feat: add filtered full-text search benchmarking

[jamesgao-jpg]

Context

PR zilliztech/VectorDBBench#794 introduced first-class BM25 full-text search benchmarking. This PR extends that work with filtered FTS workloads, semantic relevance metrics, additional backend controls, and OSS OpenSearch support.

Summary

• add filtered FTS dataset preparation and propagate filter data through cases, task runners, and search runners
• implement FTS filtering for Milvus/Zilliz, Elastic Cloud, OSS OpenSearch, Turbopuffer, and Vespa paths
• add semantic recall, MRR, and NDCG handling for FTS results while separating filter-quality checks from concurrent performance queries
• expose FTS filter cases, BM25 controls, collection/index names, shard/replica settings, and backend search controls through CLI and frontend configuration
• add OSS OpenSearch FTS configuration and execution support
• publish curated filtered FTS result artifacts for the frontend result views

Compatibility

• existing unfiltered FTS cases remain supported
• backend-specific analyzer, BM25, filter-field, and search-level settings remain explicit in each backend case configuration
• mathematical BM25 ground-truth plumbing is removed in favor of semantic qrel-based quality metrics

Verification

• exact DCO sign-off verified for all 16 commits
• 46 focused FTS case, CLI, dataset, runner, formatting, metric, OSS OpenSearch, and Turbopuffer tests passed
• tests/test_fts_backend_filters.py was not collected locally because the optional elasticsearch SDK is not installed in the available environment

Signed-off-by: jamesgao-jpg james.gao@zilliz.com

[sre-ci-robot]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by: jamesgao-jpg
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.

Details

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

[jamesgao-jpg]

Superseded by #815, which removes filtered FTS frontend and result publication while retaining the unfiltered OSS OpenSearch and semantic FTS scope.