming as for pgvecto_rs. The option is added to both the web UI and CLI.

The supported values are none and halfvec.

• For the CLI, not specifying the option is equivalent to selecting none.
• When halfvec is selected, scalar FP16 quantization is applied when creating the index (HNSW or IVFFlat).
• Additional quantization types can be added in the future (e.g., bit vectors).

[lucagiac81]

/assign @XuanYang-cn

[lucagiac81]

Resolved conflicts due to recently merged PR #362

[sre-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: alwayslove2013, lucagiac81
To complete the pull request process, please assign xuanyang-cn after the PR has been reviewed.
You can assign the PR to them by writing /assign @xuanyang-cn in a comment when ready.

The full list of commands accepted by this bot can be found here.

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[jkatz]

FWIW I think this is a good start - we should add in binary quantization support as well. However, because BQ requires reranking, there may be some additional work to do here.