Add documentation for Agentic Memory semantic search and hybrid search APIs

[dhrubo-os]

Description

Add documentation for two new Agentic Memory search APIs introduced in OpenSearch 3.6:

1. Semantic Search Memory API (_semantic_search) — Search long-term memories using natural language queries with automatic embedding generation
2. Hybrid Search Memory API (_hybrid_search) — Search long-term memories using a combination of BM25 keyword matching and neural vector search with per-request weight tuning

Also updates the Agentic Memory APIs index page to include links to the new API pages.

New pages

• _ml-commons-plugin/api/agentic-memory-apis/semantic-search-memory.md
• _ml-commons-plugin/api/agentic-memory-apis/hybrid-search-memory.md

Updated pages

• _ml-commons-plugin/api/agentic-memory-apis/index.md — Added links to the two new API pages

Related issues

Resolves #12292

Related PRs

• ml-commons implementation: [FEATURE] Semantic and Hybrid Search APIs for Long-Term Memory Retrieval ml-commons#4658

Check List

• New functionality has been documented.
• Commits are signed per the DCO using --signoff.

By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.
For more information on following Developer Certificate of Origin and signing off your commits, please check here.

[github-actions]

Thank you for submitting your PR. The PR states are In progress (or Draft) -> Tech review -> Doc review -> Merged.

Before you submit your PR for doc review, make sure the content is technically accurate. If you need help finding a tech reviewer, tag a maintainer.

When you're ready for doc review, tag the assignee of this PR. The doc reviewer may push edits to the PR directly or leave comments and editorial suggestions for you to address (let us know in a comment if you have a preference).